DOL-ILAB SDC - Section_9
Pablo Diego-Rosell, PhD
2021-10-02
- Setup filenames
- Setup data, functions and create dictionary for dataset review
- Direct PII: variables to be removed
- Direct PII-team: Encode field team names
- Small locations: Encode locations with pop <100,000 using random large numbers
- Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
- Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
- Matching and crosstabulations: Run automated PII check
- Open-ends: review responses for any sensitive information, redact as necessary
- GPS data: Displace
- Save processed data in Stata and SPSS format
rm(list=ls(all=t))Setup filenames
filename <- "Section_9" # !!!Update filename
functions_vers <- "functions_1.8.R" # !!!Update helper functions fileSetup data, functions and create dictionary for dataset review
source (functions_vers)Visually inspect variables in "dictionary.csv" and flag for risk, using the following flags:
# Direct PII: Respondent Names, Addresses, Identification Numbers, Phone Numbers
# Direct PII-team: Interviewer Names, other field team names
# Indirect PII-ordinal: Date of birth, Age, income, education, household composition.
# Indirect PII-categorical: Gender, education, ethnicity, nationality,
# occupation, employer, head of household, marital status
# GPS: Longitude, Latitude
# Small Location: Location (<100,000)
# Large Location (>100,000)
# Weight: weightVar
# Household ID: hhId,
# Open-ends: Review responses for any sensitive information, redact as necessary Direct PII: variables to be removed
# !!!No Direct PIIDirect PII-team: Encode field team names
# !!!No Direct PII-teamSmall locations: Encode locations with pop <100,000 using random large numbers
# !!!No small locationsIndirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
# Focus on variables with a "Lowest Freq" in dictionary of 30 or less.
# Top code high income to the 99.5 percentile
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q1)[na.exclude(mydata$s9q1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q1. In the last 7 days how much did the household spend on Bread and Cereals ? Sa n
## 0 12 17 20 24 25 26 30 35 36 37 38 40 45 50 53 54 60 67 68 70 72
## 15 2 1 4 2 1 1 4 2 2 1 1 7 2 15 1 2 5 1 2 6 1
## 75 80 87 88 90 98 100 104 105 108 110 112 114 115 116 118 126 128 132 135 138 140
## 1 4 1 1 1 1 28 1 2 2 1 1 1 1 1 1 1 2 1 1 1 10
## 144 145 147 148 150 152 155 157 158 160 162 164 165 166 168 170 171 175 176 180 183 185
## 1 1 1 1 31 1 2 1 1 8 2 1 3 1 3 2 1 3 2 5 1 2
## 188 189 190 195 196 199 200 202 205 210 214 215 216 218 220 222 224 225 226 230 231 235
## 1 1 4 3 1 1 56 2 1 12 1 4 1 1 3 1 9 1 3 7 3 2
## 236 237 238 239 240 242 245 246 248 250 251 252 254 255 256 258 259 260 264 265 266 267
## 1 1 2 1 13 3 12 1 3 17 2 4 1 3 1 2 2 5 2 3 5 1
## 270 273 276 277 279 280 281 282 284 285 288 290 292 293 294 295 300 301 302 304 305 306
## 7 1 1 1 1 16 2 2 2 1 3 2 1 1 4 2 61 4 2 1 2 2
## 307 308 309 310 312 315 316 317 318 320 322 324 325 328 329 330 334 335 336 337 339 340
## 1 4 2 6 3 8 2 1 1 9 2 2 1 2 1 9 1 2 5 2 1 11
## 344 345 346 348 349 350 351 352 354 355 356 357 359 360 364 365 366 367 368 369 370 371
## 1 3 3 1 2 45 2 1 2 4 1 4 1 8 7 1 1 2 6 1 6 2
## 372 373 376 377 378 380 383 384 385 386 387 388 390 392 395 397 398 399 400 401 402 403
## 2 1 1 1 11 15 2 3 7 1 2 1 3 6 2 1 1 2 44 1 1 1
## 404 406 408 409 410 412 413 415 416 417 418 420 422 424 425 427 429 430 431 432 434 435
## 3 1 2 1 4 1 2 1 1 2 1 31 1 1 4 1 1 6 1 2 5 1
## 436 438 440 442 446 447 448 449 450 452 455 456 460 462 464 466 467 468 469 470 474 475
## 2 4 7 1 1 1 15 1 26 1 11 2 11 3 1 4 2 1 1 5 1 5
## 476 478 480 481 483 484 485 486 487 488 490 493 495 496 498 500 501 502 504 505 506 508
## 7 2 13 1 2 1 1 1 2 2 30 1 2 1 3 113 2 1 15 1 2 6
## 510 515 517 518 520 522 523 524 525 526 528 529 530 532 534 536 537 540 544 545 546 550
## 12 1 1 10 9 1 2 2 12 2 1 1 6 9 2 3 1 7 2 2 4 10
## 552 553 554 555 556 560 564 567 569 570 572 574 575 577 578 579 580 582 583 584 585 588
## 2 1 1 2 1 34 4 3 1 5 1 5 4 1 4 1 1 3 1 5 3 7
## 590 592 595 596 599 600 602 604 605 606 608 609 610 611 612 613 615 616 617 620 624 625
## 6 1 8 3 1 28 2 2 1 1 1 1 6 1 3 1 1 3 1 4 2 1
## 627 630 632 635 636 639 640 644 645 647 650 651 652 654 655 656 658 660 661 662 665 666
## 1 28 3 2 1 1 8 11 2 1 12 5 1 1 1 1 3 8 1 3 4 1
## 668 670 672 674 675 676 677 678 679 680 685 686 688 689 690 692 693 695 696 700 702 704
## 2 3 16 1 2 1 1 1 1 4 1 2 2 2 3 1 4 1 1 79 1 1
## 705 707 708 710 714 715 720 722 725 726 728 730 731 732 733 735 737 738 740 741 742 745
## 2 2 1 1 6 1 6 2 1 1 3 2 1 2 1 23 1 1 7 1 5 1
## 746 749 750 752 754 755 756 760 766 770 774 775 777 779 780 782 784 785 788 789 790 791
## 1 1 15 3 1 3 9 1 1 18 1 1 3 1 5 1 3 3 1 1 3 3
## 792 793 794 795 797 798 800 803 805 806 808 810 812 816 819 820 821 823 825 826 827 829
## 1 2 1 1 1 9 27 1 5 1 1 2 3 1 3 1 1 1 2 2 1 2
## 830 833 834 835 840 842 843 850 851 854 855 860 861 868 870 872 875 876 880 882 884 890
## 1 2 2 1 33 1 1 8 1 2 1 2 1 1 2 1 6 1 2 8 1 2
## 892 896 898 900 903 910 915 920 925 928 929 930 931 938 940 945 948 950 955 960 962 965
## 1 1 1 11 2 6 1 2 1 1 1 3 1 2 1 6 1 2 1 2 1 1
## 966 970 976 980 987 988 995 996 997 998 1000 1007 1008 1015 1016 1020 1022 1029 1036 1040 1043 1050
## 2 1 1 7 2 1 1 1 1 1 36 1 2 3 1 2 1 1 1 5 1 15
## 1058 1060 1064 1068 1070 1071 1075 1080 1085 1088 1092 1100 1106 1110 1115 1119 1120 1128 1134 1145 1148 1155
## 1 1 2 1 1 1 1 2 2 1 1 3 1 1 1 1 5 1 2 1 1 1
## 1162 1170 1173 1176 1190 1193 1200 1218 1221 1225 1230 1240 1260 1275 1300 1323 1325 1330 1339 1358 1360 1372
## 2 1 1 2 2 1 14 1 1 1 1 1 4 1 3 1 1 3 1 2 2 1
## 1386 1400 1410 1424 1438 1448 1500 1554 1568 1584 1600 1610 1626 1680 1700 1720 1736 1848 1850 1890 1892 2000
## 1 14 1 1 1 1 12 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4
## 2016 2050 2072 2100 2138 2380 2700 2738 3004 3720 3880 4000 <NA>
## 1 1 1 3 1 1 1 1 1 1 1 2 6
## [1] "Frequency table after encoding"
## s9q1. In the last 7 days how much did the household spend on Bread and Cereals ? Sa n
## 0 12 17 20 24 25 26 30
## 15 2 1 4 2 1 1 4
## 35 36 37 38 40 45 50 53
## 2 2 1 1 7 2 15 1
## 54 60 67 68 70 72 75 80
## 2 5 1 2 6 1 1 4
## 87 88 90 98 100 104 105 108
## 1 1 1 1 28 1 2 2
## 110 112 114 115 116 118 126 128
## 1 1 1 1 1 1 1 2
## 132 135 138 140 144 145 147 148
## 1 1 1 10 1 1 1 1
## 150 152 155 157 158 160 162 164
## 31 1 2 1 1 8 2 1
## 165 166 168 170 171 175 176 180
## 3 1 3 2 1 3 2 5
## 183 185 188 189 190 195 196 199
## 1 2 1 1 4 3 1 1
## 200 202 205 210 214 215 216 218
## 56 2 1 12 1 4 1 1
## 220 222 224 225 226 230 231 235
## 3 1 9 1 3 7 3 2
## 236 237 238 239 240 242 245 246
## 1 1 2 1 13 3 12 1
## 248 250 251 252 254 255 256 258
## 3 17 2 4 1 3 1 2
## 259 260 264 265 266 267 270 273
## 2 5 2 3 5 1 7 1
## 276 277 279 280 281 282 284 285
## 1 1 1 16 2 2 2 1
## 288 290 292 293 294 295 300 301
## 3 2 1 1 4 2 61 4
## 302 304 305 306 307 308 309 310
## 2 1 2 2 1 4 2 6
## 312 315 316 317 318 320 322 324
## 3 8 2 1 1 9 2 2
## 325 328 329 330 334 335 336 337
## 1 2 1 9 1 2 5 2
## 339 340 344 345 346 348 349 350
## 1 11 1 3 3 1 2 45
## 351 352 354 355 356 357 359 360
## 2 1 2 4 1 4 1 8
## 364 365 366 367 368 369 370 371
## 7 1 1 2 6 1 6 2
## 372 373 376 377 378 380 383 384
## 2 1 1 1 11 15 2 3
## 385 386 387 388 390 392 395 397
## 7 1 2 1 3 6 2 1
## 398 399 400 401 402 403 404 406
## 1 2 44 1 1 1 3 1
## 408 409 410 412 413 415 416 417
## 2 1 4 1 2 1 1 2
## 418 420 422 424 425 427 429 430
## 1 31 1 1 4 1 1 6
## 431 432 434 435 436 438 440 442
## 1 2 5 1 2 4 7 1
## 446 447 448 449 450 452 455 456
## 1 1 15 1 26 1 11 2
## 460 462 464 466 467 468 469 470
## 11 3 1 4 2 1 1 5
## 474 475 476 478 480 481 483 484
## 1 5 7 2 13 1 2 1
## 485 486 487 488 490 493 495 496
## 1 1 2 2 30 1 2 1
## 498 500 501 502 504 505 506 508
## 3 113 2 1 15 1 2 6
## 510 515 517 518 520 522 523 524
## 12 1 1 10 9 1 2 2
## 525 526 528 529 530 532 534 536
## 12 2 1 1 6 9 2 3
## 537 540 544 545 546 550 552 553
## 1 7 2 2 4 10 2 1
## 554 555 556 560 564 567 569 570
## 1 2 1 34 4 3 1 5
## 572 574 575 577 578 579 580 582
## 1 5 4 1 4 1 1 3
## 583 584 585 588 590 592 595 596
## 1 5 3 7 6 1 8 3
## 599 600 602 604 605 606 608 609
## 1 28 2 2 1 1 1 1
## 610 611 612 613 615 616 617 620
## 6 1 3 1 1 3 1 4
## 624 625 627 630 632 635 636 639
## 2 1 1 28 3 2 1 1
## 640 644 645 647 650 651 652 654
## 8 11 2 1 12 5 1 1
## 655 656 658 660 661 662 665 666
## 1 1 3 8 1 3 4 1
## 668 670 672 674 675 676 677 678
## 2 3 16 1 2 1 1 1
## 679 680 685 686 688 689 690 692
## 1 4 1 2 2 2 3 1
## 693 695 696 700 702 704 705 707
## 4 1 1 79 1 1 2 2
## 708 710 714 715 720 722 725 726
## 1 1 6 1 6 2 1 1
## 728 730 731 732 733 735 737 738
## 3 2 1 2 1 23 1 1
## 740 741 742 745 746 749 750 752
## 7 1 5 1 1 1 15 3
## 754 755 756 760 766 770 774 775
## 1 3 9 1 1 18 1 1
## 777 779 780 782 784 785 788 789
## 3 1 5 1 3 3 1 1
## 790 791 792 793 794 795 797 798
## 3 3 1 2 1 1 1 9
## 800 803 805 806 808 810 812 816
## 27 1 5 1 1 2 3 1
## 819 820 821 823 825 826 827 829
## 3 1 1 1 2 2 1 2
## 830 833 834 835 840 842 843 850
## 1 2 2 1 33 1 1 8
## 851 854 855 860 861 868 870 872
## 1 2 1 2 1 1 2 1
## 875 876 880 882 884 890 892 896
## 6 1 2 8 1 2 1 1
## 898 900 903 910 915 920 925 928
## 1 11 2 6 1 2 1 1
## 929 930 931 938 940 945 948 950
## 1 3 1 2 1 6 1 2
## 955 960 962 965 966 970 976 980
## 1 2 1 1 2 1 1 7
## 987 988 995 996 997 998 1000 1007
## 2 1 1 1 1 1 36 1
## 1008 1015 1016 1020 1022 1029 1036 1040
## 2 3 1 2 1 1 1 5
## 1043 1050 1058 1060 1064 1068 1070 1071
## 1 15 1 1 2 1 1 1
## 1075 1080 1085 1088 1092 1100 1106 1110
## 1 2 2 1 1 3 1 1
## 1115 1119 1120 1128 1134 1145 1148 1155
## 1 1 5 1 2 1 1 1
## 1162 1170 1173 1176 1190 1193 1200 1218
## 2 1 1 2 2 1 14 1
## 1221 1225 1230 1240 1260 1275 1300 1323
## 1 1 1 1 4 1 3 1
## 1325 1330 1339 1358 1360 1372 1386 1400
## 1 3 1 2 2 1 1 14
## 1410 1424 1438 1448 1500 1554 1568 1584
## 1 1 1 1 12 1 1 1
## 1600 1610 1626 1680 1700 1720 1736 1848
## 1 1 1 1 1 1 1 1
## 1850 1890 1892 2000 2016 2050 2072 2087 or more
## 1 1 1 4 1 1 1 12
## <NA>
## 6
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q2)[na.exclude(mydata$s9q2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q2. In the last 7 days how much did the household spend on Roots and tubers ? Sa n
## 0 5 7 10 11 12 13 14 15 16 17 18 20 22 23 24 25 26 28 30 35 36
## 515 5 1 45 1 2 1 1 36 1 1 1 204 2 1 2 34 2 1 73 17 2
## 39 40 44 45 48 50 52 55 56 60 63 68 70 75 80 84 90 100 105 116 120 140
## 1 48 1 4 1 90 1 2 2 33 1 1 6 2 9 1 3 70 2 1 13 12
## 150 160 175 200 210 245 250 280 300 450 500 530 700 1000 <NA>
## 17 1 1 30 1 1 3 1 6 1 3 1 1 1 976
## [1] "Frequency table after encoding"
## s9q2. In the last 7 days how much did the household spend on Roots and tubers ? Sa n
## 0 5 7 10 11 12 13 14 15
## 515 5 1 45 1 2 1 1 36
## 16 17 18 20 22 23 24 25 26
## 1 1 1 204 2 1 2 34 2
## 28 30 35 36 39 40 44 45 48
## 1 73 17 2 1 48 1 4 1
## 50 52 55 56 60 63 68 70 75
## 90 1 2 2 33 1 1 6 2
## 80 84 90 100 105 116 120 140 150
## 9 1 3 70 2 1 13 12 17
## 160 175 200 210 245 250 280 300 360 or more
## 1 1 30 1 1 3 1 6 7
## <NA>
## 976
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q3)[na.exclude(mydata$s9q3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q3. In the last 7 days how much did the household spend on Vegetables ? Sa nakalipa
