DOL-ILAB SDC - Section_11
Pablo Diego-Rosell, PhD
2021-10-19
- 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_11" # !!!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 PII Direct 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$eh_s11q3)[na.exclude(mydata$eh_s11q3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q3. Q795: What is the total amount of the loan? If your household has had multiple l
## -998 0 2000 3000 5000 6000 6500 7000 8000 9000 10000 11000 12000 14000 15000 17000
## 2 1 3 1 6 3 1 2 5 1 4 1 3 1 11 1
## 19000 20000 25000 30000 38000 40000 45000 50000 60000 70000 80000 85000 90000 1e+05 110000 140000
## 1 5 2 3 1 1 2 4 1 1 2 1 2 2 1 1
## 150000 3e+05 350000 <NA>
## 1 1 1 2209
## [1] "Frequency table after encoding"
## eh_s11q3. Q795: What is the total amount of the loan? If your household has had multiple l
## -998 0 2000 3000 5000 6000 6500
## 2 1 3 1 6 3 1
## 7000 8000 9000 10000 11000 12000 14000
## 2 5 1 4 1 3 1
## 15000 17000 19000 20000 25000 30000 38000
## 11 1 1 5 2 3 1
## 40000 45000 50000 60000 70000 80000 85000
## 1 2 4 1 1 2 1
## 90000 1e+05 110000 140000 150000 3e+05 330500 or more
## 2 2 1 1 1 1 1
## <NA>
## 2209
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q4)[na.exclude(mydata$eh_s11q4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q4. Q796: In the past 12 months, how much did your household pay in interest on thes
## -998 0 1 8 15 25 200 207 300 400 500 520 643 800 850 900
## 10 4 1 1 1 1 4 1 1 1 2 1 1 2 1 1
## 1000 1080 1200 1500 1614 1900 1950 2000 2625 3000 3600 3840 4000 4250 4400 4800
## 2 1 3 2 1 1 1 3 1 4 1 1 1 1 1 1
## 5000 5200 6000 7500 9000 10000 11000 12000 13000 13500 15000 16000 21000 40000 68000 120000
## 1 1 2 1 1 3 2 2 1 1 1 1 1 1 1 1
## <NA>
## 2209
## [1] "Frequency table after encoding"
## eh_s11q4. Q796: In the past 12 months, how much did your household pay in interest on thes
## -998 0 1 8 15 25 200 207
## 10 4 1 1 1 1 4 1
## 300 400 500 520 643 800 850 900
## 1 1 2 1 1 2 1 1
## 1000 1080 1200 1500 1614 1900 1950 2000
## 2 1 3 2 1 1 1 3
## 2625 3000 3600 3840 4000 4250 4400 4800
## 1 4 1 1 1 1 1 1
## 5000 5200 6000 7500 9000 10000 11000 12000
## 1 1 2 1 1 3 2 2
## 13000 13500 15000 16000 21000 40000 68000 99719 or more
## 1 1 1 1 1 1 1 1
## <NA>
## 2209
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q6)[na.exclude(mydata$eh_s11q6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q6. Q798: What is the total amount of the loan? If your household has had multiple l
## -998 0 20 500 616 1000 1500 1600 1700 1935 2000 2060 2200 2500 2600 3000
## 4 4 1 3 1 4 2 1 1 1 20 1 1 1 1 38
## 4000 4200 4500 5000 5250 6000 6188 6240 6480 7000 8000 9000 9500 10000 11000 12000
## 17 1 2 120 1 61 1 1 1 25 34 16 1 135 8 25
## 13000 13320 14000 14592 15000 16000 17000 18000 19000 19260 20000 21000 22000 23000 23460 24000
## 16 1 12 1 45 10 10 11 5 1 32 2 4 6 1 3
## 24900 25000 27000 28000 29000 30000 33000 35000 36000 37000 38000 40000 42000 45000 46000 50000
## 1 15 4 4 1 20 2 6 1 2 1 3 3 2 1 10
## 52000 55000 60000 64000 65000 70000 80000 1e+05 115000 