## 0 5 8 9 10 11 12 14 15 16 20 22 24 25 27 28 30 32 35 36 40 41
## 491 9 2 1 38 2 2 2 30 1 109 1 1 26 3 1 110 1 18 1 61 1
## 42 43 44 45 47 50 55 58 60 65 66 70 75 77 80 81 85 88 90 100 101 105
## 3 1 1 17 1 240 9 1 49 4 1 43 5 1 34 1 1 1 15 261 1 14
## 110 118 120 122 125 126 133 135 140 145 150 160 165 170 175 180 185 200 210 220 245 250
## 1 1 21 2 1 1 1 1 29 1 105 4 1 2 4 4 1 153 21 1 2 19
## 260 280 300 315 350 360 370 400 420 490 500 550 560 600 700 800 1050 1400 2180 <NA>
## 1 10 82 1 16 1 1 10 3 1 23 1 2 1 11 1 3 1 1 135
## [1] "Frequency table after encoding"
## s9q3. In the last 7 days how much did the household spend on Vegetables ? Sa nakalipa
## 0 5 8 9 10 11 12 14 15
## 491 9 2 1 38 2 2 2 30
## 16 20 22 24 25 27 28 30 32
## 1 109 1 1 26 3 1 110 1
## 35 36 40 41 42 43 44 45 47
## 18 1 61 1 3 1 1 17 1
## 50 55 58 60 65 66 70 75 77
## 240 9 1 49 4 1 43 5 1
## 80 81 85 88 90 100 101 105 110
## 34 1 1 1 15 261 1 14 1
## 118 120 122 125 126 133 135 140 145
## 1 21 2 1 1 1 1 29 1
## 150 160 165 170 175 180 185 200 210
## 105 4 1 2 4 4 1 153 21
## 220 245 250 260 280 300 315 350 360
## 1 2 19 1 10 82 1 16 1
## 370 400 420 490 500 550 560 600 700 or more
## 1 10 3 1 23 1 2 1 17
## <NA>
## 135
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q4)[na.exclude(mydata$s9q4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q4. In the last 7 days how much did the household spend on Meat ? Sa nakalipas na p
## 0 5 20 25 30 31 32 33 35 37 40 44 45 48 50 55 60 64 65 70 72 74
## 76 1 8 3 2 1 1 1 3 1 7 1 11 1 44 2 15 1 1 23 1 1
## 75 80 84 85 86 87 90 91 95 99 100 105 109 110 117 120 122 128 130 135 140 150
## 26 35 1 8 1 1 48 1 12 1 140 4 1 12 1 25 1 2 15 3 28 88
## 155 160 164 165 170 171 175 176 180 185 188 190 195 200 202 210 220 224 225 230 240 245
## 1 64 1 4 48 1 6 1 208 5 1 64 3 224 1 10 17 1 3 4 11 1
## 250 260 270 273 275 280 290 300 310 315 320 325 330 334 340 345 350 360 370 380 395 400
## 32 6 5 1 1 6 2 85 1 2 14 1 6 1 13 1 17 41 4 7 1 42
## 415 420 430 435 440 450 455 458 480 490 500 508 510 520 525 530 540 550 554 570 580 600
## 1 1 2 1 1 8 1 1 3 1 48 1 8 2 1 1 15 2 1 3 1 19
## 620 630 640 680 700 738 750 760 800 820 840 850 900 990 1000 1200 1295 1400 1500 1540 1800 2000
## 1 2 2 3 11 1 1 1 3 2 1 1 2 1 7 1 1 1 1 1 1 1
## 2240 2520 2700 3000 <NA>
## 1 1 1 2 496
## [1] "Frequency table after encoding"
## s9q4. In the last 7 days how much did the household spend on Meat ? Sa nakalipas na p
## 0 5 20 25 30 31 32 33
## 76 1 8 3 2 1 1 1
## 35 37 40 44 45 48 50 55
## 3 1 7 1 11 1 44 2
## 60 64 65 70 72 74 75 80
## 15 1 1 23 1 1 26 35
## 84 85 86 87 90 91 95 99
## 1 8 1 1 48 1 12 1
## 100 105 109 110 117 120 122 128
## 140 4 1 12 1 25 1 2
## 130 135 140 150 155 160 164 165
## 15 3 28 88 1 64 1 4
## 170 171 175 176 180 185 188 190
## 48 1 6 1 208 5 1 64
## 195 200 202 210 220 224 225 230
## 3 224 1 10 17 1 3 4
## 240 245 250 260 270 273 275 280
## 11 1 32 6 5 1 1 6
## 290 300 310 315 320 325 330 334
## 2 85 1 2 14 1 6 1
## 340 345 350 360 370 380 395 400
## 13 1 17 41 4 7 1 42
## 415 420 430 435 440 450 455 458
## 1 1 2 1 1 8 1 1
## 480 490 500 508 510 520 525 530
## 3 1 48 1 8 2 1 1
## 540 550 554 570 580 600 620 630
## 15 2 1 3 1 19 1 2
## 640 680 700 738 750 760 800 820
## 2 3 11 1 1 1 3 2
## 840 850 900 990 1000 1200 1295 1400 or more
## 1 1 2 1 7 1 1 10
## <NA>
## 496
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q5)[na.exclude(mydata$s9q5)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q5", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q5. In the last 7 days how much did the household spend on Fish? Sa nakalipas na pi
## 0 5 10 12 15 16 17 20 25 28 30 32 34 35 36 38 40 42 45 48 50 53
## 300 1 2 2 2 2 2 10 8 1 19 1 1 11 3 1 30 1 6 1 70 1
## 54 55 58 59 60 64 65 70 75 80 85 89 90 95 96 100 105 106 108 110 114 115
## 1 4 1 1 70 1 12 50 17 49 3 1 28 3 2 215 2 1 1 13 1 1
## 118 119 120 124 126 130 134 135 139 140 142 145 150 154 155 156 157 160 165 170 174 175
## 1 2 131 1 1 34 1 4 2 32 1 3 105 1 2 2 3 32 1 4 2 1
## 178 180 181 184 185 190 193 194 195 198 199 200 202 204 208 210 212 220 225 228 230 231
## 1 38 1 1 3 9 1 1 1 3 1 163 2 1 1 21 1 12 1 1 5 1
## 240 244 245 250 260 261 267 269 270 272 275 280 281 285 286 290 296 297 300 310 315 320
## 42 2 1 32 13 1 1 1 8 1 1 21 1 2 1 3 1 1 144 1 1 5
## 330 334 340 345 350 352 355 360 370 375 380 385 390 395 400 410 420 424 428 430 444 450
## 6 1 2 1 35 1 1 26 3 1 1 1 3 1 36 1 19 1 1 2 1 4
## 455 478 480 490 500 520 525 530 550 560 600 618 624 630 640 680 700 720 770 840 900 945
## 1 1 6 7 41 2 4 1 1 6 9 1 1 1 1 1 15 2 1 10 2 1
## 990 1000 1050 1260 1400 3254 <NA>
## 1 3 1 1 1 1 154
## [1] "Frequency table after encoding"
## s9q5. In the last 7 days how much did the household spend on Fish? Sa nakalipas na pi
## 0 5 10 12 15 16 17 20 25
## 300 1 2 2 2 2 2 10 8
## 28 30 32 34 35 36 38 40 42
## 1 19 1 1 11 3 1 30 1
## 45 48 50 53 54 55 58 59 60
## 6 1 70 1 1 4 1 1 70
## 64 65 70 75 80 85 89 90 95
## 1 12 50 17 49 3 1 28 3
## 96 100 105 106 108 110 114 115 118
## 2 215 2 1 1 13 1 1 1
## 119 120 124 126 130 134 135 139 140
## 2 131 1 1 34 1 4 2 32
## 142 145 150 154 155 156 157 160 165
## 1 3 105 1 2 2 3 32 1
## 170 174 175 178 180 181 184 185 190
## 4 2 1 1 38 1 1 3 9
## 193 194 195 198 199 200 202 204 208
## 1 1 1 3 1 163 2 1 1
## 210 212 220 225 228 230 231 240 244
## 21 1 12 1 1 5 1 42 2
## 245 250 260 261 267 269 270 272 275
## 1 32 13 1 1 1 8 1 1
## 280 281 285 286 290 296 297 300 310
## 21 1 2 1 3 1 1 144 1
## 315 320 330 334 340 345 350 352 355
## 1 5 6 1 2 1 35 1 1
## 360 370 375 380 385 390 395 400 410
## 26 3 1 1 1 3 1 36 1
## 420 424 428 430 444 450 455 478 480
## 19 1 1 2 1 4 1 1 6
## 490 500 520 525 530 550 560 600 618
## 7 41 2 4 1 1 6 9 1
## 624 630 640 680 700 720 770 840 857 or more
## 1 1 1 1 15 2 1 10 11
## <NA>
## 154
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q6)[na.exclude(mydata$s9q6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q6. In the last 7 days how much did the household spend on Dairy products and eggs ?
## 0 3 6 8 10 12 13 14 15 18 19 20 21 22 24 25 26 27 28 30 31 32
## 80 1 3 1 2 20 3 18 8 22 1 51 39 1 40 15 1 3 30 96 1 2
## 34 35 36 38 39 40 41 42 43 45 48 49 50 51 52 53 54 55 56 58 59 60
## 1 41 47 3 1 17 1 48 2 6 16 12 126 1 5 2 9 4 13 2 2 87
## 61 62 63 64 65 66 67 68 69 70 71 72 75 76 78 79 80 81 82 83 84 85
## 1 1 10 5 5 8 1 3 1 41 2 32 14 2 4 2 17 1 1 2 34 5
## 86 87 88 90 91 92 93 94 95 96 97 98 99 100 101 102 104 105 106 107 108 109
## 3 3 3 22 4 2 1 1 4 8 1 6 2 106 3 2 3 13 1 4 4 2
## 110 111 112 113 114 115 116 118 120 123 124 125 126 127 128 129 130 131 133 134 135 137
## 8 1 4 1 3 4 1 1 25 1 2 6 13 2 1 2 6 1 1 1 3 1
## 138 140 141 142 144 145 146 147 149 150 153 155 156 157 158 159 160 162 164 165 167 168
## 2 21 3 3 5 3 2 13 2 53 2 2 1 2 1 2 7 1 1 2 1 10
## 170 174 175 176 177 178 179 180 183 184 185 189 190 191 193 194 195 196 197 199 200 203
## 4 1 1 2 1 1 2 11 2 1 2 1 3 1 1 2 1 3 1 1 65 1
## 206 209 210 211 215 217 220 221 222 223 224 225 226 227 228 230 231 232 234 235 236 238
## 1 1 18 1 1 1 3 1 1 2 1 3 1 1 2 4 2 1 1 2 2 2
## 240 241 242 244 245 246 248 250 251 252 255 259 260 262 264 265 268 270 274 275 276 278
## 1 1 3 1 4 1 1 12 1 5 1 2 2 1 3 1 1 3 1 1 1 1
## 280 282 285 287 288 290 294 297 300 302 306 307 308 309 310 315 316 318 320 326 329 330
## 4 1 1 1 1 2 2 1 32 1 1 1 1 1 1 2 1 1 2 1 1 3
## 337 338 340 343 345 350 355 357 360 365 371 372 374 375 376 381 385 386 392 396 400 402
## 2 1 1 1 1 14 1 2 1 1 1 2 1 2 1 1 2 1 1 1 7 1
## 406 415 416 420 422 430 434 450 454 456 460 485 500 520 524 542 548 550 556 564 570 575
## 1 1 1 6 1 2 1 2 1 2 1 1 22 1 1 1 1 1 1 1 1 1
## 580 600 602 605 616 650 660 665 680 686 698 700 710 730 731 749 765 780 786 800 805 820
## 1 4 1 1 1 1 2 1 2 1 1 4 1 1 1 1 1 1 1 3 1 1
## 823 850 900 910 917 949 950 958 1000 1060 1125 2000 <NA>
## 1 2 2 1 1 1 1 1 3 1 1 1 380
## [1] "Frequency table after encoding"
## s9q6. In the last 7 days how much did the household spend on Dairy products and eggs ?
## 0 3 6 8 10 12 13 14 15
## 80 1 3 1 2 20 3 18 8
## 18 19 20 21 22 24 25 26 27
## 22 1 51 39 1 40 15 1 3
## 28 30 31 32 34 35 36 38 39
## 30 96 1 2 1 41 47 3 1
## 40 41 42 43 45 48 49 50 51
## 17 1 48 2 6 16 12 126 1
## 52 53 54 55 56 58 59 60 61
## 5 2 9 4 13 2 2 87 1
## 62 63 64 65 66 67 68 69 70
## 1 10 5 5 8 1 3 1 41
## 71 72 75 76 78 79 80 81 82
## 2 32 14 2 4 2 17 1 1
## 83 84 85 86 87 88 90 91 92
## 2 34 5 3 3 3 22 4 2
## 93 94 95 96 97 98 99 100 101
## 1 1 4 8 1 6 2 106 3
## 102 104 105 106 107 108 109 110 111
## 2 3 13 1 4 4 2 8 1
## 112 113 114 115 116 118 120 123 124
## 4 1 3 4 1 1 25 1 2
## 125 126 127 128 129 130 131 133 134
## 6 13 2 1 2 6 1 1 1
## 135 137 138 140 141 142 144 145 146
## 3 1 2 21 3 3 5 3 2
## 147 149 150 153 155 156 157 158 159
## 13 2 53 2 2 1 2 1 2
## 160 162 164 165 167 168 170 174 175
## 7 1 1 2 1 10 4 1 1
## 176 177 178 179 180 183 184 185 189
## 2 1 1 2 11 2 1 2 1
## 190 191 193 194 195 196 197 199 200
## 3 1 1 2 1 3 1 1 65
## 203 206 209 210 211 215 217 220 221
## 1 1 1 18 1 1 1 3 1
## 222 223 224 225 226 227 228 230 231
## 1 2 1 3 1 1 2 4 2
## 232 234 235 236 238 240 241 242 244
## 1 1 2 2 2 1 1 3 1
## 245 246 248 250 251 252 255 259 260
## 4 1 1 12 1 5 1 2 2
## 262 264 265 268 270 274 275 276 278
## 1 3 1 1 3 1 1 1 1
## 280 282 285 287 288 290 294 297 300
## 4 1 1 1 1 2 2 1 32
## 302 306 307 308 309 310 315 316 318
## 1 1 1 1 1 1 2 1 1
## 320 326 329 330 337 338 340 343 345
## 2 1 1 3 2 1 1 1 1
## 350 355 357 360 365 371 372 374 375
## 14 1 2 1 1 1 2 1 2
## 376 381 385 386 392 396 400 402 406
## 1 1 2 1 1 1 7 1 1
## 415 416 420 422 430 434 450 454 456
## 1 1 6 1 2 1 2 1 2
## 460 485 500 520 524 542 548 550 556
## 1 1 22 1 1 1 1 1 1
## 564 570 575 580 600 602 605 616 650
## 1 1 1 1 4 1 1 1 1
## 660 665 680 686 698 700 710 730 731
## 2 1 2 1 1 4 1 1 1
## 749 765 780 786 800 805 820 823 850
## 1 1 1 1 3 1 1 1 2
## 900 910 912 or more <NA>
## 2 1 10 380
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q7)[na.exclude(mydata$s9q7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q7. In the last 7 days how much did the household spend on Oils and fats ? Sa nakal
## 0 3 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
## 28 3 26 2 4 2 3 77 4 19 12 24 116 39 40 77 11 308 15 32 20 36
## 25 26 27 28 29 30 31 32 33 34 35 36 38 40 41 42 43 44 45 46 47 48
## 100 31 16 38 2 187 1 48 3 26 69 42 9 146 1 12 5 17 33 5 2 32
## 50 51 52 53 54 55 56 58 59 60 62 63 64 65 66 68 69 70 72 75 76 80
## 112 6 15 2 21 3 7 3 1 102 2 2 3 4 8 2 2 37 9 13 2 21
## 81 83 84 85 89 90 91 93 98 100 105 110 111 113 119 120 129 130 132 140 144 150
## 1 1 2 4 2 26 1 1 1 52 7 2 1 1 1 7 1 1 1 1 1 8
## 156 160 168 175 179 180 195 200 230 245 280 300 315 640 710 875 1120 <NA>
## 1 4 1 1 1 2 1 11 1 1 1 3 1 1 1 1 1 40
## [1] "Frequency table after encoding"
## s9q7. In the last 7 days how much did the household spend on Oils and fats ? Sa nakal
## 0 3 5 6 7 8 9 10 11
## 28 3 26 2 4 2 3 77 4
## 12 13 14 15 16 17 18 19 20
## 19 12 24 116 39 40 77 11 308
## 21 22 23 24 25 26 27 28 29
## 15 32 20 36 100 31 16 38 2
## 30 31 32 33 34 35 36 38 40
## 187 1 48 3 26 69 42 9 146
## 41 42 43 44 45 46 47 48 50
## 1 12 5 17 33 5 2 32 112
## 51 52 53 54 55 56 58 59 60
## 6 15 2 21 3 7 3 1 102
## 62 63 64 65 66 68 69 70 72
## 2 2 3 4 8 2 2 37 9
## 75 76 80 81 83 84 85 89 90
## 13 2 21 1 1 2 4 2 26
## 91 93 98 100 105 110 111 113 119
## 1 1 1 52 7 2 1 1 1
## 120 129 130 132 140 144 150 156 160
## 7 1 1 1 1 1 8 1 4
## 168 175 179 180 195 200 or more <NA>
## 1 1 1 2 1 22 40
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q8)[na.exclude(mydata$s9q8)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q8", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q8. In the last 7 days how much did the household spend on Fruits ? Sa nakalipas na
## 0 5 10 12 15 16 18 20 24 25 28 30 35 40 43 45 50 55 56 58 60 65
## 467 2 22 2 21 1 1 78 1 49 1 78 28 71 1 12 144 1 1 1 48 2
## 70 72 75 80 85 90 95 96 97 99 100 105 110 120 130 140 150 160 175 180 200 220
## 24 1 4 28 3 9 1 1 1 1 109 2 2 11 1 2 32 3 1 3 42 1
## 230 250 255 260 272 280 290 295 300 315 320 337 350 360 400 410 420 500 1000 1750 2000 <NA>
## 2 3 1 1 1 2 1 1 15 1 1 1 3 1 1 1 1 5 1 1 1 937
## [1] "Frequency table after encoding"
## s9q8. In the last 7 days how much did the household spend on Fruits ? Sa nakalipas na
## 0 5 10 12 15 16 18 20 24
## 467 2 22 2 21 1 1 78 1
## 25 28 30 35 40 43 45 50 55
## 49 1 78 28 71 1 12 144 1
## 56 58 60 65 70 72 75 80 85
## 1 1 48 2 24 1 4 28 3
## 90 95 96 97 99 100 105 110 120
## 9 1 1 1 1 109 2 2 11
## 130 140 150 160 175 180 200 220 230
## 1 2 32 3 1 3 42 1 2
## 250 255 260 272 280 290 295 300 315
## 3 1 1 1 2 1 1 15 1
## 320 337 350 360 400 410 420 500 or more <NA>
## 1 1 3 1 1 1 1 8 937
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q9)[na.exclude(mydata$s9q9)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q9", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q9. In the last 7 days how much did the household spend on Sugar, Jam, honey, sweets
## 0 2 3 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## 18 1 1 4 2 2 2 1 20 7 28 40 36 88 17 8 16 2 47 5 41 17
## 24 25 26 27 28 30 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47
## 66 47 47 11 69 105 22 1 10 26 19 3 7 16 76 3 51 12 35 62 45 3
## 48 49 50 51 52 53 54 55 56 57 58 59 60 62 63 64 65 66 68 69 70 72
## 73 2 103 3 29 4 9 10 37 1 10 1 75 3 3 8 8 8 3 9 20 9
## 73 74 75 76 77 78 80 81 84 85 86 87 88 89 90 91 92 93 94 95 96 97
## 1 1 16 2 3 6 31 1 28 2 2 1 12 1 25 24 12 1 1 1 14 1
## 98 100 102 103 104 105 106 110 112 115 116 117 119 120 121 122 123 124 125 126 129 130
## 30 72 1 1 9 34 1 6 20 1 3 1 5 24 1 1 1 1 2 5 1 4
## 132 135 138 140 144 148 150 154 155 156 158 160 161 165 168 169 175 179 180 182 189 192
## 4 3 1 6 6 1 22 2 2 1 1 1 5 1 2 1 2 1 6 2 1 1
## 196 200 210 211 215 235 240 250 251 260 278 280 300 312 315 322 350 370 400 420 500 526
## 1 28 4 1 1 1 2 2 1 1 1 1 8 1 1 2 1 1 1 1 6 1
## 600 720 820 966 985 <NA>
## 1 1 1 1 1 175
## [1] "Frequency table after encoding"
## s9q9. In the last 7 days how much did the household spend on Sugar, Jam, honey, sweets
## 0 2 3 5 6 7 8 9 10
## 18 1 1 4 2 2 2 1 20
## 11 12 13 14 15 16 17 18 19
## 7 28 40 36 88 17 8 16 2
## 20 21 22 23 24 25 26 27 28
## 47 5 41 17 66 47 47 11 69
## 30 32 33 34 35 36 37 38 39
## 105 22 1 10 26 19 3 7 16
## 40 41 42 43 44 45 46 47 48
## 76 3 51 12 35 62 45 3 73
## 49 50 51 52 53 54 55 56 57
## 2 103 3 29 4 9 10 37 1
## 58 59 60 62 63 64 65 66 68
## 10 1 75 3 3 8 8 8 3
## 69 70 72 73 74 75 76 77 78
## 9 20 9 1 1 16 2 3 6
## 80 81 84 85 86 87 88 89 90
## 31 1 28 2 2 1 12 1 25
## 91 92 93 94 95 96 97 98 100
## 24 12 1 1 1 14 1 30 72
## 102 103 104 105 106 110 112 115 116
## 1 1 9 34 1 6 20 1 3
## 117 119 120 121 122 123 124 125 126
## 1 5 24 1 1 1 1 2 5
## 129 130 132 135 138 140 144 148 150
## 1 4 4 3 1 6 6 1 22
## 154 155 156 158 160 161 165 168 169
## 2 2 1 1 1 5 1 2 1
## 175 179 180 182 189 192 196 200 210
## 2 1 6 2 1 1 1 28 4
## 211 215 235 240 250 251 260 278 280
## 1 1 1 2 2 1 1 1 1
## 300 312 315 322 350 370 400 420 500 or more
## 8 1 1 2 1 1 1 1 12
## <NA>
## 175
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q10)[na.exclude(mydata$s9q10)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q10", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q10. In the last 7 days how much did the household spend on Non-alcoholic drinks ? S
## 0 4 6 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26
## 6 2 4 1 2 14 1 8 4 12 7 2 11 28 14 134 21 33 12 13 66 4
## 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48
## 4 20 2 50 3 8 5 14 32 24 7 17 3 86 1 26 7 21 15 12 5 14
## 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70
## 31 154 7 9 2 8 9 16 7 3 4 73 1 5 11 7 10 4 6 6 2 70
## 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
## 4 8 3 5 20 6 14 9 6 40 1 4 7 22 6 8 3 6 6 10 1 6
## 94 95 96 97 98 99 100 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
## 5 3 6 2 30 2 153 4 2 5 12 8 3 6 1 10 3 2 1 4 2 4
## 117 118 119 120 122 123 124 125 126 127 128 129 130 132 133 134 135 138 140 141 142 144
## 2 4 5 18 4 2 4 2 5 1 5 1 6 2 1 7 2 2 29 2 5 3
## 145 147 148 150 152 153 154 156 158 159 160 161 162 164 165 166 168 170 172 174 175 176
## 3 14 4 52 2 1 9 2 3 1 9 1 2 1 2 4 6 4 1 2 6 2
## 178 180 181 184 185 186 187 189 190 191 193 194 195 196 198 199 200 206 207 208 210 212
## 2 5 2 3 1 2 1 5 1 1 1 1 1 8 2 1 55 1 1 1 9 2
## 214 215 217 220 222 223 225 226 229 231 236 238 240 242 245 246 248 250 252 253 256 258
## 1 3 1 1 1 1 1 1 1 2 2 1 1 1 3 2 1 6 2 1 1 2
## 260 263 266 273 276 280 285 286 288 290 294 300 304 308 311 313 314 317 320 324 337 338
## 1 1 2 1 1 7 1 1 1 2 3 23 1 1 1 1 1 1 1 1 1 1
## 343 350 354 356 360 361 378 400 413 414 420 430 441 490 500 525 539 630 652 665 682 690
## 1 11 1 1 1 1 1 2 1 1 1 1 1 2 6 1 1 1 1 1 1 1
## 710 872 1000 <NA>
## 1 1 1 132
## [1] "Frequency table after encoding"
## s9q10. In the last 7 days how much did the household spend on Non-alcoholic drinks ? S
## 0 4 6 8 9 10 11 12 13
## 6 2 4 1 2 14 1 8 4
## 14 15 16 17 18 19 20 21 22
## 12 7 2 11 28 14 134 21 33
## 23 24 25 26 27 28 29 30 31
## 12 13 66 4 4 20 2 50 3
## 32 33 34 35 36 37 38 39 40
## 8 5 14 32 24 7 17 3 86
## 41 42 43 44 45 46 47 48 49
## 1 26 7 21 15 12 5 14 31
## 50 51 52 53 54 55 56 57 58
## 154 7 9 2 8 9 16 7 3
## 59 60 61 62 63 64 65 66 67
## 4 73 1 5 11 7 10 4 6
## 68 69 70 71 72 73 74 75 76
## 6 2 70 4 8 3 5 20 6
## 77 78 79 80 81 82 83 84 85
## 14 9 6 40 1 4 7 22 6
## 86 87 88 89 90 91 92 94 95
## 8 3 6 6 10 1 6 5 3
## 96 97 98 99 100 102 103 104 105
## 6 2 30 2 153 4 2 5 12
## 106 107 108 109 110 111 112 113 114
## 8 3 6 1 10 3 2 1 4
## 115 116 117 118 119 120 122 123 124
## 2 4 2 4 5 18 4 2 4
## 125 126 127 128 129 130 132 133 134
## 2 5 1 5 1 6 2 1 7
## 135 138 140 141 142 144 145 147 148
## 2 2 29 2 5 3 3 14 4
## 150 152 153 154 156 158 159 160 161
## 52 2 1 9 2 3 1 9 1
## 162 164 165 166 168 170 172 174 175
## 2 1 2 4 6 4 1 2 6
## 176 178 180 181 184 185 186 187 189
## 2 2 5 2 3 1 2 1 5
## 190 191 193 194 195 196 198 199 200
## 1 1 1 1 1 8 2 1 55
## 206 207 208 210 212 214 215 217 220
## 1 1 1 9 2 1 3 1 1
## 222 223 225 226 229 231 236 238 240
## 1 1 1 1 1 2 2 1 1
## 242 245 246 248 250 252 253 256 258
## 1 3 2 1 6 2 1 1 2
## 260 263 266 273 276 280 285 286 288
## 1 1 2 1 1 7 1 1 1
## 290 294 300 304 308 311 313 314 317
## 2 3 23 1 1 1 1 1 1
## 320 324 337 338 343 350 354 356 360
## 1 1 1 1 1 11 1 1 1
## 361 378 400 413 414 420 430 441 490
## 1 1 2 1 1 1 1 1 2
## 500 or more <NA>
## 16 132
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q11)[na.exclude(mydata$s9q11)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q11", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q11. In the last 7 days how much did the household spend on Alcoholic drinks ? Sa na
## 0 1 10 15 16 17 18 20 21 22 25 27 28 29 30 32 34 35 36 37 38 40
## 188 1 4 1 1 1 1 16 2 2 9 2 2 1 5 1 1 7 1 3 4 57
## 42 43 44 45 47 48 49 50 53 60 65 70 75 80 82 84 85 86 88 90 94 95
## 11 2 5 52 3 5 1 33 1 9 2 7 5 15 1 6 7 1 1 25 2 3
## 100 105 114 115 120 135 140 145 150 152 160 162 168 170 175 180 182 195 200 210 225 245
## 76 3 2 1 6 4 1 1 12 2 3 2 2 3 1 4 1 1 24 1 1 1
## 250 265 280 288 294 300 301 315 320 400 500 700 800 900 1000 1120 1500 2000 <NA>
## 4 1 4 1 4 15 1 4 1 3 5 1 1 1 2 1 3 2 1583
## [1] "Frequency table after encoding"
## s9q11. In the last 7 days how much did the household spend on Alcoholic drinks ? Sa na
## 0 1 10 15 16 17 18 20
## 188 1 4 1 1 1 1 16
## 21 22 25 27 28 29 30 32
## 2 2 9 2 2 1 5 1
## 34 35 36 37 38 40 42 43
## 1 7 1 3 4 57 11 2
## 44 45 47 48 49 50 53 60
## 5 52 3 5 1 33 1 9
## 65 70 75 80 82 84 85 86
## 2 7 5 15 1 6 7 1
## 88 90 94 95 100 105 114 115
## 1 25 2 3 76 3 2 1
## 120 135 140 145 150 152 160 162
## 6 4 1 1 12 2 3 2
## 168 170 175 180 182 195 200 210
## 2 3 1 4 1 1 24 1
## 225 245 250 265 280 288 294 300
## 1 1 4 1 4 1 4 15
## 301 315 320 400 500 700 800 900
## 1 4 1 3 5 1 1 1
## 1000 1120 1500 or more <NA>
## 2 1 5 1583
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q12)[na.exclude(mydata$s9q12)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q12", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q12. In the last 7 days how much did the household spend on Tobacco ? Sa nakalipas n
## 0 3 4 5 6 9 10 12 14 15 16 18 20 21 24 25 26 27 28 30 31 32
## 3 2 1 5 2 1 18 3 7 5 1 4 34 4 3 7 1 2 10 32 1 1
## 35 36 37 38 39 40 42 45 49 50 52 53 54 56 58 60 61 63 64 68 70 72
## 30 2 2 4 1 48 10 13 2 47 2 1 1 6 2 31 1 7 2 2 78 1
## 75 76 80 81 84 85 86 88 90 93 95 96 98 100 105 108 111 112 114 120 122 123
## 2 1 33 1 8 1 2 3 17 1 1 1 1 65 26 2 1 4 2 44 1 1
## 126 128 129 130 132 133 135 140 141 148 150 152 154 160 167 168 170 175 180 181 182 189
## 3 1 1 1 1 4 4 72 1 1 20 2 4 14 1 1 2 21 2 1 1 2
## 190 192 196 200 208 210 217 220 224 225 240 245 250 252 259 260 263 266 270 273 280 294
## 2 1 3 31 1 38 1 1 3 1 2 9 3 2 3 1 1 7 1 3 72 4
## 300 301 308 315 331 350 360 370 378 380 385 400 420 470 480 490 500 518 532 560 600 602
## 14 1 1 22 1 18 2 1 1 1 4 2 8 1 1 2 4 1 2 7 1 1
## 700 770 800 810 840 <NA>
## 4 1 2 1 3 1181
## [1] "Frequency table after encoding"
## s9q12. In the last 7 days how much did the household spend on Tobacco ? Sa nakalipas n
## 0 3 4 5 6 9 10 12 14
## 3 2 1 5 2 1 18 3 7
## 15 16 18 20 21 24 25 26 27
## 5 1 4 34 4 3 7 1 2
## 28 30 31 32 35 36 37 38 39
## 10 32 1 1 30 2 2 4 1
## 40 42 45 49 50 52 53 54 56
## 48 10 13 2 47 2 1 1 6
## 58 60 61 63 64 68 70 72 75
## 2 31 1 7 2 2 78 1 2
## 76 80 81 84 85 86 88 90 93
## 1 33 1 8 1 2 3 17 1
## 95 96 98 100 105 108 111 112 114
## 1 1 1 65 26 2 1 4 2
## 120 122 123 126 128 129 130 132 133
## 44 1 1 3 1 1 1 1 4
## 135 140 141 148 150 152 154 160 167
## 4 72 1 1 20 2 4 14 1
## 168 170 175 180 181 182 189 190 192
## 1 2 21 2 1 1 2 2 1
## 196 200 208 210 217 220 224 225 240
## 3 31 1 38 1 1 3 1 2
## 245 250 252 259 260 263 266 270 273
## 9 3 2 3 1 1 7 1 3
## 280 294 300 301 308 315 331 350 360
## 72 4 14 1 1 22 1 18 2
## 370 378 380 385 400 420 470 480 490
## 1 1 1 4 2 8 1 1 2
## 500 518 532 560 600 602 700 770 782 or more
## 4 1 2 7 1 1 4 1 6
## <NA>
## 1181
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q13)[na.exclude(mydata$s9q13)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q13", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q13. In the last 7 days how much did the household spend on Spices and condiments ?