130300 2e+05 230000 5e+05 <NA>
## 1 1 4 1 1 1 4 2 1 1 1 1 1 1499
## [1] "Frequency table after encoding"
## eh_s11q6. Q798: What is the total amount of the loan? If your household has had multiple l
## -998 0 20 500 616 1000 1500
## 4 4 1 3 1 4 2
## 1600 1700 1935 2000 2060 2200 2500
## 1 1 1 20 1 1 1
## 2600 3000 4000 4200 4500 5000 5250
## 1 38 17 1 2 120 1
## 6000 6188 6240 6480 7000 8000 9000
## 61 1 1 1 25 34 16
## 9500 10000 11000 12000 13000 13320 14000
## 1 135 8 25 16 1 12
## 14592 15000 16000 17000 18000 19000 19260
## 1 45 10 10 11 5 1
## 20000 21000 22000 23000 23460 24000 24900
## 32 2 4 6 1 3 1
## 25000 27000 28000 29000 30000 33000 35000
## 15 4 4 1 20 2 6
## 36000 37000 38000 40000 42000 45000 46000
## 1 2 1 3 3 2 1
## 50000 52000 55000 60000 64000 65000 70000
## 10 1 1 4 1 1 1
## 80000 1e+05 115000 115917 or more <NA>
## 4 2 1 4 1499
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q7)[na.exclude(mydata$eh_s11q7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q7. Q799: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 1 3 12 24 28 30 40 50 54 55 60 68 70 72 75 80
## 2 66 41 1 3 2 1 1 2 1 3 1 1 2 1 1 1 1 1
## 90 96 100 110 120 125 140 150 175 180 200 220 235 240 249 250 270 280 300
## 2 1 5 1 2 1 1 2 1 2 12 1 1 1 1 8 2 1 7
## 304 305 315 334 340 350 380 390 400 410 428 438 450 470 485 500 520 530 540
## 1 2 1 1 1 1 1 1 7 1 1 1 4 2 1 17 2 1 1
## 550 552 560 588 600 616 620 640 653 690 695 696 700 727 740 750 752 767 800
## 2 1 2 1 17 1 1 2 1 1 1 1 7 1 1 7 1 1 17
## 816 834 840 850 856 870 882 900 910 915 980 1000 1047 1049 1050 1080 1095 1100 1125
## 1 1 2 2 1 1 1 20 2 1 1 49 1 1 1 2 1 1 1
## 1130 1155 1175 1176 1180 1190 1200 1220 1225 1240 1245 1250 1280 1300 1320 1350 1360 1400 1440
## 2 1 1 1 1 1 26 1 1 1 1 2 2 1 1 1 2 5 1
## 1480 1500 1544 1600 1610 1650 1668 1672 1680 1700 1720 1800 1850 1890 1920 1940 1950 2000 2040
## 1 24 1 9 1 2 1 1 1 1 1 7 1 1 1 2 1 42 1
## 2100 2130 2160 2190 2200 2250 2300 2320 2400 2440 2450 2470 2480 2500 2592 2600 2625 2650 2660
## 3 1 1 1 3 1 1 1 12 1 1 1 4 6 1 2 1 1 1
## 2680 2700 2720 2736 2800 2850 2870 2880 2900 2930 3000 3200 3232 3250 3300 3400 3440 3460 3500
## 1 2 2 1 6 1 1 1 2 1 34 2 1 1 1 1 3 1 6
## 3520 3600 3675 3700 3750 3800 3827 3850 3920 4000 4100 4160 4200 4250 4400 4440 4500 4600 4650
## 1 8 2 1 4 2 1 1 1 11 1 1 1 1 1 1 4 1 1
## 4784 4800 4960 5000 5108 5132 5200 5250 5270 5300 5600 5640 5840 6000 6145 6250 6300 6321 6480
## 1 4 1 8 1 1 2 1 1 1 1 1 1 7 1 1 1 1 1
## 6500 6600 6800 6900 7000 7200 7344 7600 7680 8000 8140 8460 8500 8550 9000 9200 9600 10000 11000
## 1 1 1 1 1 2 1 1 1 2 1 1 1 1 3 1 2 2 2
## 11270 11550 12000 13000 14400 14714 14800 14980 15800 17060 17800 18300 18468 19200 20368 20904 22000 22920 23400
## 1 1 6 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## 25000 28000 30000 30600 40000 55200 62000 73930 75760 <NA>
## 1 1 1 1 2 1 1 1 1 1499
## [1] "Frequency table after encoding"
## eh_s11q7. Q799: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 1 3 12 24 28
## 2 66 41 1 3 2 1 1
## 30 40 50 54 55 60 68 70
## 2 1 3 