## 0 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 20 21 22 23 24
## 14 1 2 8 3 3 4 4 49 4 13 1 4 27 2 3 4 144 3 2 4 4
## 25 26 27 28 29 30 31 32 34 35 36 37 38 40 41 42 43 44 45 46 47 48
## 29 2 3 4 1 131 1 5 2 26 7 2 7 36 6 4 2 1 9 2 1 1
## 49 50 51 52 53 54 55 56 57 58 60 63 64 65 66 67 68 70 71 73 75 80
## 1 591 2 2 3 4 6 2 1 4 56 1 1 4 1 2 1 40 1 2 8 26
## 83 86 90 92 93 95 96 100 102 105 108 110 120 123 125 130 140 150 156 160 170 180
## 1 1 5 1 2 1 1 502 1 4 2 1 13 1 1 2 11 111 1 2 1 3
## 200 210 230 233 245 250 270 280 300 320 350 400 490 500 700 1000 2000 <NA>
## 137 1 1 1 1 13 1 1 65 1 7 4 1 15 2 1 1 31
## [1] "Frequency table after encoding"
## s9q13. In the last 7 days how much did the household spend on Spices and condiments ?
## 0 3 4 5 6 7 8 9 10
## 14 1 2 8 3 3 4 4 49
## 11 12 13 14 15 16 17 18 20
## 4 13 1 4 27 2 3 4 144
## 21 22 23 24 25 26 27 28 29
## 3 2 4 4 29 2 3 4 1
## 30 31 32 34 35 36 37 38 40
## 131 1 5 2 26 7 2 7 36
## 41 42 43 44 45 46 47 48 49
## 6 4 2 1 9 2 1 1 1
## 50 51 52 53 54 55 56 57 58
## 591 2 2 3 4 6 2 1 4
## 60 63 64 65 66 67 68 70 71
## 56 1 1 4 1 2 1 40 1
## 73 75 80 83 86 90 92 93 95
## 2 8 26 1 1 5 1 2 1
## 96 100 102 105 108 110 120 123 125
## 1 502 1 4 2 1 13 1 1
## 130 140 150 156 160 170 180 200 210
## 2 11 111 1 2 1 3 137 1
## 230 233 245 250 270 280 300 320 350
## 1 1 1 13 1 1 65 1 7
## 400 490 500 or more <NA>
## 4 1 19 31
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q14)[na.exclude(mydata$s9q14)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q14", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q14. In the last 7 days how much did the household spend on Prepared foods ? Sa naka
## 0 5 10 14 15 20 24 25 30 34 35 40 42 45 50 60 62 68 70 75 80 85
## 9 2 15 1 12 48 2 18 58 1 16 48 1 9 101 56 1 1 23 11 26 2
## 90 98 100 102 105 110 120 125 126 130 135 140 147 150 160 170 175 180 200 210 230 240
## 24 1 91 1 15 2 13 1 1 2 1 25 1 48 3 1 1 14 34 10 1 2
## 245 250 280 300 315 320 350 375 400 420 450 455 480 490 500 525 560 600 630 700 840 900
## 3 7 11 28 1 1 10 1 5 4 1 1 1 3 6 1 3 1 2 4 1 1
## 1000 <NA>
## 2 1445
## [1] "Frequency table after encoding"
## s9q14. In the last 7 days how much did the household spend on Prepared foods ? Sa naka
## 0 5 10 14 15 20 24 25 30
## 9 2 15 1 12 48 2 18 58
## 34 35 40 42 45 50 60 62 68
## 1 16 48 1 9 101 56 1 1
## 70 75 80 85 90 98 100 102 105
## 23 11 26 2 24 1 91 1 15
## 110 120 125 126 130 135 140 147 150
## 2 13 1 1 2 1 25 1 48
## 160 170 175 180 200 210 230 240 245
## 3 1 1 14 34 10 1 2 3
## 250 280 300 315 320 350 375 400 420
## 7 11 28 1 1 10 1 5 4
## 450 455 480 490 500 525 560 600 630
## 1 1 1 3 6 1 3 1 2
## 700 or more <NA>
## 8 1445
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q15other)[na.exclude(mydata$s9q15other)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q15other", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q15other. In the last 7 days how much did the household spend on other food items? Sa nak
## 0 5 7 8 10 15 20 21 24 25 30 34 35 36 40 45 50 58
## 1567 2 1 3 1 1 8 1 1 1 6 1 1 1 5 3 16 1
## 60 70 75 80 100 105 120 126 130 136 140 144 150 168 200 210 245 250
## 8 4 2 1 20 3 1 1 1 1 4 1 5 1 8 1 1 1
## 256 260 280 300 350 476 495 500 525 550 600 630 660 700 850 1000 1050 1148
## 1 1 2 4 1 1 1 3 1 1 1 1 1 2 1 2 1 1
## 1200 1400 1520 1900 2000 3500 5000 6000 15000 <NA>
## 1 1 1 1 3 2 1 1 1 574
## [1] "Frequency table after encoding"
## s9q15other. In the last 7 days how much did the household spend on other food items? Sa nak
## 0 5 7 8 10 15 20 21
## 1567 2 1 3 1 1 8 1
## 24 25 30 34 35 36 40 45
## 1 1 6 1 1 1 5 3
## 50 58 60 70 75 80 100 105
## 16 1 8 4 2 1 20 3
## 120 126 130 136 140 144 150 168
## 1 1 1 1 4 1 5 1
## 200 210 245 250 256 260 280 300
## 8 1 1 1 1 1 2 4
## 350 476 495 500 525 550 600 630
## 1 1 1 3 1 1 1 1
## 660 700 850 1000 1050 1148 1200 1400
## 1 2 1 2 1 1 1 1
## 1520 1670 or more <NA>
## 1 9 574
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q32)[na.exclude(mydata$s9q32)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q32", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q32. In the last 30 days how much did the household spend on Airtime, internet, other
## 0 5 10 11 12 13 15 17 18 20 21 22 23 24 25 26 27 28 30 32 33 34
## 79 2 25 1 20 14 41 10 5 55 1 17 21 8 4 17 1 1 101 4 1 15
## 35 36 39 40 42 44 45 46 47 48 50 51 52 54 55 60 63 64 65 66 68 69
## 5 8 9 62 1 6 13 8 1 15 109 2 20 4 2 110 1 3 1 3 9 4
## 70 72 75 80 83 84 88 90 92 96 99 100 102 104 105 110 112 120 126 128 132 136
## 8 9 4 67 1 1 17 10 9 5 2 194 3 8 1 1 1 60 1 1 2 4
## 140 144 146 148 150 156 160 161 165 168 170 175 176 180 184 192 195 200 210 215 219 220
## 2 6 1 1 79 3 16 1 1 1 2 1 2 11 4 3 2 108 2 1 1 1
## 224 225 230 240 243 250 254 255 260 264 270 272 276 280 284 288 296 300 304 306 308 320
## 1 2 2 19 1 10 1 1 5 4 1 1 2 4 1 1 1 91 2 1 1 9
## 324 325 336 344 350 352 356 360 364 392 400 408 416 420 430 440 450 492 500 510 517 520
## 2 1 1 1 6 1 1 3 2 1 19 3 1 2 1 1 2 2 28 1 1 1
## 528 550 600 660 680 720 750 800 836 900 930 960 1000 1050 1099 1400 1500 1650 1800 2000 2100 2640
## 1 1 16 2 1 1 2 4 1 2 1 1 7 1 1 1 2 1 1 2 1 1
## 3600 <NA>
## 1 505
## [1] "Frequency table after encoding"
## s9q32. In the last 30 days how much did the household spend on Airtime, internet, other
## 0 5 10 11 12 13 15 17
## 79 2 25 1 20 14 41 10
## 18 20 21 22 23 24 25 26
## 5 55 1 17 21 8 4 17
## 27 28 30 32 33 34 35 36
## 1 1 101 4 1 15 5 8
## 39 40 42 44 45 46 47 48
## 9 62 1 6 13 8 1 15
## 50 51 52 54 55 60 63 64
## 109 2 20 4 2 110 1 3
## 65 66 68 69 70 72 75 80
## 1 3 9 4 8 9 4 67
## 83 84 88 90 92 96 99 100
## 1 1 17 10 9 5 2 194
## 102 104 105 110 112 120 126 128
## 3 8 1 1 1 60 1 1
## 132 136 140 144 146 148 150 156
## 2 4 2 6 1 1 79 3
## 160 161 165 168 170 175 176 180
## 16 1 1 1 2 1 2 11
## 184 192 195 200 210 215 219 220
## 4 3 2 108 2 1 1 1
## 224 225 230 240 243 250 254 255
## 1 2 2 19 1 10 1 1
## 260 264 270 272 276 280 284 288
## 5 4 1 1 2 4 1 1
## 296 300 304 306 308 320 324 325
## 1 91 2 1 1 9 2 1
## 336 344 350 352 356 360 364 392
## 1 1 6 1 1 3 2 1
## 400 408 416 420 430 440 450 492
## 19 3 1 2 1 1 2 2
## 500 510 517 520 528 550 600 660
## 28 1 1 1 1 1 16 2
## 680 720 750 800 836 900 930 960
## 1 1 2 4 1 2 1 1
## 1000 1050 1099 1400 1404 or more <NA>
## 7 1 1 1 9 505
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q33)[na.exclude(mydata$s9q33)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q33", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q33. In the last 30 days how much did the household spend on Travel, transport, hotel
## 0 5 9 10 14 16 20 24 25 26 28 30 32 34 36 40 42 44
## 26 1 1 4 1 4 12 2 1 1 1 14 7 4 3 37 1 2
## 48 50 51 52 53 56 60 64 68 70 72 75 76 80 90 96 100 104
## 1 38 1 1 1 3 21 3 2 9 1 3 3 30 8 2 93 2
## 112 120 136 140 144 150 154 160 170 180 200 210 220 224 240 250 260 270
## 1 18 2 7 3 17 2 21 2 8 74 5 1 2 11 8 2 2
## 280 281 288 300 304 308 310 312 320 325 328 350 360 370 384 390 400 450
## 13 1 2 59 1 1 1 2 9 1 1 1 5 1 1 1 30 2
## 480 500 520 560 600 640 648 660 680 700 720 750 780 784 800 832 840 864
## 17 58 1 7 24 1 1 1 1 6 5 3 1 1 11 1 3 1
## 900 920 930 960 990 1000 1030 1032 1050 1056 1080 1140 1160 1200 1240 1250 1260 1280
## 12 1 1 3 1 16 1 1 1 1 1 2 4 16 1 1 1 1
## 1300 1320 1400 1470 1500 1580 1600 1620 1640 1680 1700 1800 1860 1920 2000 2080 2090 2100
## 1 2 1 1 12 1 1 1 1 3 1 2 1 1 13 1 1 2
## 2112 2120 2200 2250 2300 2400 2496 2500 2600 2700 2880 2980 3000 3420 4000 4050 4200 4500
## 1 1 2 1 1 3 1 2 1 1 3 1 9 1 5 1 2 2
## 4576 5200 5600 6000 7020 7840 8000 12800 61500 <NA>
## 1 1 1 1 1 1 1 1 1 1333
## [1] "Frequency table after encoding"
## s9q33. In the last 30 days how much did the household spend on Travel, transport, hotel
## 0 5 9 10 14 16 20 24
## 26 1 1 4 1 4 12 2
## 25 26 28 30 32 34 36 40
## 1 1 1 14 7 4 3 37
## 42 44 48 50 51 52 53 56
## 1 2 1 38 1 1 1 3
## 60 64 68 70 72 75 76 80
## 21 3 2 9 1 3 3 30
## 90 96 100 104 112 120 136 140
## 8 2 93 2 1 18 2 7
## 144 150 154 160 170 180 200 210
## 3 17 2 21 2 8 74 5
## 220 224 240 250 260 270 280 281
## 1 2 11 8 2 2 13 1
## 288 300 304 308 310 312 320 325
## 2 59 1 1 1 2 9 1
## 328 350 360 370 384 390 400 450
## 1 1 5 1 1 1 30 2
## 480 500 520 560 600 640 648 660
## 17 58 1 7 24 1 1 1
## 680 700 720 750 780 784 800 832
## 1 6 5 3 1 1 11 1
## 840 864 900 920 930 960 990 1000
## 3 1 12 1 1 3 1 16
## 1030 1032 1050 1056 1080 1140 1160 1200
## 1 1 1 1 1 2 4 16
## 1240 1250 1260 1280 1300 1320 1400 1470
## 1 1 1 1 1 2 1 1
## 1500 1580 1600 1620 1640 1680 1700 1800
## 12 1 1 1 1 3 1 2
## 1860 1920 2000 2080 2090 2100 2112 2120
## 1 1 13 1 1 2 1 1
## 2200 2250 2300 2400 2496 2500 2600 2700
## 2 1 1 3 1 2 1 1
## 2880 2980 3000 3420 4000 4050 4200 4500
## 3 1 9 1 5 1 2 2
## 4576 5200 5600 6000 6193 or more <NA>
## 1 1 1 1 5 1333
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q34)[na.exclude(mydata$s9q34)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q34", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q34. In the last 30 days how much did the household spend on Lottery tickets/gambling
## 0 3 5 6 10 15 20 25 27 30 35 40 50 60 80 90 100 105 120 150 160 180
## 7 1 1 2 13 6 34 1 1 18 2 18 30 8 9 4 30 2 6 15 5 1
## 200 220 240 280 300 320 360 365 400 420 450 480 500 600 900 1000 1400 1500 1800 2000 2100 2400
## 20 1 5 1 22 1 1 1 5 1 3 1 5 5 4 2 1 1 4 1 1 1
## 2500 3000 3650 4000 <NA>
## 1 1 1 1 1991
## [1] "Frequency table after encoding"
## s9q34. In the last 30 days how much did the household spend on Lottery tickets/gambling
## 0 3 5 6 10 15 20 25
## 7 1 1 2 13 6 34 1
## 27 30 35 40 50 60 80 90
## 1 18 2 18 30 8 9 4
## 100 105 120 150 160 180 200 220
## 30 2 6 15 5 1 20 1
## 240 280 300 320 360 365 400 420
## 5 1 22 1 1 1 5 1
## 450 480 500 600 900 1000 1400 1500
## 3 1 5 5 4 2 1 1
## 1800 2000 2100 2400 2500 3000 3312 or more <NA>
## 4 1 1 1 1 1 2 1991
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q35)[na.exclude(mydata$s9q35)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q35", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q35. In the last 30 days how much did the household spend on Clothing and shoes ? Sa
## 0 10 20 25 30 35 45 50 60 65 70 80 85 90 96 100 105 110
## 7 1 2 2 2 1 1 13 1 1 4 5 1 6 1 38 1 3
## 120 125 130 132 140 150 160 165 180 190 195 200 205 210 220 225 226 230
## 5 1 5 1 1 28 4 1 4 3 1 50 1 2 4 1 1 1
## 240 250 260 270 280 285 290 295 300 310 320 325 330 332 335 350 355 360
## 4 26 2 3 9 1 2 2 51 2 1 1 3 1 2 20 1 3
## 370 380 400 405 410 420 425 430 440 450 455 460 465 470 475 480 495 500
## 2 5 19 1 1 2 1 2 1 10 1 1 1 3 1 3 1 82
## 505 510 515 520 530 550 560 580 600 620 640 650 670 700 709 745 750 765
## 1 1 1 1 1 8 2 2 18 1 3 6 1 17 1 1 6 1
## 779 800 850 900 950 960 1000 1060 1070 1080 1100 1120 1140 1150 1200 1230 1250 1300
## 1 11 3 5 1 1 48 1 1 1 4 1 1 1 3 1 2 3
## 1350 1400 1440 1450 1500 1600 1880 1900 2000 2080 2100 2300 2500 2600 2790 2800 3000 3600
## 1 1 1 1 24 5 1 1 18 1 1 1 2 3 1 2 11 1
## 4500 5000 10000 16000 <NA>
## 1 2 1 1 1579
## [1] "Frequency table after encoding"
## s9q35. In the last 30 days how much did the household spend on Clothing and shoes ? Sa
## 0 10 20 25 30 35 45 50
## 7 1 2 2 2 1 1 13
## 60 65 70 80 85 90 96 100
## 1 1 4 5 1 6 1 38
## 105 110 120 125 130 132 140 150
## 1 3 5 1 5 1 1 28
## 160 165 180 190 195 200 205 210
## 4 1 4 3 1 50 1 2
## 220 225 226 230 240 250 260 270
## 4 1 1 1 4 26 2 3
## 280 285 290 295 300 310 320 325
## 9 1 2 2 51 2 1 1
## 330 332 335 350 355 360 370 380
## 3 1 2 20 1 3 2 5
## 400 405 410 420 425 430 440 450
## 19 1 1 2 1 2 1 10
## 455 460 465 470 475 480 495 500
## 1 1 1 3 1 3 1 82
## 505 510 515 520 530 550 560 580
## 1 1 1 1 1 8 2 2
## 600 620 640 650 670 700 709 745
## 18 1 3 6 1 17 1 1
## 750 765 779 800 850 900 950 960
## 6 1 1 11 3 5 1 1
## 1000 1060 1070 1080 1100 1120 1140 1150
## 48 1 1 1 4 1 1 1
## 1200 1230 1250 1300 1350 1400 1440 1450
## 3 1 2 3 1 1 1 1
## 1500 1600 1880 1900 2000 2080 2100 2300
## 24 5 1 1 18 1 1 1
## 2500 2600 2790 2800 3000 3600 4500 4709 or more
## 2 3 1 2 11 1 1 4
## <NA>
## 1579
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q36)[na.exclude(mydata$s9q36)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q36", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q36. In the last 30 days how much did the household spend on Recreation/entertainment
## 0 20 50 81 100 120 150 180 200 235 250 300 350 380 400 470 500 700 800 900 1000 1200
## 6 1 2 1 8 2 1 1 9 1 1 6 1 1 2 1 16 1 1 1 4 1
## 2000 3000 4000 5000 <NA>
## 4 1 1 2 2220
## [1] "Frequency table after encoding"
## s9q36. In the last 30 days how much did the household spend on Recreation/entertainment
## 0 20 50 81 100 120 150 180
## 6 1 2 1 8 2 1 1
## 200 235 250 300 350 380 400 470
## 9 1 1 6 1 1 2 1
## 500 700 800 900 1000 1200 2000 3000
## 16 1 1 1 4 1 4 1
## 4000 5000 or more <NA>
## 1 2 2220
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q37)[na.exclude(mydata$s9q37)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q37", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q37. In the last 30 days how much did the household spend on Personal items ? Sa na
## 0 6 7 8 10 12 14 15 16 18 20 21 22 24 25 27 28 30 32 33 34 35
## 19 1 3 3 3 1 11 8 2 5 19 8 1 22 11 1 30 26 17 5 1 15
## 36 38 40 42 44 45 46 48 49 50 51 52 53 54 55 56 57 58 60 63 64 65
## 5 6 30 7 4 6 3 16 3 92 1 2 3 2 5 35 1 2 35 2 16 6
## 66 67 68 70 71 72 73 75 76 78 79 80 82 83 84 85 86 87 88 89 90 91
## 5 2 5 18 3 13 2 8 4 5 2 39 2 2 12 1 4 1 2 4 9 1
## 92 93 94 95 96 97 98 99 100 101 102 104 105 106 108 109 110 112 113 114 115 116
## 7 1 3 3 11 1 2 10 248 1 1 2 13 4 1 6 12 3 1 3 4 3
## 117 118 119 120 121 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
## 1 11 9 26 1 5 9 3 2 6 1 6 1 6 3 1 2 1 3 3 1 4
## 141 142 143 144 145 146 147 149 150 152 153 154 155 156 157 158 159 160 162 163 164 165
## 1 1 2 3 4 1 2 2 129 1 1 1 2 5 1 2 1 13 3 1 5 4
## 166 168 169 170 172 173 174 175 176 177 178 179 180 181 183 184 185 186 187 188 190 191
## 4 4 1 3 1 1 3 1 1 1 1 1 10 1 2 1 2 1 1 1 6 1
## 192 193 194 196 197 200 202 204 205 206 208 209 210 212 216 217 219 220 222 225 227 228
## 1 2 1 3 1 204 1 2 1 2 2 2 4 1 1 1 3 6 1 2 1 2
## 229 230 233 234 235 236 238 240 243 244 246 250 256 259 260 264 268 270 273 277 278 280
## 1 6 1 2 1 2 5 10 1 3 1 59 2 2 4 1 3 2 1 1 2 4
## 283 284 285 286 287 290 295 296 299 300 305 308 309 310 315 320 322 324 325 326 330 332
## 1 1 2 1 2 1 3 2 1 119 1 2 1 3 1 4 2 2 2 1 1 1
## 335 338 339 340 345 347 348 349 350 355 356 360 367 370 371 375 380 390 392 400 409 416
## 1 4 2 3 1 1 1 1 16 1 1 2 1 3 1 1 1 2 1 23 1 1
## 417 424 429 430 436 448 450 460 480 482 497 500 504 511 520 529 530 538 545 550 560 573
## 1 1 2 1 1 1 5 1 2 1 1 91 1 1 2 1 1 1 1 2 1 1
## 578 595 600 610 628 634 650 660 700 744 750 800 867 870 944 980 985 1000 1200 1250 1500 2000
## 1 1 12 1 1 1 1 1 1 1 1 2 1 1 1 1 1 17 1 2 3 1
## 3000 <NA>
## 2 224
## [1] "Frequency table after encoding"
## s9q37. In the last 30 days how much did the household spend on Personal items ? Sa na
## 0 6 7 8 10 12 14 15
## 19 1 3 3 3 1 11 8
## 16 18 20 21 22 24 25 27
## 2 5 19 8 1 22 11 1
## 28 30 32 33 34 35 36 38
## 30 26 17 5 1 15 5 6
## 40 42 44 45 46 48 49 50
## 30 7 4 6 3 16 3 92
## 51 52 53 54 55 56 57 58
## 1 2 3 2 5 35 1 2
## 60 63 64 65 66 67 68 70
## 35 2 16 6 5 2 5 18
## 71 72 73 75 76 78 79 80
## 3 13 2 8 4 5 2 39
## 82 83 84 85 86 87 88 89
## 2 2 12 1 4 1 2 4
## 90 91 92 93 94 95 96 97
## 9 1 7 1 3 3 11 1
## 98 99 100 101 102 104 105 106
## 2 10 248 1 1 2 13 4
## 108 109 110 112 113 114 115 116
## 1 6 12 3 1 3 4 3
## 117 118 119 120 121 124 125 126
## 1 11 9 26 1 5 9 3
## 127 128 129 130 131 132 133 134
## 2 6 1 6 1 6 3 1
## 135 136 137 138 139 140 141 142
## 2 1 3 3 1 4 1 1
## 143 144 145 146 147 149 150 152
## 2 3 4 1 2 2 129 1
## 153 154 155 156 157 158 159 160
## 1 1 2 5 1 2 1 13
## 162 163 164 165 166 168 169 170
## 3 1 5 4 4 4 1 3
## 172 173 174 175 176 177 178 179
## 1 1 3 1 1 1 1 1
## 180 181 183 184 185 186 187 188
## 10 1 2 1 2 1 1 1
## 190 191 192 193 194 196 197 200
## 6 1 1 2 1 3 1 204
## 202 204 205 206 208 209 210 212
## 1 2 1 2 2 2 4 1
## 216 217 219 220 222 225 227 228
## 1 1 3 6 1 2 1 2
## 229 230 233 234 235 236 238 240
## 1 6 1 2 1 2 5 10
## 243 244 246 250 256 259 260 264
## 1 3 1 59 2 2 4 1
## 268 270 273 277 278 280 283 284
## 3 2 1 1 2 4 1 1
## 285 286 287 290 295 296 299 300
## 2 1 2 1 3 2 1 119
## 305 308 309 310 315 320 322 324
## 1 2 1 3 1 4 2 2
## 325 326 330 332 335 338 339 340
## 2 1 1 1 1 4 2 3
## 345 347 348 349 350 355 356 360
## 1 1 1 1 16 1 1 2
## 367 370 371 375 380 390 392 400
## 1 3 1 1 1 2 1 23
## 409 416 417 424 429 430 436 448
## 1 1 1 1 2 1 1 1
## 450 460 480 482 497 500 504 511
## 5 1 2 1 1 91 1 1
## 520 529 530 538 545 550 560 573
## 2 1 1 1 1 2 1 1
## 578 595 600 610 628 634 650 660
## 1 1 12 1 1 1 1 1
## 700 744 750 800 867 870 944 980
## 1 1 1 2 1 1 1 1
## 985 1000 or more <NA>
## 1 26 224
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q38)[na.exclude(mydata$s9q38)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q38", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q38. In the last 30 days how much did the household spend on Household items? Sa nak
## 0 4 15 17 18 20 24 25 29 30 32 35 38 40 42 45 46 48 50 52 54 55
## 10 1 1 1 3 4 5 2 1 2 1 2 1 8 3 2 2 2 42 3 4 4
## 56 57 58 59 60 61 62 63 65 66 68 69 70 71 72 74 75 76 77 78 80 81
## 4 1 1 1 14 1 3 2 2 3 2 1 9 1 9 2 1 1 1 4 16 1
## 82 83 84 85 86 87 88 89 90 91 92 93 94 96 97 99 100 101 102 104 105 106
## 1 1 3 2 1 1 5 1 4 1 2 2 1 7 1 1 208 1 1 2 5 2
## 108 109 110 112 114 116 117 118 119 120 122 123 124 125 126 128 129 130 131 132 134 135
## 5 1 4 3 2 4 2 2 1 22 2 1 2 1 3 5 2 7 2 2 2 1
## 136 137 138 139 140 144 145 146 148 149 150 152 153 154 155 156 158 159 160 162 164 165
## 5 1 3 1 6 11 3 2 3 1 150 6 1 1 2 5 2 3 13 2 2 2
## 166 167 168 169 170 171 172 173 174 176 178 180 181 184 185 187 189 190 192 193 196 198
## 2 1 6 1 4 2 2 2 1 5 2 24 1 2 1 1 1 1 5 1 1 5
## 200 202 204 206 208 210 211 213 214 215 216 217 218 220 222 224 226 228 230 232 234 235
## 306 1 1 2 2 4 2 1 1 1 10 1 2 8 2 3 2 4 5 4 2 2
## 236 240 241 244 245 246 247 248 250 252 253 255 256 258 260 261 264 265 266 268 270 272
## 1 15 1 2 1 3 1 3 72 2 1 3 3 1 8 2 3 3 1 3 5 4
## 275 276 278 280 284 288 289 292 293 295 296 300 304 306 308 311 312 314 316 318 320 322
## 1 4 2 17 2 7 1 3 1 1 3 236 2 2 1 1 2 1 2 1 9 1
## 324 325 326 328 330 332 334 336 338 340 342 344 345 348 350 354 356 357 360 368 369 370
## 3 1 2 3 5 1 2 1 3 6 1 1 2 1 27 1 2 2 11 2 1 2
## 372 376 379 380 384 386 390 392 394 395 396 398 400 402 404 405 408 410 416 420 424 428
## 2 2 1 7 2 1 2 2 1 1 3 1 67 1 1 2 6 2 1 4 1 2
## 430 431 432 436 440 444 448 450 452 456 459 460 466 468 470 472 476 480 486 488 492 496
## 1 2 4 2 4 1 2 8 1 2 1 1 2 1 1 4 2 8 1 2 1 1
## 498 500 505 508 510 511 520 524 526 536 544 550 560 565 576 578 580 584 588 592 594 596
## 1 186 1 1 1 1 9 2 1 1 1 2 5 1 2 1 1 1 1 1 1 1
## 600 616 620 624 630 632 634 636 640 646 650 652 680 696 698 700 708 720 730 750 752 756
## 24 1 1 1 3 1 1 1 1 1 4 1 5 1 1 10 1 2 1 1 1 1
## 763 765 792 800 810 860 876 888 900 960 970 975 1000 1020 1100 1104 1200 1248 1260 1280 1300 1380
## 1 1 1 20 1 1 1 1 2 1 1 1 36 1 1 1 3 1 1 1 1 1
## 1400 1410 1480 1500 1640 1720 1800 2000 3000 <NA>
## 1 1 1 10 1 1 1 5 2 51
## [1] "Frequency table after encoding"
## s9q38. In the last 30 days how much did the household spend on Household items? Sa nak
## 0 4 15 17 18 20 24 25
## 10 1 1 1 3 4 5 2
## 29 30 32 35 38 40 42 45
## 1 2 1 2 1 8 3 2
## 46 48 50 52 54 55 56 57
## 2 2 42 3 4 4 4 1
## 58 59 60 61 62 63 65 66
## 1 1 14 1 3 2 2 3
## 68 69 70 71 72 74 75 76
## 2 1 9 1 9 2 1 1
## 77 78 80 81 82 83 84 85
## 1 4 16 1 1 1 3 2
## 86 87 88 89 90 91 92 93
## 1 1 5 1 4 1 2 2
## 94 96 97 99 100 101 102 104
## 1 7 1 1 208 1 1 2
## 105 106 108 109 110 112 114 116
## 5 2 5 1 4 3 2 4
## 117 118 119 120 122 123 124 125
## 2 2 1 22 2 1 2 1
## 126 128 129 130 131 132 134 135
## 3 5 2 7 2 2 2 1
## 136 137 138 139 140 144 145 146
## 5 1 3 1 6 11 3 2
## 148 149 150 152 153 154 155 156
## 3 1 150 6 1 1 2 5
## 158 159 160 162 164 165 166 167
## 2 3 13 2 2 2 2 1
## 168 169 170 171 172 173 174 176
## 6 1 4 2 2 2 1 5
## 178 180 181 184 185 187 189 190
## 2 24 1 2 1 1 1 1
## 192 193 196 198 200 202 204 206
## 5 1 1 5 306 1 1 2
## 208 210 211 213 214 215 216 217
## 2 4 2 1 1 1 10 1
## 218 220 222 224 226 228 230 232
## 2 8 2 3 2 4 5 4
## 234 235 236 240 241 244 245 246
## 2 2 1 15 1 2 1 3
## 247 248 250 252 253 255 256 258
## 1 3 72 2 1 3 3 1
## 260 261 264 265 266 268 270 272
## 8 2 3 3 1 3 5 4
## 275 276 278 280 284 288 289 292
## 1 4 2 17 2 7 1 3
## 293 295 296 300 304 306 308 311
## 1 1 3 236 2 2 1 1
## 312 314 316 318 320 322 324 325
## 2 1 2 1 9 1 3 1
## 326 328 330 332 334 336 338 340
## 2 3 5 1 2 1 3 6
## 342 344 345 348 350 354 356 357
## 1 1 2 1 27 1 2 2
## 360 368 369 370 372 376 379 380
## 11 2 1 2 2 2 1 7
## 384 386 390 392 394 395 396 398
## 2 1 2 2 1 1 3 1
## 400 402 404 405 408 410 416 420
## 67 1 1 2 6 2 1 4
## 424 428 430 431 432 436 440 444
## 1 2 1 2 4 2 4 1
## 448 450 452 456 459 460 466 468
## 2 8 1 2 1 1 2 1
## 470 472 476 480 486 488 492 496
## 1 4 2 8 1 2 1 1
## 498 500 505 508 510 511 520 524
## 1 186 1 1 1 1 9 2
## 526 536 544 550 560 565 576 578
## 1 1 1 2 5 1 2 1
## 580 584 588 592 594 596 600 616
## 1 1 1 1 1 1 24 1
## 620 624 630 632 634 636 640 646
## 1 1 3 1 1 1 1 1
## 650 652 680 696 698 700 708 720
## 4 1 5 1 1 10 1 2
## 730 750 752 756 763 765 792 800
## 1 1 1 1 1 1 1 20
## 810 860 876 888 900 960 970 975
## 1 1 1 1 2 1 1 1
## 1000 1020 1100 1104 1200 1248 1260 1280
## 36 1 1 1 3 1 1 1
## 1300 1380 1400 1410 1480 1500 or more <NA>
## 1 1 1 1 1 20 51
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q39)[na.exclude(mydata$s9q39)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q39", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q39. In the last 30 days how much did the household spend on Firewood, kerosene, and
## 0 10 12 15 18 20 24 30 35 40 50 53 60 70 72 80 84 85 90 100 112 120
## 11 1 1 1 1 3 1 6 1 3 7 1 2 4 1 1 1 2 2 15 1 10
## 125 126 130 134 138 140 150 160 167 168 170 171 173 175 180 186 190 200 210 220 225 226
## 1 1 3 1 1 10 39 14 1 1 11 1 1 2 20 1 3 55 2 5 3 1
## 230 233 240 245 250 258 260 262 270 275 280 300 310 320 325 326 330 336 340 345 350 353
## 5 2 17 1 30 1 8 1 5 3 6 63 2 10 1 1 2 2 5 1 6 1
## 360 375 380 390 395 400 410 420 425 430 435 440 450 460 470 475 480 485 490 500 506 508
## 14 1 3 1 1 30 2 11 2 9 2 8 28 5 6 3 22 1 4 51 1 1
## 510 515 520 530 540 548 550 560 562 565 575 580 593 600 630 640 650 660 665 672 680 690
## 1 1 10 6 11 1 7 3 1 1 2 6 1 43 5 2 4 2 1 1 4 1
## 700 720 768 800 840 858 900 1000 1008 1150 1200 1377 1400 1500 1680 1800 2880 <NA>
## 7 6 1 8 2 1 16 3 1 1 3 1 1 3 1 1 1 1493
## [1] "Frequency table after encoding"
## s9q39. In the last 30 days how much did the household spend on Firewood, kerosene, and
## 0 10 12 15 18 20 24 30
## 11 1 1 1 1 3 1 6
## 35 40 50 53 60 70 72 80
## 1 3 7 1 2 4 1 1
## 84 85 90 100 112 120 125 126
## 1 2 2 15 1 10 1 1
## 130 134 138 140 150 160 167 168
## 3 1 1 10 39 14 1 1
## 170 171 173 175 180 186 190 200
## 11 1 1 2 20 1 3 55
## 210 220 225 226 230 233 240 245
## 2 5 3 1 5 2 17 1
## 250 258 260 262 270 275 280 300
## 30 1 8 1 5 3 6 63
## 310 320 325 326 330 336 340 345
## 2 10 1 1 2 2 5 1
## 350 353 360 375 380 390 395 400
## 6 1 14 1 3 1 1 30
## 410 420 425 430 435 440 450 460
## 2 11 2 9 2 8 28 5
## 470 475 480 485 490 500 506 508
## 6 3 22 1 4 51 1 1
## 510 515 520 530 540 548 550 560
## 1 1 10 6 11 1 7 3
## 562 565 575 580 593 600 630 640
## 1 1 2 6 1 43 5 2
## 650 660 665 672 680 690 700 720
## 4 2 1 1 4 1 7 6
## 768 800 840 858 900 1000 1008 1150
## 1 8 2 1 16 3 1 1
## 1200 1377 1400 1500 or more <NA>
## 3 1 1 6 1493
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q40)[na.exclude(mydata$s9q40)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q40", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q40. In the last 30 days how much did the household spend on Electricity ? Sa nakali
## 0 1 10 12 18 20 21 22 25 27 29 30 32 33 34 35 36 37 38 39 40 41
## 20 1 3 1 1 5 1 1 2 1 4 8 1 1 1 4 1 1 3 1 5 2
## 42 43 45 47 48 49 50 51 52 53 54 55 56 57 60 61 62 63 64 65 66 67
## 1 3 4 3 6 1 38 1 4 3 4 4 2 5 9 1 5 1 1 7 2 3
## 68 69 70 71 72 73 74 75 76 77 78 79 80 82 83 85 88 90 91 92 93 94
## 6 2 12 1 4 1 1 6 2 1 3 7 8 2 2 5 1 5 3 1 3 1
## 95 96 97 98 99 100 103 104 105 106 107 108 109 110 111 117 119 120 122 125 126 127
## 4 3 2 1 1 83 1 2 3 1 1 1 1 2 3 1 1 22 1 6 1 1
## 128 130 131 132 134 135 136 138 139 140 141 142 143 145 146 147 148 149 150 151 153 154
## 1 10 1 1 1 3 1 2 1 13 1 1 3 2 1 2 1 1 70 1 2 1
## 155 157 158 159 160 161 163 164 165 167 168 170 173 180 181 182 185 189 190 191 192 194
## 2 1 1 1 5 2 1 1 5 1 1 9 1 14 2 1 5 1 6 1 1 2
## 195 196 197 200 202 203 205 206 209 210 211 212 214 216 217 218 220 221 222 223 225 227
## 2 4 2 147 1 2 2 1 2 5 1 2 1 2 1 5 6 3 2 2 1 3
## 228 230 231 232 233 235 236 237 238 240 242 245 246 247 248 250 251 254 255 256 260 261
## 1 8 1 1 1 6 1 1 1 10 1 1 2 1 1 61 1 4 3 5 11 1
## 262 265 266 267 268 270 275 277 278 280 282 284 286 287 289 290 295 297 300 305 306 308
## 3 2 1 1 2 8 2 1 1 21 1 2 1 1 3 4 2 2 165 1 1 1
## 310 312 314 315 316 319 320 322 325 326 328 330 332 333 335 336 338 340 341 342 345 346
## 2 3 1 2 2 1 11 1 7 1 1 3 1 1 2 2 1 6 1 1 3 1
## 349 350 351 353 354 355 356 357 358 360 362 364 365 366 368 370 372 373 375 380 382 387
## 1 56 3 1 2 1 2 2 1 6 1 1 5 1 2 4 1 1 3 7 1 2
## 389 390 392 393 395 396 397 398 400 403 405 407 408 409 412 413 415 416 420 421 423 425
## 2 3 1 1 1 1 1 1 73 1 1 1 1 1 1 1 1 1 3 1 1 2
## 426 429 430 432 435 439 440 443 444 445 447 449 450 451 453 455 456 460 462 463 470 475
## 1 1 5 1 1 1 2 1 2 1 1 1 17 2 1 1 1 2 1 1 1 2
## 478 479 480 485 487 488 490 493 494 498 500 501 510 515 517 518 520 522 525 529 530 533
## 1 1 6 1 1 1 1 1 1 1 91 1 1 1 1 1 5 1 1 2 1 1
## 535 536 540 542 545 546 550 555 558 560 567 568 569 570 575 580 588 590 592 600 601 610
## 1 1 4 1 3 1 4 2 1 3 1 1 1 2 1 4 1 2 1 65 1 1
## 613 620 625 644 647 650 652 660 675 676 680 683 685 689 691 700 709 720 721 727 730 740
## 1 3 1 1 1 5 1 3 1 1 1 1 2 1 1 49 1 1 1 1 1 1
## 750 777 780 786 800 812 830 832 840 850 854 855 860 875 877 900 926 938 946 950 957 960
## 6 1 5 3 28 1 1 1 1 3 1 1 2 1 1 18 1 1 2 2 1 1
## 966 970 973 990 996 998 1000 1020 1026 1037 1040 1069 1080 1082 1100 1150 1200 1260 1270 1300 1387 1395
## 1 1 1 1 1 1 36 1 1 1 1 1 1 1 10 1 17 1 1 9 1 1
## 1400 1500 1550 1600 1700 1800 1900 2000 2003 2300 2400 2500 2600 2700 3000 3600 4900 9000 <NA>
## 2 12 1 2 2 1 3 4 1 1 1 3 1 1 2 1 1 1 351
## [1] "Frequency table after encoding"
## s9q40. In the last 30 days how much did the household spend on Electricity ? Sa nakali
## 0 1 10 12 18 20 21 22
## 20 1 3 1 1 5 1 1
## 25 27 29 30 32 33 34 35
## 2 1 4 8 1 1 1 4
## 36 37 38 39 40 41 42 43
## 1 1 3 1 5 2 1 3
## 45 47 48 49 50 51 52 53
## 4 3 6 1 38 1 4 3
## 54 55 56 57 60 61 62 63
## 4 4 2 5 9 1 5 1
## 64 65 66 67 68 69 70 71
## 1 7 2 3 6 2 12 1
## 72 73 74 75 76 77 78 79
## 4 1 1 6 2 1 3 7
## 80 82 83 85 88 90 91 92
## 8 2 2 5 1 5 3 1
## 93 94 95 96 97 98 99 100
## 3 1 4 3 2 1 1 83
## 103 104 105 106 107 108 109 110
## 1 2 3 1 1 1 1 2
## 111 117 119 120 122 125 126 127
## 3 1 1 22 1 6 1 1
## 128 130 131 132 134 135 136 138
## 1 10 1 1 1 3 1 2
## 139 140 141 142 143 145 146 147
## 1 13 1 1 3 2 1 2
## 148 149 150 151 153 154 155 157
## 1 1 70 1 2 1 2 1
## 158 159 160 161 163 164 165 167
## 1 1 5 2 1 1 5 1
## 168 170 173 180 181 182 185 189
## 1 9 1 14 2 1 5 1
## 190 191 192 194 195 196 197 200
## 6 1 1 2 2 4 2 147
## 202 203 205 206 209 210 211 212
## 1 2 2 1 2 5 1 2
## 214 216 217 218 220 221 222 223
## 1 2 1 5 6 3 2 2
## 225 227 228 230 231 232 233 235
## 1 3 1 8 1 1 1 6
## 236 237 238 240 242 245 246 247
## 1 1 1 10 1 1 2 1
## 248 250 251 254 255 256 260 261
## 1 61 1 4 3 5 11 1
## 262 265 266 267 268 270 275 277
## 3 2 1 1 2 8 2 1
## 278 280 282 284 286 287 289 290
## 1 21 1 2 1 1 3 4
## 295 297 300 305 306 308 310 312
## 2 2 165 1 1 1 2 3
## 314 315 316 319 320 322 325 326
## 1 2 2 1 11 1 7 1
## 328 330 332 333 335 336 338 340
## 1 3 1 1 2 2 1 6
## 341 342 345 346 349 350 351 353
## 1 1 3 1 1 56 3 1
## 354 355 356 357 358 360 362 364
## 2 1 2 2 1 6 1 1
## 365 366 368 370 372 373 375 380
## 5 1 2 4 1 1 3 7
## 382 387 389 390 392 393 395 396
## 1 2 2 3 1 1 1 1
## 397 398 400 403 405 407 408 409
## 1 1 73 1 1 1 1 1
## 412 413 415 416 420 421 423 425
## 1 1 1 1 3 1 1 2
## 426 429 430 432 435 439 440 443
## 1 1 5 1 1 1 2 1
## 444 445 447 449 450 451 453 455
## 2 1 1 1 17 2 1 1
## 456 460 462 463 470 475 478 479
## 1 2 1 1 1 2 1 1
## 480 485 487 488 490 493 494 498
## 6 1 1 1 1 1 1 1
## 500 501 510 515 517 518 520 522
## 91 1 1 1 1 1 5 1
## 525 529 530 533 535 536 540 542
## 1 2 1 1 1 1 4 1
## 545 546 550 555 558 560 567 568
## 3 1 4 2 1 3 1 1
## 569 570 575 580 588 590 592 600
## 1 2 1 4 1 2 1 65
## 601 610 613 620 625 644 647 650
## 1 1 1 3 1 1 1 5
## 652 660 675 676 680 683 685 689
## 1 3 1 1 1 1 2 1
## 691 700 709 720 721 727 730 740
## 1 49 1 1 1 1 1 1
## 750 777 780 786 800 812 830 832
## 6 1 5 3 28 1 1 1
## 840 850 854 855 860 875 877 900
## 1 3 1 1 2 1 1 18
## 926 938 946 950 957 960 966 970
## 1 1 2 2 1 1 1 1
## 973 990 996 998 1000 1020 1026 1037
## 1 1 1 1 36 1 1 1
## 1040 1069 1080 1082 1100 1150 1200 1260
## 1 1 1 1 10 1 17 1
## 1270 1300 1387 1395 1400 1500 1550 1600
## 1 9 1 1 2 12 1 2
## 1700 1800 1900 2000 2003 2300 2400 2427 or more
## 2 1 3 4 1 1 1 10
## <NA>
## 351
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q41)[na.exclude(mydata$s9q41)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q41", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q41. In the last 30 days how much did the household spend on Water ? Sa nakalipas na