1 1 2 1 1
## 72 75 80 90 96 100 110 120
## 1 1 1 2 1 5 1 2
## 125 140 150 175 180 200 220 235
## 1 1 2 1 2 12 1 1
## 240 249 250 270 280 300 304 305
## 1 1 8 2 1 7 1 2
## 315 334 340 350 380 390 400 410
## 1 1 1 1 1 1 7 1
## 428 438 450 470 485 500 520 530
## 1 1 4 2 1 17 2 1
## 540 550 552 560 588 600 616 620
## 1 2 1 2 1 17 1 1
## 640 653 690 695 696 700 727 740
## 2 1 1 1 1 7 1 1
## 750 752 767 800 816 834 840 850
## 7 1 1 17 1 1 2 2
## 856 870 882 900 910 915 980 1000
## 1 1 1 20 2 1 1 49
## 1047 1049 1050 1080 1095 1100 1125 1130
## 1 1 1 2 1 1 1 2
## 1155 1175 1176 1180 1190 1200 1220 1225
## 1 1 1 1 1 26 1 1
## 1240 1245 1250 1280 1300 1320 1350 1360
## 1 1 2 2 1 1 1 2
## 1400 1440 1480 1500 1544 1600 1610 1650
## 5 1 1 24 1 9 1 2
## 1668 1672 1680 1700 1720 1800 1850 1890
## 1 1 1 1 1 7 1 1
## 1920 1940 1950 2000 2040 2100 2130 2160
## 1 2 1 42 1 3 1 1
## 2190 2200 2250 2300 2320 2400 2440 2450
## 1 3 1 1 1 12 1 1
## 2470 2480 2500 2592 2600 2625 2650 2660
## 1 4 6 1 2 1 1 1
## 2680 2700 2720 2736 2800 2850 2870 2880
## 1 2 2 1 6 1 1 1
## 2900 2930 3000 3200 3232 3250 3300 3400
## 2 1 34 2 1 1 1 1
## 3440 3460 3500 3520 3600 3675 3700 3750
## 3 1 6 1 8 2 1 4
## 3800 3827 3850 3920 4000 4100 4160 4200
## 2 1 1 1 11 1 1 1
## 4250 4400 4440 4500 4600 4650 4784 4800
## 1 1 1 4 1 1 1 4
## 4960 5000 5108 5132 5200 5250 5270 5300
## 1 8 1 1 2 1 1 1
## 5600 5640 5840 6000 6145 6250 6300 6321
## 1 1 1 7 1 1 1 1
## 6480 6500 6600 6800 6900 7000 7200 7344
## 1 1 1 1 1 1 2 1
## 7600 7680 8000 8140 8460 8500 8550 9000
## 1 1 2 1 1 1 1 3
## 9200 9600 10000 11000 11270 11550 12000 13000
## 1 2 2 2 1 1 6 1
## 14400 14714 14800 14980 15800 17060 17800 18300
## 1 1 1 1 1 1 1 1
## 18468 19200 20368 20904 22000 22920 23400 25000
## 1 1 1 1 1 1 1 1
## 28000 30000 30600 40000 40911 or more <NA>
## 1 1 1 2 4 1499
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q9)[na.exclude(mydata$eh_s11q9)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q9", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q9. Q801: What is the total amount of the loan? If your household has had multiple l
## -999 -998 0 40 100 120 144 150 200 250 300 330 350 355 399 400
## 1 2 2 1 20 1 1 2 21 2 15 1 3 1 1 7
## 500 560 600 650 700 800 850 900 1000 1100 1150 1200 1300 1500 1600 1700
## 55 2 6 1 4 3 1 3 107 2 1 6 3 27 1 3
## 1800 1805 2000 2200 2220 2400 2450 2500 2600 2700 2780 2800 3000 3200 3250 3500
## 1 1 77 1 1 2 1 11 1 2 1 1 60 1 1 4
## 3800 4000 4200 4300 4400 4500 5000 5200 5500 6000 6295 6360 6500 6800 7000 7500
## 2 20 1 1 1 2 83 1 2 15 1 1 1 1 23 1
## 8000 8500 9000 10000 11000 12000 12800 13000 14400 15000 16000 16500 17000 18000 18200 19000
## 9 1 4 50 3 5 2 4 1 14 1 1 4 2 1 1
## 20000 24000 25000 28500 30000 30900 35000 36000 37060 40000 42000 45000 50000 60000 70000 74000
## 23 1 4 1 13 1 4 1 1 7 1 2 5 4 1 1
## 80000 1e+05 105000 150000 315000 8e+05 <NA>
## 1 6 1 1 1 1 1476
## [1] "Frequency table after encoding"
## eh_s11q9. Q801: What is the total amount of the loan? If your household has had multiple l
## -999 -998 0 40 100 120 144 150
## 