## 0 5 8 10 12 14 15 16 20 24 25 26 28 30 35 36 40 44 45 48 50 55
## 22 2 1 15 2 1 2 2 68 1 8 1 3 21 1 1 21 1 6 3 33 1
## 56 60 63 70 72 75 80 84 85 90 96 100 105 107 120 125 127 130 133 135 140 144
## 2 28 1 4 2 5 7 2 1 20 1 47 1 1 22 7 1 7 2 2 12 1
## 145 150 160 161 163 165 168 169 170 180 187 190 191 197 200 204 210 211 215 216 220 222
## 3 48 16 1 8 1 4 1 2 17 1 1 1 1 62 3 2 2 1 2 4 1
## 225 226 228 233 234 236 240 248 250 254 256 260 261 270 272 280 285 291 293 295 300 306
## 4 4 1 1 2 2 17 2 23 1 1 1 1 2 1 5 2 2 1 1 63 1
## 320 324 327 330 350 358 360 365 370 375 379 380 384 385 386 392 395 400 409 410 420 421
## 6 1 1 2 8 1 4 1 1 3 1 2 2 1 1 1 1 22 1 1 3 1
## 440 445 449 450 454 470 475 480 490 500 516 518 525 540 550 560 564 565 570 600 603 630
## 1 1 1 8 1 1 1 2 1 28 1 1 1 2 1 3 1 1 1 17 1 1
## 650 660 689 700 750 800 900 930 1000 1050 1100 1196 1200 1500 1800 2800 3600 6000 <NA>
## 4 1 1 6 3 6 5 1 4 1 2 1 4 1 1 1 1 1 1399
## [1] "Frequency table after encoding"
## s9q41. In the last 30 days how much did the household spend on Water ? Sa nakalipas na
## 0 5 8 10 12 14 15 16
## 22 2 1 15 2 1 2 2
## 20 24 25 26 28 30 35 36
## 68 1 8 1 3 21 1 1
## 40 44 45 48 50 55 56 60
## 21 1 6 3 33 1 2 28
## 63 70 72 75 80 84 85 90
## 1 4 2 5 7 2 1 20
## 96 100 105 107 120 125 127 130
## 1 47 1 1 22 7 1 7
## 133 135 140 144 145 150 160 161
## 2 2 12 1 3 48 16 1
## 163 165 168 169 170 180 187 190
## 8 1 4 1 2 17 1 1
## 191 197 200 204 210 211 215 216
## 1 1 62 3 2 2 1 2
## 220 222 225 226 228 233 234 236
## 4 1 4 4 1 1 2 2
## 240 248 250 254 256 260 261 270
## 17 2 23 1 1 1 1 2
## 272 280 285 291 293 295 300 306
## 1 5 2 2 1 1 63 1
## 320 324 327 330 350 358 360 365
## 6 1 1 2 8 1 4 1
## 370 375 379 380 384 385 386 392
## 1 3 1 2 2 1 1 1
## 395 400 409 410 420 421 440 445
## 1 22 1 1 3 1 1 1
## 449 450 454 470 475 480 490 500
## 1 8 1 1 1 2 1 28
## 516 518 525 540 550 560 564 565
## 1 1 1 2 1 3 1 1
## 570 600 603 630 650 660 689 700
## 1 17 1 1 4 1 1 6
## 750 800 900 930 1000 1050 1100 1196
## 3 6 5 1 4 1 2 1
## 1200 1355 or more <NA>
## 4 5 1399
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q42)[na.exclude(mydata$s9q42)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q42", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q42. In the last 30 days how much did the household spend on House rent/mortgage ? S
## 0 20 35 50 100 140 150 200 240 250 300 324 350 500 600 700 750 800 900 1000 1200 1250
## 3 3 1 5 7 1 1 5 1 2 7 1 3 6 3 3 1 3 1 11 4 1
## 1300 1500 1700 2000 2300 2500 3000 3500 5000 <NA>
## 2 5 3 4 1 2 4 1 1 2200
## [1] "Frequency table after encoding"
## s9q42. In the last 30 days how much did the household spend on House rent/mortgage ? S
## 0 20 35 50 100 140 150 200
## 3 3 1 5 7 1 1 5
## 240 250 300 324 350 500 600 700
## 1 2 7 1 3 6 3 3
## 750 800 900 1000 1200 1250 1300 1500
## 1 3 1 11 4 1 2 5
## 1700 2000 2300 2500 3000 3500 4287 or more <NA>
## 3 4 1 2 4 1 1 2200
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q43)[na.exclude(mydata$s9q43)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q43", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q43. In the last 30 days how much did the household spend on Fixing home damage or im
## 0 5 10 24 28 30 35 50 60 100 120 125 150 200 250
## 4 1 1 1 1 1 1 3 1 1 4 1 3 2 1
## 300 350 400 416 450 500 520 540 600 675 700 720 800 850 856
## 4 1 3 1 1 12 1 1 4 1 1 1 1 1 1
## 900 1000 1100 1200 1250 1425 1500 1700 1800 1984 2000 2200 2300 2500 2700
## 1 11 2 2 3 1 6 1 1 1 13 2 1 1 1
## 2800 3000 3500 3720 4000 4050 5000 6000 6200 6300 7000 8000 10000 11000 12000
## 2 6 3 1 7 1 8 2 1 1 2 4 4 1 1
## 13000 14000 15000 18000 20000 23000 25000 26000 27000 30000 40000 50000 60000 70000 1e+05
## 2 1 7 1 7 1 1 2 1 7 2 1 1 1 1
## 220000 1e+06 <NA>
## 1 1 2107
## [1] "Frequency table after encoding"
## s9q43. In the last 30 days how much did the household spend on Fixing home damage or im
## 0 5 10 24 28 30 35
## 4 1 1 1 1 1 1
## 50 60 100 120 125 150 200
## 3 1 1 4 1 3 2
## 250 300 350 400 416 450 500
## 1 4 1 3 1 1 12
## 520 540 600 675 700 720 800
## 1 1 4 1 1 1 1
## 850 856 900 1000 1100 1200 1250
## 1 1 1 11 2 2 3
## 1425 1500 1700 1800 1984 2000 2200
## 1 6 1 1 1 13 2
## 2300 2500 2700 2800 3000 3500 3720
## 1 1 1 2 6 3 1
## 4000 4050 5000 6000 6200 6300 7000
## 7 1 8 2 1 1 2
## 8000 10000 11000 12000 13000 14000 15000
## 4 4 1 1 2 1 7
## 18000 20000 23000 25000 26000 27000 30000
## 1 7 1 1 2 1 7
## 40000 50000 60000 70000 1e+05 220000 266800 or more
## 2 1 1 1 1 1 1
## <NA>
## 2107
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q44)[na.exclude(mydata$s9q44)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q44", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q44. In the last 30 days how much did the household spend on Religious expenses or ot
## 0 1 2 5 7 8 10 15 17 20 25 28 30 35 40 45 50 55 60 70 75 80
## 11 2 2 36 1 1 75 11 1 267 4 1 26 2 59 1 88 1 13 1 1 55
## 100 108 110 120 125 140 150 160 180 200 208 210 240 250 260 300 320 400 450 500 508 520
## 90 1 1 6 1 2 14 5 1 46 1 2 6 3 1 8 1 10 1 7 1 1
## 600 680 700 800 1000 1080 2000 <NA>
## 3 1 3 1 8 1 1 1410
## [1] "Frequency table after encoding"
## s9q44. In the last 30 days how much did the household spend on Religious expenses or ot
## 0 1 2 5 7 8 10 15
## 11 2 2 36 1 1 75 11
## 17 20 25 28 30 35 40 45
## 1 267 4 1 26 2 59 1
## 50 55 60 70 75 80 100 108
## 88 1 13 1 1 55 90 1
## 110 120 125 140 150 160 180 200
## 1 6 1 2 14 5 1 46
## 208 210 240 250 260 300 320 400
## 1 2 6 3 1 8 1 10
## 450 500 508 520 600 680 700 800
## 1 7 1 1 3 1 3 1
## 1000 or more <NA>
## 10 1410
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q45)[na.exclude(mydata$s9q45)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q45", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q45. In the last 30 days how much did the household spend on Charitable donations ?
## 0 1 5 10 12 15 20 22 25 30 35 36 38 40 50 58 60 70 75 80 100 120
## 8 1 16 42 1 2 137 1 2 24 3 1 1 13 59 1 5 3 1 14 47 3
## 150 180 200 250 280 300 400 500 600 1000 1500 <NA>
## 6 2 12 2 1 3 1 5 2 5 1 1871
## [1] "Frequency table after encoding"
## s9q45. In the last 30 days how much did the household spend on Charitable donations ?
## 0 1 5 10 12 15 20 22
## 8 1 16 42 1 2 137 1
## 25 30 35 36 38 40 50 58
## 2 24 3 1 1 13 59 1
## 60 70 75 80 100 120 150 180
## 5 3 1 14 47 3 6 2
## 200 250 280 300 400 500 600 1000 or more
## 12 2 1 3 1 5 2 6
## <NA>
## 1871
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q46)[na.exclude(mydata$s9q46)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q46", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q46. In the last 30 days how much did the household spend on Weddings ? Sa nakalipas
## 0 20 50 60 70 80 90 100 120 150 200 220 250 300 350 500 700 850
## 2 4 5 2 2 1 1 39 3 9 31 1 4 12 3 13 2 1
## 1000 1200 1500 1700 2000 2500 3000 5000 7000 15000 25000 <NA>
## 3 1 2 1 4 1 2 3 2 3 2 2137
## [1] "Frequency table after encoding"
## s9q46. In the last 30 days how much did the household spend on Weddings ? Sa nakalipas
## 0 20 50 60 70 80 90
## 2 4 5 2 2 1 1
## 100 120 150 200 220 250 300
## 39 3 9 31 1 4 12
## 350 500 700 850 1000 1200 1500
## 3 13 2 1 3 1 2
## 1700 2000 2500 3000 5000 7000 15000
## 1 4 1 2 3 2 3
## 25000 or more <NA>
## 2 2137
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q47)[na.exclude(mydata$s9q47)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q47", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q47. In the last 30 days how much did the household spend on Funerals (including outs
## 0 2 5 10 18 20 25 30 32 35 40 45 50 55 60
## 2 1 3 23 1 40 3 8 1 1 13 1 55 1 4
## 70 85 100 105 120 150 160 200 208 250 300 320 400 500 600
## 1 1 54 1 1 7 1 24 1 1 7 1 3 15 2
## 700 900 1000 1500 2000 2064 2500 3500 5000 10000 12000 18000 20000 40000 60000
## 1 1 3 2 3 1 1 1 1 2 1 1 1 1 1
## 87000 1e+05 160000 <NA>
## 1 1 1 1995
## [1] "Frequency table after encoding"
## s9q47. In the last 30 days how much did the household spend on Funerals (including outs
## 0 2 5 10 18 20 25
## 2 1 3 23 1 40 3
## 30 32 35 40 45 50 55
## 8 1 1 13 1 55 1
## 60 70 85 100 105 120 150
## 4 1 1 54 1 1 7
## 160 200 208 250 300 320 400
## 1 24 1 1 7 1 3
## 500 600 700 900 1000 1500 2000
## 15 2 1 1 3 2 3
## 2064 2500 3500 5000 10000 12000 18000
## 1 1 1 1 2 1 1
## 20000 40000 60000 87000 93500 or more <NA>
## 1 1 1 1 2 1995
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q48)[na.exclude(mydata$s9q48)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q48", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q48. In the last 30 days how much did the household spend on School/college fees, uni
## 0 2 10 11 12 14 15 19 20 24 25 28 30 35 40 50 52 55
## 20 1 3 2 3 1 2 1 15 1 3 1 12 2 8 16 1 1
## 59 60 63 70 72 73 75 80 88 95 96 100 110 111 115 120 125 130
## 1 11 1 4 2 1 4 6 1 2 1 61 1 1 1 5 1 2
## 135 138 140 145 150 160 170 175 179 180 198 200 202 213 220 225 230 236
## 1 1 3 1 36 6 4 3 1 7 1 45 1 1 1 1 3 1
## 240 250 265 270 275 278 280 286 288 290 295 300 320 325 326 330 335 340
## 2 14 1 2 2 1 4 1 1 2 1 51 2 1 1 1 1 1
## 350 355 358 360 370 375 380 390 400 410 420 430 450 460 470 475 480 485
## 14 1 2 2 1 1 3 1 25 2 1 1 5 3 1 1 1 1
## 500 506 545 547 550 560 561 566 569 570 580 600 620 650 665 670 672 675
## 75 1 1 1 2 4 1 1 1 1 1 18 2 2 1 1 1 1
## 680 690 694 700 708 720 740 750 770 775 800 812 820 825 850 890 900 905
## 2 1 1 20 1 1 1 2 1 1 12 1 1 1 2 1 9 1
## 945 950 960 1000 1040 1050 1060 1100 1200 1298 1300 1320 1450 1500 1520 1535 1550 1600
## 1 1 1 43 1 5 1 4 11 1 4 1 1 17 1 1 1 1
## 1700 1732 1740 1750 1800 1880 1950 2000 2100 2120 2200 2250 2300 2350 2400 2450 2500 2600
## 1 1 1 1 3 1 1 17 1 1 1 1 3 1 3 1 5 1
## 2700 2900 3000 3050 3100 3500 4000 4100 4750 5000 5200 6000 6610 7000 7250 8500 9000 9600
## 1 1 10 1 1 3 1 1 1 5 1 2 1 1 1 1 2 1
## 10000 17000 18000 22960 35000 <NA>
## 4 1 1 1 1 1468
## [1] "Frequency table after encoding"
## s9q48. In the last 30 days how much did the household spend on School/college fees, uni
## 0 2 10 11 12 14 15
## 20 1 3 2 3 1 2
## 19 20 24 25 28 30 35
## 1 15 1 3 1 12 2
## 40 50 52 55 59 60 63
## 8 16 1 1 1 11 1
## 70 72 73 75 80 88 95
## 4 2 1 4 6 1 2
## 96 100 110 111 115 120 125
## 1 61 1 1 1 5 1
## 130 135 138 140 145 150 160
## 2 1 1 3 1 36 6
## 170 175 179 180 198 200 202
## 4 3 1 7 1 45 1
## 213 220 225 230 236 240 250
## 1 1 1 3 1 2 14
## 265 270 275 278 280 286 288
## 1 2 2 1 4 1 1
## 290 295 300 320 325 326 330
## 2 1 51 2 1 1 1
## 335 340 350 355 358 360 370
## 1 1 14 1 2 2 1
## 375 380 390 400 410 420 430
## 1 3 1 25 2 1 1
## 450 460 470 475 480 485 500
## 5 3 1 1 1 1 75
## 506 545 547 550 560 561 566
## 1 1 1 2 4 1 1
## 569 570 580 600 620 650 665
## 1 1 1 18 2 2 1
## 670 672 675 680 690 694 700
## 1 1 1 2 1 1 20
## 708 720 740 750 770 775 800
## 1 1 1 2 1 1 12
## 812 820 825 850 890 900 905
## 1 1 1 2 1 9 1
## 945 950 960 1000 1040 1050 1060
## 1 1 1 43 1 5 1
## 1100 1200 1298 1300 1320 1450 1500
## 4 11 1 4 1 1 17
## 1520 1535 1550 1600 1700 1732 1740
## 1 1 1 1 1 1 1
## 1750 1800 1880 1950 2000 2100 2120
## 1 3 1 1 17 1 1
## 2200 2250 2300 2350 2400 2450 2500
## 1 1 3 1 3 1 5
## 2600 2700 2900 3000 3050 3100 3500
## 1 1 1 10 1 1 3
## 4000 4100 4750 5000 5200 6000 6610
## 1 1 1 5 1 2 1
## 7000 7250 8500 9000 9600 10000 or more <NA>
## 1 1 1 2 1 8 1468
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q49)[na.exclude(mydata$s9q49)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q49", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q49. In the last 30 days how much did the household spend on Medical expenses, (inclu
## 0 5 6 10 12 14 15 16 18 20 24 25 26 28 30
## 16 2 4 12 1 2 3 1 2 21 5 1 2 2 11
## 32 33 34 35 36 38 40 42 44 45 46 50 51 52 53
## 2 1 1 2 3 1 5 2 1 3 2 18 1 1 1
## 55 59 60 62 63 64 65 66 67 68 70 72 75 80 87
## 2 2 1 1 1 2 2 1 1 1 7 1 2 4 1
## 88 89 90 92 95 99 100 103 105 108 110 113 116 120 124
## 1 1 5 2 2 2 28 1 1 1 2 2 1 11 1
## 125 127 130 135 136 138 140 142 150 154 156 160 166 170 175
## 1 1 3 1 1 1 5 1 18 1 1 3 1 4 1
## 180 188 190 200 208 210 212 215 220 222 224 225 230 232 233
## 2 1 2 36 1 1 1 1 2 1 1 1 1 1 1
## 234 236 240 242 243 250 252 270 275 278 280 283 289 290 300
## 1 1 2 1 1 12 1 1 3 1 2 1 2 1 26
## 305 308 310 320 324 325 330 335 350 356 358 359 360 375 376
## 1 1 2 2 1 1 1 1 8 1 1 1 1 2 1
## 378 380 400 404 410 423 429 440 450 455 470 475 476 480 490
## 1 1 17 1 1 1 1 1 7 1 4 1 1 2 3
## 496 500 508 512 520 524 530 531 540 550 555 557 560 568 580
## 1 44 1 1 2 1 1 1 4 5 1 1 2 1 1
## 596 600 630 635 645 650 700 710 724 749 750 756 760 770 773
## 1 10 1 1 1 8 14 1 1 1 4 1 1 1 1
## 790 800 814 825 834 848 849 850 855 880 900 910 925 928 950
## 1 7 1 1 1 1 1 1 1 1 6 2 1 1 1
## 965 975 980 1000 1020 1030 1045 1046 1050 1055 1090 1100 1107 1111 1120
## 1 1 1 50 1 1 1 1 2 1 1 5 1 1 2
## 1134 1140 1145 1150 1200 1230 1233 1250 1270 1300 1310 1330 1350 1365 1400
## 1 1 1 1 8 1 1 1 1 3 1 1 2 1 1
## 1420 1490 1500 1550 1572 1600 1670 1700 1710 1790 1800 1825 1830 1850 1889
## 1 1 31 1 1 4 1 1 1 2 2 1 1 1 1
## 1900 1950 1960 2000 2015 2025 2028 2080 2150 2163 2200 2232 2250 2270 2300
## 1 1 1 20 1 1 1 2 2 1 2 1 1 1 1
## 2400 2500 2600 2625 2650 2700 2710 2732 2750 2800 2835 3000 3010 3020 3096
## 2 10 2 1 1 3 1 1 1 1 1 16 1 1 1
## 3100 3140 3185 3300 3400 3500 3580 3600 4000 4050 4200 4300 4440 4500 4552
## 1 1 1 2 1 3 1 1 10 1 1 1 1 1 1
## 4690 4716 4800 4820 5000 5100 5200 5250 5400 5500 5550 5800 6000 6500 7000
## 1 1 1 1 18 1 1 1 1 1 2 1 3 2 5
## 7120 7500 7548 7710 7860 8000 8200 8500 8663 8766 9000 9189 9500 10000 10234
## 1 2 1 1 1 3 1 1 1 1 2 1 1 5 1
## 10700 11000 11610 11980 12000 13000 14300 15000 18500 20000 21006 22000 22080 27360 27500
## 1 1 1 1 1 1 1 3 1 3 1 2 1 1 1
## 33500 35000 50000 70000 1e+05 134000 <NA>
## 1 1 1 1 1 1 1375
## [1] "Frequency table after encoding"
## s9q49. In the last 30 days how much did the household spend on Medical expenses, (inclu
## 0 5 6 10 12 14 15
## 16 2 4 12 1 2 3
## 16 18 20 24 25 26 28
## 1 2 21 5 1 2 2
## 30 32 33 34 35 36 38
## 11 2 1 1 2 3 1
## 40 42 44 45 46 50 51
## 5 2 1 3 2 18 1
## 52 53 55 59 60 62 63
## 1 1 2 2 1 1 1
## 64 65 66 67 68 70 72
## 2 2 1 1 1 7 1
## 75 80 87 88 89 90 92
## 2 4 1 1 1 5 2
## 95 99 100 103 105 108 110
## 2 2 28 1 1 1 2
## 113 116 120 124 125 127 130
## 2 1 11 1 1 1 3
## 135 136 138 140 142 150 154
## 1 1 1 5 1 18 1
## 156 160 166 170 175 180 188
## 1 3 1 4 1 2 1
## 190 200 208 210 212 215 220
## 2 36 1 1 1 1 2
## 222 224 225 230 232 233 234
## 1 1 1 1 1 1 1
## 236 240 242 243 250 252 270
## 1 2 1 1 12 1 1
## 275 278 280 283 289 290 300
## 3 1 2 1 2 1 26
## 305 308 310 320 324 325 330
## 1 1 2 2 1 1 1
## 335 350 356 358 359 360 375
## 1 8 1 1 1 1 2
## 376 378 380 400 404 410 423
## 1 1 1 17 1 1 1
## 429 440 450 455 470 475 476
## 1 1 7 1 4 1 1
## 480 490 496 500 508 512 520
## 2 3 1 44 1 1 2
## 524 530 531 540 550 555 557
## 1 1 1 4 5 1 1
## 560 568 580 596 600 630 635
## 2 1 1 1 10 1 1
## 645 650 700 710 724 749 750
## 1 8 14 1 1 1 4
## 756 760 770 773 790 800 814
## 1 1 1 1 1 7 1
## 825 834 848 849 850 855 880
## 1 1 1 1 1 1 1
## 900 910 925 928 950 965 975
## 6 2 1 1 1 1 1
## 980 1000 1020 1030 1045 1046 1050
## 1 50 1 1 1 1 2
## 1055 1090 1100 1107 1111 1120 1134
## 1 1 5 1 1 2 1
## 1140 1145 1150 1200 1230 1233 1250
## 1 1 1 8 1 1 1
## 1270 1300 1310 1330 1350 1365 1400
## 1 3 1 1 2 1 1
## 1420 1490 1500 1550 1572 1600 1670
## 1 1 31 1 1 4 1
## 1700 1710 1790 1800 1825 1830 1850
## 1 1 2 2 1 1 1
## 1889 1900 1950 1960 2000 2015 2025
## 1 1 1 1 20 1 1
## 2028 2080 2150 2163 2200 2232 2250
## 1 2 2 1 2 1 1
## 2270 2300 2400 2500 2600 2625 2650
## 1 1 2 10 2 1 1
## 2700 2710 2732 2750 2800 2835 3000
## 3 1 1 1 1 1 16
## 3010 3020 3096 3100 3140 3185 3300
## 1 1 1 1 1 1 2
## 3400 3500 3580 3600 4000 4050 4200
## 1 3 1 1 10 1 1
## 4300 4440 4500 4552 4690 4716 4800
## 1 1 1 1 1 1 1
## 4820 5000 5100 5200 5250 5400 5500
## 1 18 1 1 1 1 1
## 5550 5800 6000 6500 7000 7120 7500
## 2 1 3 2 5 1 2
## 7548 7710 7860 8000 8200 8500 8663
## 1 1 1 3 1 1 1
## 8766 9000 9189 9500 10000 10234 10700
## 1 2 1 1 5 1 1
## 11000 11610 11980 12000 13000 14300 15000
## 1 1 1 1 1 1 3
## 18500 20000 21006 22000 22080 27360 27500
## 1 3 1 2 1 1 1
## 33500 34099 or more <NA>
## 1 5 1375
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q50)[na.exclude(mydata$s9q50)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q50", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q50. In the last 30 days how much did the household spend on Household durables (read
## 0 20 25 30 35 37 38 40 42 45 48 50 52 56 58 60 65 70
## 5 6 1 6 8 1 2 7 1 8 1 21 1 1 1 9 2 5
## 73 75 80 85 90 95 100 102 110 115 120 125 130 135 140 150 160 170
## 1 1 6 2 5 1 25 1 1 1 12 2 4 1 3 11 4 1
## 175 180 190 195 200 205 210 220 235 240 241 250 257 260 300 332 337 350
## 1 2 1 2 18 1 1 1 1 2 1 8 1 1 12 1 1 5
## 352 380 385 400 414 450 470 500 540 600 620 700 720 750 800 860 900 920
## 1 1 1 4 1 2 2 12 1 2 1 3 1 1 1 1 2 1
## 999 1000 1100 1270 1500 1680 1900 2100 2700 3000 3600 5000 5495 5500 6000 11000 12000 <NA>
## 1 3 1 1 2 1 1 1 1 2 1 1 1 1 1 1 1 2009
## [1] "Frequency table after encoding"
## s9q50. In the last 30 days how much did the household spend on Household durables (read
## 0 20 25 30 35 37 38 40
## 5 6 1 6 8 1 2 7
## 42 45 48 50 52 56 58 60
## 1 8 1 21 1 1 1 9
## 65 70 73 75 80 85 90 95
## 2 5 1 1 6 2 5 1
## 100 102 110 115 120 125 130 135
## 25 1 1 1 12 2 4 1
## 140 150 160 170 175 180 190 195
## 3 11 4 1 1 2 1 2
## 200 205 210 220 235 240 241 250
## 18 1 1 1 1 2 1 8
## 257 260 300 332 337 350 352 380
## 1 1 12 1 1 5 1 1
## 385 400 414 450 470 500 540 600
## 1 4 1 2 2 12 1 2
## 620 700 720 750 800 860 900 920
## 1 3 1 1 1 1 2 1
## 999 1000 1100 1270 1500 1680 1900 2100
## 1 3 1 1 2 1 1 1
## 2700 3000 3600 5000 5495 5500 6000 8849 or more
## 1 2 1 1 1 1 1 2
## <NA>
## 2009
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q51)[na.exclude(mydata$s9q51)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q51", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q51. In the last 30 days how much did the household spend on Dowry ? Sa nakalipas na
## 500 <NA>
## 1 2295
## [1] "Frequency table after encoding"
## s9q51. In the last 30 days how much did the household spend on Dowry ? Sa nakalipas na
## 500 or more <NA>
## 1 2295
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q52)[na.exclude(mydata$s9q52)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q52", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q52. In the last 30 days how much did the household spend on Fees paid to barangay of
## 0 5 8 10 11 12 15 16 18 20 21 22 25 30 35 38 40 41 45 50 55 60
## 4 3 2 5 1 1 6 1 1 10 1 1 8 15 18 2 11 1 4 23 2 3
## 65 70 75 78 80 85 90 95 96 100 105 120 130 135 140 150 155 160 200 215 230 250
## 6 7 1 1 4 2 1 1 1 19 2 2 1 2 2 6 1 1 4 1 1 4
## 300 480 500 600 700 1000 3000 <NA>
## 3 1 3 1 1 2 1 2091
## [1] "Frequency table after encoding"
## s9q52. In the last 30 days how much did the household spend on Fees paid to barangay of
## 0 5 8 10 11 12 15 16
## 4 3 2 5 1 1 6 1
## 18 20 21 22 25 30 35 38
## 1 10 1 1 8 15 18 2
## 40 41 45 50 55 60 65 70
## 11 1 4 23 2 3 6 7
## 75 78 80 85 90 95 96 100
## 1 1 4 2 1 1 1 19
## 105 120 130 135 140 150 155 160
## 2 2 1 2 2 6 1 1
## 200 215 230 250 300 480 500 600
## 4 1 1 4 3 1 3 1
## 700 1000 or more <NA>
## 1 3 2091
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q73)[na.exclude(mydata$s9q73)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q73", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q73. In the last 12 months did you spend any money on other expenses greater than PHP
## 0. No 1. Yes <NA>
## 1936 358 2
## [1] "Frequency table after encoding"
## s9q73. In the last 12 months did you spend any money on other expenses greater than PHP
## 0. No 1 or more <NA>
## 1936 358 2
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q75)[na.exclude(mydata$s9q75)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q75", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q75. How much did you spend on these other expenses in total in the last 12 months?
## 0 500 650 1000 1002 1008 1026 1050 1100 1121 1150 1180 1200 1250 1300
## 51 1 1 16 1 1 1 1 7 1 2 1 16 1 5
## 1400 1450 1500 1585 1600 1700 1750 1800 2000 2100 2300 2400 2500 2560 2600
## 1 1 30 1 3 3 1 5 25 1 2 4 9 1 1
## 2640 2700 2800 2875 2900 3000 3008 3100 3180 3200 3250 3500 3600 3680 3700
## 1 5 5 1 2 22 1 1 1 1 1 6 1 1 1
## 3800 4000 4200 4500 4750 4990 5000 5500 5715 6000 6500 7000 8000 9000 10000
## 1 13 1 2 1 1 18 1 1 8 1 3 7 1 8
## 12000 14000 15000 16000 16500 18000 18500 19200 20000 21000 23000 24000 25000 27360 28000
## 4 1 3 3 1 1 1 1 3 1 1 2 1 1 1
## 30000 32500 33500 34200 35000 47000 50000 60000 120000 2e+05 250000 5e+05 1e+06 <NA>
## 2 1 1 1 1 1 1 2 1 1 1 1 1 1945
## [1] "Frequency table after encoding"
## s9q75. How much did you spend on these other expenses in total in the last 12 months?
## 0 500 650 1000 1002 1008 1026
## 51 1 1 16 1 1 1
## 1050 1100 1121 1150 1180 1200 1250
## 1 7 1 2 1 16 1
## 1300 1400 1450 1500 1585 1600 1700
## 5 1 1 30 1 3 3
## 1750 1800 2000 2100 2300 2400 2500
## 1 5 25 1 2 4 9
## 2560 2600 2640 2700 2800 2875 2900
## 1 1 1 5 5 1 2
## 3000 3008 3100 3180 3200 3250 3500
## 22 1 1 1 1 1 6
## 3600 3680 3700 3800 4000 4200 4500
## 1 1 1 1 13 1 2
## 4750 4990 5000 5500 5715 6000 6500
## 1 1 18 1 1 8 1
## 7000 8000 9000 10000 12000 14000 15000
## 3 7 1 8 4 1 3
## 16000 16500 18000 18500 19200 20000 21000
## 3 1 1 1 1 3 1
## 23000 24000 25000 27360 28000 30000 32500
## 1 2 1 1 1 2 1
## 33500 34200 35000 47000 50000 60000 120000
## 1 1 1 1 1 2 1
## 2e+05 250000 312500 or more <NA>
## 1 1 2 1945
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q76)[na.exclude(mydata$s9q76)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q76", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q76. Clothing for you? Damit para sa iyo?
## 0 2 8 10 20 25 30 33 35 36 40 45 50 60 65 70 75 80 85 90 95 100
## 2046 1 1 3 10 2 14 1 3 1 4 1 20 9 1 2 1 3 1 5 1 36
## 110 120 130 150 160 170 180 190 200 220 235 250 260 270 280 300 305 320 330 350 360 380
## 1 7 3 18 1 1 3 1 19 1 1 10 1 1 2 11 1 2 1 6 1 1
## 400 460 495 500 700 800 1000 1500 1700 1950 2000 3000 <NA>
## 3 1 1 6 6 3 6 1 1 1 2 2 4
## [1] "Frequency table after encoding"
## s9q76. Clothing for you? Damit para sa iyo?
## 0 2 8 10 20 25 30 33
## 2046 1 1 3 10 2 14 1
## 35 36 40 45 50 60 65 70
## 3 1 4 1 20 9 1 2
## 75 80 85 90 95 100 110 120
## 1 3 1 5 1 36 1 7
## 130 150 160 170 180 190 200 220
## 3 18 1 1 3 1 19 1
## 235 250 260 270 280 300 305 320
## 1 10 1 1 2 11 1 2
## 330 350 360 380 400 460 495 500
## 1 6 1 1 3 1 1 6
## 700 800 1000 or more <NA>
## 6 3 13 4
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q77)[na.exclude(mydata$s9q77)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q77", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q77. Clothing for your spouse/partner? Damit para sa asawa/kinakasama mo?
## 0 2 8 10 15 20 25 30 33 35 36 40 45 50 55 60 70 75
## 2121 1 1 1 1 3 2 2 1 2 1 3 1 13 1 4 1 1
## 80 85 90 100 105 120 130 150 160 165 180 200 240 250 270 280 300 350
## 3 1 2 33 1 1 1 16 1 1 2 8 1 5 1 4 10 4
## 360 380 399 400 480 500 550 595 600 700 750 1000 1500 2000 2005 3000 65222 <NA>
## 1 2 1 1 1 8 1 1 5 2 1 4 1 3 1 1 1 6
## [1] "Frequency table after encoding"
## s9q77. Clothing for your spouse/partner? Damit para sa asawa/kinakasama mo?
## 0 2 8 10 15 20 25 30 33
## 2121 1 1 1 1 3 2 2 1
## 35 36 40 45 50 55 60 70 75
## 2 1 3 1 13 1 4 1 1
## 80 85 90 100 105 120 130 150 160
## 3 1 2 33 1 1 1 16 1
## 165 180 200 240 250 270 280 300 350
## 1 2 8 1 5 1 4 10 4
## 360 380 399 400 480 500 550 595 600
## 1 2 1 1 1 8 1 1 5
## 700 727 or more <NA>
## 2 12 6
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q78)[na.exclude(mydata$s9q78)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q78", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q78. Clothing for the children? Damit para sa mga bata?
## 0 2 8 20 25 30 35 40 50 60 66 70 75 80 85 90 95 100
## 1536 1 3 8 1 8 7 2 16 5 1 6 1 3 1 3 1 51
## 105 108 110 115 120 125 130 138 140 150 160 170 180 185 190 200 210 215
## 1 1 2 1 10 1 8 1 1 27 4 2 9 1 2 60 1 1
## 216 220 226 235 240 250 255 270 275 277 280 290 295 300 306 310 320 330
## 1 2 1 1 2 23 1 2 1 1 4 1 1 66 1 1 3 3
## 332 350 360 370 375 380 390 400 405 420 430 450 460 470 475 480 500 520
## 1 19 5 1 1 7 1 21 1 1 2 9 2 1 1 1 89 3
## 547 550 560 580 595 600 620 650 670 700 750 779 800 810 850 900 935 1000
## 1 4 2 2 1 19 1 2 2 18 3 1 14 1 1 3 1 52
## 1020 1040 1080 1100 1150 1200 1250 1400 1450 1500 1600 1880 1900 2000 2200 2300 2400 2500
## 1 1 1 5 1 4 1 1 1 29 3 1 2 14 1 1 1 2
## 2600 2660 2800 3000 3480 3500 4500 5000 12500 <NA>
## 1 1 1 11 1 2 1 1 1 10
## [1] "Frequency table after encoding"
## s9q78. Clothing for the children? Damit para sa mga bata?
## 0 2 8 20 25 30 35 40
## 1536 1 3 8 1 8 7 2
## 50 60 66 70 75 80 85 90
## 16 5 1 6 1 3 1 3
## 95 100 105 108 110 115 120 125
## 1 51 1 1 2 1 10 1
## 130 138 140 150 160 170 180 185
## 8 1 1 27 4 2 9 1
## 190 200 210 215 216 220 226 235
## 2 60 1 1 1 2 1 1
## 240 250 255 270 275 277 280 290
## 2 23 1 2 1 1 4 1
## 295 300 306 310 320 330 332 350
## 1 66 1 1 3 3 1 19
## 360 370 375 380 390 400 405 420
## 5 1 1 7 1 21 1 1
## 430 450 460 470 475 480 500 520
## 2 9 2 1 1 1 89 3
## 547 550 560 580 595 600 620 650
## 1 4 2 2 1 19 1 2
## 670 700 750 779 800 810 850 900
## 2 18 3 1 14 1 1 3
## 935 1000 1020 1040 1080 1100 1150 1200
## 1 52 1 1 1 5 1 4
## 1250 1400 1450 1500 1600 1880 1900 2000
## 1 1 1 29 3 1 2 14
## 2200 2300 2400 2500 2600 2660 2800 3000 or more
## 1 1 1 2 1 1 1 17
## <NA>
## 10
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q79)[na.exclude(mydata$s9q79)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q79", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q79. Medical expenses for you? Gastos pang medikal para sa iyo?