1 2 2 1 20 1 1 2
## 200 250 300 330 350 355 399 400
## 21 2 15 1 3 1 1 7
## 500 560 600 650 700 800 850 900
## 55 2 6 1 4 3 1 3
## 1000 1100 1150 1200 1300 1500 1600 1700
## 107 2 1 6 3 27 1 3
## 1800 1805 2000 2200 2220 2400 2450 2500
## 1 1 77 1 1 2 1 11
## 2600 2700 2780 2800 3000 3200 3250 3500
## 1 2 1 1 60 1 1 4
## 3800 4000 4200 4300 4400 4500 5000 5200
## 2 20 1 1 1 2 83 1
## 5500 6000 6295 6360 6500 6800 7000 7500
## 2 15 1 1 1 1 23 1
## 8000 8500 9000 10000 11000 12000 12800 13000
## 9 1 4 50 3 5 2 4
## 14400 15000 16000 16500 17000 18000 18200 19000
## 1 14 1 1 4 2 1 1
## 20000 24000 25000 28500 30000 30900 35000 36000
## 23 1 4 1 13 1 4 1
## 37060 40000 42000 45000 50000 60000 70000 74000
## 1 7 1 2 5 4 1 1
## 80000 1e+05 or more <NA>
## 1 10 1476
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q10)[na.exclude(mydata$eh_s11q10)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q10", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q10. Q802: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 1 50 70 100 120 125 150 200 250 300 320 340 350 400 450 480
## 7 5 533 2 6 1 17 2 1 10 23 3 17 1 1 1 13 3 1
## 500 550 600 700 750 760 800 1000 1050 1100 1200 1250 1300 1400 1500 1750 1800 2000 2200
## 8 1 9 8 1 1 3 28 1 2 6 2 1 4 12 1 1 17 1
## 2400 2500 2800 2900 3000 3250 3600 4000 4500 4800 5000 5250 5600 6000 7000 7500 8500 9000 10000
## 3 2 2 1 6 1 2 4 1 1 7 1 1 5 3 2 1 1 2
## 12000 15000 16800 18000 20000 30900 60000 <NA>
## 1 2 1 2 4 1 1 1476
## [1] "Frequency table after encoding"
## eh_s11q10. Q802: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 1 50 70 100 120
## 7 5 533 2 6 1 17 2
## 125 150 200 250 300 320 340 350
## 1 10 23 3 17 1 1 1
## 400 450 480 500 550 600 700 750
## 13 3 1 8 1 9 8 1
## 760 800 1000 1050 1100 1200 1250 1300
## 1 3 28 1 2 6 2 1
## 1400 1500 1750 1800 2000 2200 2400 2500
## 4 12 1 1 17 1 3 2
## 2800 2900 3000 3250 3600 4000 4500 4800
## 2 1 6 1 2 4 1 1
## 5000 5250 5600 6000 7000 7500 8500 9000
## 7 1 1 5 3 2 1 1
## 10000 12000 15000 16800 18000 20000 or more <NA>
## 2 1 2 1 2 6 1476
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q12)[na.exclude(mydata$eh_s11q12)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q12", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q12. Q804: What is the total amount of the loan? If your household has had multiple l
## -998 350 450 600 700 840 950 1000 1180 1200 1350 1400 1500 2200 2250 2400
## 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## 2500 2700 3000 3500 4000 5000 5500 6000 7000 8000 9250 10000 12000 13000 14000 16000
## 2 1 2 1 1 6 1 2 1 4 1 10 1 1 1 1
## 17000 18000 18500 18760 20000 21900 22000 23000 25000 26800 29000 30000 32000 35000 49000 50000
## 1 1 1 1 10 1 1 1 1 1 1 2 1 1 1 1
## 51000 60000 69000 70000 1e+05 105000 146000 <NA>
## 1 1 1 1 2 1 1 2202
## [1] "Frequency table after encoding"
## eh_s11q12. Q804: What is the total amount of the loan? If your household has had multiple l
## -998 350 450 600 700 840 950
## 1 1 1 1 1 1 1
## 1000 1180 1200 1350 1400 1500 2200
## 1 1 1 1 1 1 1
## 2250 2400 2500 2700 3000 3500 4000
## 1 1 2 1 2 1 1
## 5000 5500 6000 7000 8000 9250 10000
## 6 1 2 1 4 1 10
## 12000 13000 14000 16000 17000 18000 18500
## 1 1 1 1 1 1 1
## 18760 20000 21900 22000 23000 25000 26800
## 1 10 1 1 1 1 1
## 29000 30000 32000 35000 49000 50000 51000
## 1 2 1 1 1 1 1
## 60000 69000 70000 1e+05 105000 128575 or more <NA>
## 1 1 1 2 1 1 2202
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q13)[na.exclude(mydata$eh_s11q13)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q13", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q13. Q805: In the past 12 months, how much did your household pay in interest on thes
## -998 0 50 68 100 150 200 250 300 400 450 500 600 700 840 1000
## 6 32 1 1 1 1 1 1 1 1 1 4 2 3 1 3
## 1100 1300 1500 1600 1800 2000 2400 2500 3000 3600 4000 5000 6000 6400 11256 12000
## 1 1 1 3 1 3 1 1 1 1 2 2 2 1 1 1
## 15000 18000 146000 <NA>
## 1 1 1 2202
## [1] "Frequency table after encoding"
## eh_s11q13. Q805: In the past 12 months, how much did your household pay in interest on thes
## -998 0 50 68 100 150 200 250
## 6 32 1 1 1 1 1 1
## 300 400 450 500 600 700 840 1000
## 1 1 1 4 2 3 1 3
## 1100 1300 1500 1600 1800 2000 2400 2500
## 1 1 1 3 1 3 1 1
## 3000 3600 4000 5000 6000 6400 11256 12000
## 1 1 2 2 2 1 1 1
## 15000 18000 91600 or more <NA>
## 1 1 1 2202
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q15)[na.exclude(mydata$eh_s11q15)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q15", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q15. Q807: What is the total amount of the loan? If your household has had multiple l
## -998 80 200 300 350 500 600 650 700 750 1000 1200 1450 1500 1800 2000
## 1 1 1 1 1 10 3 1 1 1 20 1 1 6 1 14
## 2500 3000 3500 3600 4000 4100 4200 4500 5000 5200 5500 5600 6000 7000 8000 8100
## 6 22 2 1 4 1 1 1 19 1 1 1 7 2 1 1
## 8600 9000 10000 15000 16000 18000 20000 25000 28000 30000 35000 40000 41000 50000 54000 140000
## 1 2 14 8 1 3 5 3 1 4 1 2 1 1 1 1
## <NA>
## 2104
## [1] "Frequency table after encoding"
## eh_s11q15. Q807: What is the total amount of the loan? If your household has had multiple l
## -998 80 200 300 350 500 600 650
## 1 1 1 1 1 10 3 1
## 700 750 1000 1200 1450 1500 1800 2000
## 1 1 20 1 1 6 1 14
## 2500 3000 3500 3600 4000 4100 4200 4500
## 6 22 2 1 4 1 1 1
## 5000 5200 5500 5600 6000 7000 8000 8100
## 19 1 1 1 7 2 1 1
## 8600 9000 10000 15000 16000 18000 20000 25000
## 1 2 14 8 1 3 5 3
## 28000 30000 35000 40000 41000 50000 54000 61310 or more
## 1 4 1 2 1 1 1 1
## <NA>
## 2104
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q16)[na.exclude(mydata$eh_s11q16)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q16", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q16. Q808: In the past 12 months, how much did your household pay in interest on thes