## 0 2 3 5 6 7 10 12 15 16 18 20 21 22 24
## 1865 1 3 4 5 1 6 4 3 1 2 23 1 1 2
## 25 26 28 30 32 33 36 40 45 48 50 52 54 55 60
## 2 2 2 14 1 2 1 8 2 2 29 1 1 1 5
## 64 65 70 72 75 80 90 96 100 105 113 116 120 135 143
## 1 1 4 2 1 4 1 1 34 2 1 2 4 1 1
## 150 175 180 189 190 200 210 220 228 240 250 275 300 320 333
## 17 1 1 1 2 33 1 1 1 2 4 1 11 1 1
## 350 357 375 390 400 450 465 470 480 490 500 530 550 596 600
## 1 1 1 1 6 2 1 1 1 1 24 1 1 1 1
## 650 700 730 749 750 770 800 850 900 975 1000 1020 1027 1200 1300
## 2 4 1 1 3 1 3 2 2 1 22 1 1 4 1
## 1450 1470 1500 1550 1710 1800 1950 2000 2080 2200 2400 2435 2600 2700 2800
## 1 1 11 1 1 2 1 9 1 1 1 1 2 2 1
## 3000 3100 3400 3600 4000 4200 4300 5000 5780 6003 7000 9600 10000 15000 70000
## 7 1 1 1 3 1 1 4 1 1 2 1 2 1 1
## 134000 <NA>
## 1 5
## [1] "Frequency table after encoding"
## s9q79. Medical expenses for you? Gastos pang medikal para sa iyo?
## 0 2 3 5 6 7 10 12
## 1865 1 3 4 5 1 6 4
## 15 16 18 20 21 22 24 25
## 3 1 2 23 1 1 2 2
## 26 28 30 32 33 36 40 45
## 2 2 14 1 2 1 8 2
## 48 50 52 54 55 60 64 65
## 2 29 1 1 1 5 1 1
## 70 72 75 80 90 96 100 105
## 4 2 1 4 1 1 34 2
## 113 116 120 135 143 150 175 180
## 1 2 4 1 1 17 1 1
## 189 190 200 210 220 228 240 250
## 1 2 33 1 1 1 2 4
## 275 300 320 333 350 357 375 390
## 1 11 1 1 1 1 1 1
## 400 450 465 470 480 490 500 530
## 6 2 1 1 1 1 24 1
## 550 596 600 650 700 730 749 750
## 1 1 1 2 4 1 1 3
## 770 800 850 900 975 1000 1020 1027
## 1 3 2 2 1 22 1 1
## 1200 1300 1450 1470 1500 1550 1710 1800
## 4 1 1 1 11 1 1 2
## 1950 2000 2080 2200 2400 2435 2600 2700
## 1 9 1 1 1 1 2 2
## 2800 3000 3100 3400 3600 4000 4200 4300
## 1 7 1 1 1 3 1 1
## 5000 or more <NA>
## 14 5
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q80)[na.exclude(mydata$s9q80)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q80", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q80. Medical expenses for your spouse/partner? Gastos pang medikal para sa asawa/kin
## 0 2 4 6 10 12 13 15 16 20 24 25 30 31 40
## 1952 1 1 1 4 2 1 3 1 13 5 4 6 1 4
## 42 45 50 52 58 60 63 64 66 67 70 80 90 99 100
## 1 1 32 1 2 5 1 1 1 1 4 2 1 1 26
## 108 112 120 132 138 144 150 160 176 180 200 240 245 250 252
## 1 1 3 1 1 1 8 1 1 2 28 1 1 7 1
## 280 300 325 330 345 350 360 400 430 500 600 700 725 735 750
## 1 15 1 1 1 2 1 7 1 24 3 3 1 1 3
## 773 800 900 910 1000 1050 1100 1200 1300 1400 1500 1600 1670 1800 2000
## 1 2 3 1 17 1 1 2 1 1 15 1 1 2 8
## 2150 2400 2500 3000 3100 3150 3300 3500 4000 5000 5280 5360 7000 7104 7500
## 1 1 5 5 1 1 1 1 1 5 1 1 2 1 1
## 10000 10300 30000 32000 1e+05 280000 <NA>
## 1 1 1 1 1 1 3
## [1] "Frequency table after encoding"
## s9q80. Medical expenses for your spouse/partner? Gastos pang medikal para sa asawa/kin
## 0 2 4 6 10 12 13 15
## 1952 1 1 1 4 2 1 3
## 16 20 24 25 30 31 40 42
## 1 13 5 4 6 1 4 1
## 45 50 52 58 60 63 64 66
## 1 32 1 2 5 1 1 1
## 67 70 80 90 99 100 108 112
## 1 4 2 1 1 26 1 1
## 120 132 138 144 150 160 176 180
## 3 1 1 1 8 1 1 2
## 200 240 245 250 252 280 300 325
## 28 1 1 7 1 1 15 1
## 330 345 350 360 400 430 500 600
## 1 1 2 1 7 1 24 3
## 700 725 735 750 773 800 900 910
## 3 1 1 3 1 2 3 1
## 1000 1050 1100 1200 1300 1400 1500 1600
## 17 1 1 2 1 1 15 1
## 1670 1800 2000 2150 2400 2500 3000 3100
## 1 2 8 1 1 5 5 1
## 3150 3300 3500 4000 5000 5151 or more <NA>
## 1 1 1 1 5 12 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s9q81)[na.exclude(mydata$s9q81)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s9q81", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s9q81. Medical expenses and vaccinations for the children of the household? Gastos pan
## 0 5 6 8 10 12 14 15 16 18 20 24 26 28 30 31 32 34
## 1625 2 3 1 18 2 2 3 1 2 27 2 1 2 10 1 2 2
## 35 36 38 39 40 42 45 46 47 48 50 52 54 55 57 58 59 60
## 3 3 1 2 5 4 3 1 1 1 32 2 1 1 1 1 1 5
## 62 64 68 70 72 75 77 78 80 85 90 92 95 99 100 103 105 106
## 1 2 1 9 2 3 1 1 8 1 4 1 2 1 23 1 3 1
## 108 110 111 115 120 125 129 130 140 150 160 170 174 182 188 190 200 205
## 1 3 1 1 12 1 1 5 3 18 2 1 1 1 1 1 34 1
## 212 215 220 224 225 244 248 250 260 270 275 278 288 290 300 308 310 314
## 1 1 1 1 2 1 1 4 1 1 2 1 1 1 19 1 1 1
## 324 331 335 338 350 360 378 380 390 393 400 412 423 425 450 455 460 470
## 2 1 1 1 9 1 1 1 1 1 14 1 1 1 5 1 1 2
## 480 490 500 530 535 540 550 568 580 600 630 635 645 650 698 700 710 746
## 1 1 30 1 1 1 1 1 1 11 1 1 1 1 1 8 1 1
## 750 800 830 834 880 900 925 941 965 975 980 1000 1025 1030 1055 1070 1080 1090
## 3 5 1 1 1 4 1 1 1 1 1 28 1 1 1 1 1 1
## 1100 1151 1152 1200 1230 1233 1281 1300 1315 1320 1350 1400 1470 1500 1550 1560 1600 1700
## 4 1 1 5 1 1 1 2 1 1 1 1 1 19 1 1 2 2
## 1750 1790 1800 1850 1900 2000 2040 2150 2167 2232 2300 2500 2516 2548 2580 2650 2700 2710
## 1 1 2 1 1 23 1 1 1 1 1 5 1 1 1 1 1 2
## 2800 3000 3010 3300 3500 3600 4000 4200 4300 4440 4500 4550 4600 4690 4800 5000 5250 5400
## 1 5 1 1 4 1 7 2 1 1 1 1 1 1 1 4 1 1
## 5800 6000 6500 7000 8000 8200 8550 8766 8900 9000 9200 10000 10120 10480 11000 11110 15000 20000
## 1 2 1 3 3 1 1 1 1 1 1 4 1 1 1 1 2 3
## 21000 24000 25000 50000 <NA>
## 1 1 1 1 5
## [1] "Frequency table after encoding"
## s9q81. Medical expenses and vaccinations for the children of the household? Gastos pan
## 0 5 6 8 10 12 14
## 1625 2 3 1 18 2 2
## 15 16 18 20 24 26 28
## 3 1 2 27 2 1 2
## 30 31 32 34 35 36 38
## 10 1 2 2 3 3 1
## 39 40 42 45 46 47 48
## 2 5 4 3 1 1 1
## 50 52 54 55 57 58 59
## 32 2 1 1 1 1 1
## 60 62 64 68 70 72 75
## 5 1 2 1 9 2 3
## 77 78 80 85 90 92 95
## 1 1 8 1 4 1 2
## 99 100 103 105 106 108 110
## 1 23 1 3 1 1 3
## 111 115 120 125 129 130 140
## 1 1 12 1 1 5 3
## 150 160 170 174 182 188 190
## 18 2 1 1 1 1 1
## 200 205 212 215 220 224 225
## 34 1 1 1 1 1 2
## 244 248 250 260 270 275 278
## 1 1 4 1 1 2 1
## 288 290 300 308 310 314 324
## 1 1 19 1 1 1 2
## 331 335 338 350 360 378 380
## 1 1 1 9 1 1 1
## 390 393 400 412 423 425 450
## 1 1 14 1 1 1 5
## 455 460 470 480 490 500 530
## 1 1 2 1 1 30 1
## 535 540 550 568 580 600 630
## 1 1 1 1 1 11 1
## 635 645 650 698 700 710 746
## 1 1 1 1 8 1 1
## 750 800 830 834 880 900 925
## 3 5 1 1 1 4 1
## 941 965 975 980 1000 1025 1030
## 1 1 1 1 28 1 1
## 1055 1070 1080 1090 1100 1151 1152
## 1 1 1 1 4 1 1
## 1200 1230 1233 1281 1300 1315 1320
## 5 1 1 1 2 1 1
## 1350 1400 1470 1500 1550 1560 1600
## 1 1 1 19 1 1 2
## 1700 1750 1790 1800 1850 1900 2000
## 2 1 1 2 1 1 23
## 2040 2150 2167 2232 2300 2500 2516
## 1 1 1 1 1 5 1
## 2548 2580 2650 2700 2710 2800 3000
## 1 1 1 1 2 1 5
## 3010 3300 3500 3600 4000 4200 4300
## 1 1 4 1 7 2 1
## 4440 4500 4550 4600 4690 4800 5000
## 1 1 1 1 1 1 4
## 5250 5400 5800 6000 6500 7000 8000
## 1 1 1 2 1 3 3
## 8200 8550 8766 8900 9000 9200 10000
## 1 1 1 1 1 1 4
## 10120 10318 or more <NA>
## 1 12 5
Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
# !!!Include relevant variables in list below (Indirect PII - Categorical, and Ordinal if not processed yet)
indirect_PII <- c("s9q42a",
"s9q43a",
"s9q44a",
"s9q45a",
"s9q46a",
"s9q47a",
"s9q48a",
"s9q49a",
"s9q51a",
"s9q52a",
"s9q1a",
"s9q2a",
"s9q3a",
"s9q4a",
"s9q5a",
"s9q6a",
"s9q7a",
"s9q8a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a",
"s9q9a")
capture_tables (indirect_PII)
# !!!No data with specific values. Matching and crosstabulations: Run automated PII check
# !!! Insufficient demographic dataOpen-ends: review responses for any sensitive information, redact as necessary
# !!! Identify open-end variables here:
open_ends <- c("s9q1awhynoresponse",
"s9q1whynoresponse",
"s9q2awhynoresponse",
"s9q2whynoresponse",
"s9q3awhynoresponse",
"s9q3whynoresponse",
"s9q4awhynoresponse",
"s9q4whynoresponse",
"s9q5awhynoresponse",
"s9q5whynoresponse",
"s9q6awhynoresponse",
"s9q6whynoresponse",
"s9q7awhynoresponse",
"s9q7whynoresponse",
"s9q8awhynoresponse",
"s9q8whynoresponse",
"s9q9awhynoresponse",
"s9q9whynoresponse",
"s9q10awhynoresponse",
"s9q10whynoresponse",
"s9q11awhynoresponse",
"s9q11whynoresponse",
"s9q12awhynoresponse",
"s9q12whynoresponse",
"s9q13awhynoresponse",
"s9q13whynoresponse",
"s9q14awhynoresponse",
"s9q15",
"s9q14whynoresponse",
"s9q15otherwhynoresponse",
"s9q32awhynoresponse",
"s9q32whynoresponse",
"s9q33awhynoresponse",
"s9q33whynoresponse",
"s9q34awhynoresponse",
"s9q34whynoresponse",
"s9q35awhynoresponse",
"s9q35whynoresponse",
"s9q36awhynoresponse",
"s9q36whynoresponse",
"s9q37awhynoresponse",
"s9q37whynoresponse",
"s9q38awhynoresponse",
"s9q38whynoresponse",
"s9q39awhynoresponse",
"s9q39whynoresponse",
"s9q40awhynoresponse",
"s9q40whynoresponse",
"s9q41awhynoresponse",
"s9q41whynoresponse",
"s9q42awhynoresponse",
"s9q42whynoresponse",
"s9q43awhynoresponse",
"s9q43whynoresponse",
"s9q44awhynoresponse",
"s9q44whynoresponse",
"s9q45awhynoresponse",
"s9q45whynoresponse",
"s9q46awhynoresponse",
"s9q46whynoresponse",
"s9q47awhynoresponse",
"s9q47whynoresponse",
"s9q48awhynoresponse",
"s9q48whynoresponse",
"s9q49awhynoresponse",
"s9q49whynoresponse",
"s9q50awhynoresponse",
"s9q50whynoresponse",
"s9q51awhynoresponse",
"s9q51whynoresponse",
"s9q52awhynoresponse",
"s9q52whynoresponse",
"s9q74",
"s9q73whynoresponse",
"s9q75whynoresponse",
"s9q76whynoresponse",
"s9q77whynoresponse",
"s9q78whynoresponse",
"s9q79whynoresponse",
"s9q80whynoresponse",
"s9q81whynoresponse")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
mydata$s9q2whynoresponse[137] <- "[language]"
mydata$s9q5whynoresponse[63] <- "[language]"
mydata$s9q8whynoresponse[63] <- "[language]"
mydata$s9q14awhynoresponse[1088] <- "[language]"
mydata$s9q15[3] <- "[language]"
mydata$s9q15[19] <- "[language]"
mydata$s9q15[181] <- "[language]"
mydata$s9q15[183] <- "[language]"
mydata$s9q15[238] <- "[language]"
mydata$s9q15[541] <- "[language]"
mydata$s9q15[744] <- "[language]"
mydata$s9q15[1109] <- "[language]"
mydata$s9q15[1134] <- "[language]"
mydata$s9q15[1447] <- "[language]"
mydata$s9q15[1499] <- "[language]"
mydata$s9q15[1501] <- "[language]"
mydata$s9q15[1734] <- "[language]"
mydata$s9q32awhynoresponse[1102] <- "[name] is not informed how much his Son [name] is spending on load."
mydata$s9q40awhynoresponse[1294] <- "[person] is paying"
mydata$s9q74[176] <- "[amount redacted]"
mydata$s9q74[649] <- "Graduation fee and expenses of [name]. Uniform, shoes"
mydata$s9q74[884] <- "[amount redacted]"
mydata$s9q74[1109] <- "[amount redacted]"
mydata$s9q74[1175] <- "[amount redacted]"
mydata$s9q74[1268] <- "[amount redacted]"
mydata$s9q74[1355] <- "[amount redacted]"
mydata$s9q74[1859] <- "[amount redacted]"
mydata$s9q74[1874] <- "[amount redacted]"
mydata$s9q74[1961] <- "[amount redacted]"
mydata$s9q74[2007] <- "[amount redacted]"
mydata$s9q74[857] <- "[amount redacted] of rice"
mydata$s9q74[1569] <- "[amount redacted] for house materials"
mydata$s9q74[40] <- "[language]"
mydata$s9q74[507] <- "[language]"
mydata$s9q74[1054] <- "[language]"
mydata$s9q74[1096] <- "[language]"
mydata$s9q74[1111] <- "[language]"
mydata$s9q74[1443] <- "[language]"
mydata$s9q74[1461] <- "[language]"
mydata$s9q74[1472] <- "[language]"
mydata$s9q74[1501] <- "[language]"
mydata$s9q74[1735] <- "[language]"
mydata$s9q74[504] <- "Vaccine for [name]"
mydata$s9q74[665] <- "[illness] from her husband."
mydata$s9q74[1045] <- "Fare going to [city]"
mydata$s9q74[1187] <- "Hospitalization of [name]"
mydata$s9q74[1203] <- "Medicine, laboratory of Mother [name] and Son [name]"
mydata$s9q74[1333] <- "Fare transportation visiting her child in [city]"
mydata$s9q74[1395] <- "Medical expenses of her child who has [illness] and yhe other child who had [illness]"
mydata$s9q74[1752] <- "Hospitalization of [name] last July [year]."
mydata$s9q74[1853] <- "Hospitalization for [name]"
mydata$s9q74[1120] <- "Medicine of [name]"
mydata$s9q74[1049] <- "For Requirements and payment of her son studying in [small location]"GPS data: Displace
# !!!No GPS dataSave processed data in Stata and SPSS format
haven::write_dta(mydata, paste0(filename, "_PU.dta"))
haven::write_sav(mydata, paste0(filename, "_PU.sav"))
# Add report title dynamically
title_var <- paste0("DOL-ILAB SDC - ", filename)