## -998 0 50 60 100 150 200 250 300 350 356 400 450 500 600 650 720 750 800
## 10 16 1 1 9 2 21 2 4 1 1 12 1 5 13 1 1 2 1
## 900 1000 1200 1500 1600 1700 1800 2000 2400 2500 2800 2888 3000 3200 3400 3600 4000 4200 5000
## 3 14 4 4 1 1 4 10 1 3 1 1 7 1 1 1 4 1 5
## 5500 5600 6000 7000 7500 7800 8000 8400 18000 28200 <NA>
## 1 1 2 1 1 1 2 2 1 1 2104
## [1] "Frequency table after encoding"
## eh_s11q16. Q808: In the past 12 months, how much did your household pay in interest on thes
## -998 0 50 60 100 150 200 250
## 10 16 1 1 9 2 21 2
## 300 350 356 400 450 500 600 650
## 4 1 1 12 1 5 13 1
## 720 750 800 900 1000 1200 1500 1600
## 1 2 1 3 14 4 4 1
## 1700 1800 2000 2400 2500 2800 2888 3000
## 1 4 10 1 3 1 1 7
## 3200 3400 3600 4000 4200 5000 5500 5600
## 1 1 1 4 1 5 1 1
## 6000 7000 7500 7800 8000 8400 18000 18867 or more
## 2 1 1 1 2 2 1 1
## <NA>
## 2104
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q18)[na.exclude(mydata$eh_s11q18)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q18", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q18. Q810: What is the total amount of the loan? If your household has had multiple l
## -999 -998 0 16 20 22 25 30 34 35 36 38 40 45 50 52 57 60 70
## 1 5 4 1 1 1 1 2 1 2 1 1 2 5 11 1 1 5 6
## 72 75 76 80 84 85 87 90 95 96 97 100 110 117 120 125 130 132 135
## 1 1 1 8 1 2 1 3 1 1 2 64 3 1 5 1 2 1 1
## 139 140 143 145 147 150 155 157 163 165 175 182 184 195 200 205 209 240 250
## 1 2 1 1 1 25 1 1 2 1 1 1 1 1 74 1 1 1 10
## 260 275 280 300 320 340 350 380 400 450 460 496 500 520 555 560 570 580 600
## 2 1 1 69 1 1 8 1 20 3 1 1 81 1 1 1 1 2 17
## 613 650 700 740 752 766 784 800 870 900 950 980 1000 1020 1100 1150 1200 1250 1300
## 1 2 15 1 1 1 1 17 1 4 1 1 72 1 4 1 16 2 5
## 1400 1500 1600 1700 1780 1800 2000 2200 2300 2400 2500 2600 2622 2700 2800 2880 2900 3000 3500
## 4 28 3 2 1 4 29 3 1 10 7 1 1 2 2 1 2 24 1
## 3600 3800 4000 4500 4800 5000 5500 6000 6500 7000 8000 8640 9000 9600 10000 10500 12000 13000 14400
## 3 1 7 1 4 17 1 7 1 3 4 2 1 5 4 1 5 1 3
## 15000 16000 19200 20000 20400 24000 25200 33600 36000 38400 54000 57600 60000 72000 <NA>
## 2 1 1 2 1 1 1 2 2 2 1 1 1 3 1431
## [1] "Frequency table after encoding"
## eh_s11q18. Q810: What is the total amount of the loan? If your household has had multiple l
## -999 -998 0 16 20 22 25 30
## 1 5 4 1 1 1 1 2
## 34 35 36 38 40 45 50 52
## 1 2 1 1 2 5 11 1
## 57 60 70 72 75 76 80 84
## 1 5 6 1 1 1 8 1
## 85 87 90 95 96 97 100 110
## 2 1 3 1 1 2 64 3
## 117 120 125 130 132 135 139 140
## 1 5 1 2 1 1 1 2
## 143 145 147 150 155 157 163 165
## 1 1 1 25 1 1 2 1
## 175 182 184 195 200 205 209 240
## 1 1 1 1 74 1 1 1
## 250 260 275 280 300 320 340 350
## 10 2 1 1 69 1 1 8
## 380 400 450 460 496 500 520 555
## 1 20 3 1 1 81 1 1
## 560 570 580 600 613 650 700 740
## 1 1 2 17 1 2 15 1
## 752 766 784 800 870 900 950 980
## 1 1 1 17 1 4 1 1
## 1000 1020 1100 1150 1200 1250 1300 1400
## 72 1 4 1 16 2 5 4
## 1500 1600 1700 1780 1800 2000 2200 2300
## 28 3 2 1 4 29 3 1
## 2400 2500 2600 2622 2700 2800 2880 2900
## 10 7 1 1 2 2 1 2
## 3000 3500 3600 3800 4000 4500 4800 5000
## 24 1 3 1 7 1 4 17
## 5500 6000 6500 7000 8000 8640 9000 9600
## 1 7 1 3 4 2 1 5
## 10000 10500 12000 13000 14400 15000 16000 19200
## 4 1 5 1 3 2 1 1
## 20000 20400 24000 25200 33600 36000 38400 54000
## 2 1 1 1 2 2 2 1
## 56592 or more <NA>
## 5 1431
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q19)[na.exclude(mydata$eh_s11q19)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q19", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q19. Q811: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 6 40 50 100 150 200 240 300 500 600 766 1000 1500 1782 2300 2400
## 2 2 806 1 1 2 5 3 3 1 1 1 1 1 3 1 1 2 4
## 2880 3500 4000 5500 6000 8640 9600 12000 14400 25200 37700 38170 72000 <NA>
## 1 1 1 1 2 2 2 1 1 1 1 1 1 1431
## [1] "Frequency table after encoding"
## eh_s11q19. Q811: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 6 40 50 100 150
## 2 2 806 1 1 2 5 3
## 200 240 300 500 600 766 1000 1500
## 3 1 1 1 1 1 3 1
## 1782 2300 2400 2880 3500 4000 5500 6000
## 1 2 4 1 1 1 1 2
## 8640 9600 12000 13728 or more <NA>
## 2 2 1 5 1431
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q21)[na.exclude(mydata$eh_s11q21)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q21", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q21. Q813: What is the total amount of the loan? If your household has had multiple l
## 400 500 600 650 700 1000 1200 1300 2000 2200 2300 2400 2500 2800 3000 3500
## 1 1 1 1 1 2 1 2 6 1 1 1 1 1 3 2
## 3700 3800 4000 4500 4700 5000 6000 7000 7900 8000 9000 10000 12000 12100 13000 14000
## 1 1 2 1 1 7 3 1 1 1 2 6 3 1 1 1
## 19800 20000 21000 25200 30000 31050 35000 40000 50000 56000 59760 60000 72001 91800 105000 130000
## 1 1 2 2 2 1 1 1 5 1 1 1 1 1 1 3
## 133200 3e+05 <NA>
## 1 1 2202
## [1] "Frequency table after encoding"
## eh_s11q21. Q813: What is the total amount of the loan? If your household has had multiple l
## 400 500 600 650 700 1000 1200
## 1 1 1 1 1 2 1
## 1300 2000 2200 2300 2400 2500 2800
## 2 6 1 1 1 1 1
## 3000 3500 3700 3800 4000 4500 4700
## 3 2 1 1 2 1 1
## 5000 6000 7000 7900 8000 9000 10000
## 7 3 1 1 1 2 6
## 12000 12100 13000 14000 19800 20000 21000
## 3 1 1 1 1 1 2
## 25200 30000 31050 35000 40000 50000 56000
## 2 2 1 1 1 5 1
## 59760 60000 72001 91800 105000 130000 133200
## 1 1 1 1 1 3 1
## 229110 or more <NA>
## 1 2202
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q22)[na.exclude(mydata$eh_s11q22)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q22", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q22. Q814: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 36 80 100 150 188 200 210 219 285 300 350 375 400 500 600 740
## 1 4 38 1 1 1 1 1 1 1 1 1 1 1 1 3 2 1 1
## 900 1000 1020 1200 1500 1835 2000 3000 3500 3800 3900 4000 4200 4800 5000 6000 9120 12100 20000
## 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2
## 21800 35000 37200 69000 <NA>
## 1 1 1 1 2202
## [1] "Frequency table after encoding"
## eh_s11q22. Q814: In the past 12 months, how much did your household pay in interest on thes
## -999 -998 0 36 80 100 150 188
## 1 4 38 1 1 1 1 1
## 200 210 219 285 300 350 375 400
## 1 1 1 1 1 1 1 3
## 500 600 740 900 1000 1020 1200 1500
## 2 1 1 1 1 1 1 1
## 1835 2000 3000 3500 3800 3900 4000 4200
## 1 1 1 1 1 1 1 1
## 4800 5000 6000 9120 12100 20000 21800 35000
## 1 1 1 1 1 2 1 1
## 37200 55485 or more <NA>
## 1 1 2202
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q24)[na.exclude(mydata$eh_s11q24)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q24", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q24. Q816: How much do you owe these shops for items taken on credit? Magkano ang ut
## -998 20 40 45 50 70 77 80 95 100 120 150 180 200 250 270
## 3 1 1 1 2 1 1 1 1 2 1 3 2 3 1 1
## 300 320 400 450 500 550 600 700 792 800 1000 1100 1200 1250 1300 1400
## 6 1 1 2 6 1 6 1 1 1 12 1 4 1 2 2
## 1500 1700 1800 1875 1900 2000 2400 2500 2800 2890 2900 3000 3125 3200 3214 3400
## 2 1 3 1 1 8 2 6 3 1 1 6 1 1 1 2
## 3500 3600 3800 3870 3900 4000 4020 4200 4400 4500 4800 4900 5000 5031 5300 5400
## 2 1 2 1 2 7 1 1 1 2 1 1 5 1 1 2
## 5500 5600 5700 6000 6500 7000 8000 9000 9492 9600 10000 12000 12600 12660 12800 13500
## 1 1 2 2 1 1 2 2 1 1 5 2 1 1 1 1
## 13800 15840 15872 16000 18744 19000 21000 21200 26400 26544 27600 28000 30000 32000 33000 39060
## 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1
## 40000 41000 42000 42900 44000 44200 45000 45600 50000 52095 52800 53200 54000 54400 56000 56700
## 1 1 1 2 1 1 3 2 4 1 1 1 1 1 1 1
## 57600 60000 62100 64800 66000 66800 67200 68580 72000 74500 74525 75600 76000 79000 79200 80000
## 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 2
## 86800 91000 91200 91400 1e+05 106592 118800 124000 2e+05 <NA>
## 1 1 1 1 2 1 1 1 1 2051
## [1] "Frequency table after encoding"
## eh_s11q24. Q816: How much do you owe these shops for items taken on credit? Magkano ang ut
## -998 20 40 45 50 70 77
## 3 1 1 1 2 1 1
## 80 95 100 120 150 180 200
## 1 1 2 1 3 2 3
## 250 270 300 320 400 450 500
## 1 1 6 1 1 2 6
## 550 600 700 792 800 1000 1100
## 1 6 1 1 1 12 1
## 1200 1250 1300 1400 1500 1700 1800
## 4 1 2 2 2 1 3
## 1875 1900 2000 2400 2500 2800 2890
## 1 1 8 2 6 3 1
## 2900 3000 3125 3200 3214 3400 3500
## 1 6 1 1 1 2 2
## 3600 3800 3870 3900 4000 4020 4200
## 1 2 1 2 7 1 1
## 4400 4500 4800 4900 5000 5031 5300
## 1 2 1 1 5 1 1
## 5400 5500 5600 5700 6000 6500 7000
## 2 1 1 2 2 1 1
## 8000 9000 9492 9600 10000 12000 12600
## 2 2 1 1 5 2 1
## 12660 12800 13500 13800 15840 15872 16000
## 1 1 1 1 1 1 2
## 18744 19000 21000 21200 26400 26544 27600
## 1 1 1 1 1 1 1
## 28000 30000 32000 33000 39060 40000 41000
## 1 1 1 1 1 1 1
## 42000 42900 44000 44200 45000 45600 50000
## 1 2 1 1 3 2 4
## 52095 52800 53200 54000 54400 56000 56700
## 1 1 1 1 1 1 1
## 57600 60000 62100 64800 66000 66800 67200
## 1 2 1 1 1 1 1
## 68580 72000 74500 74525 75600 76000 79000
## 1 1 1 1 1 1 1
## 79200 80000 86800 91000 91200 91400 1e+05
## 1 2 1 1 1 1 2
## 106592 118800 123063 or more <NA>
## 1 1 2 2051
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q26)[na.exclude(mydata$eh_s11q26)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q26", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q26. Q819: What is the total amount currently saved in these bank accounts by you and
## -999 -998 0 32 100 150 300 400 500 600 700 800 900 1000 1200 1300 1400 1500 1700
## 8 12 7 1 1 1 3 2 9 2 2 1 2 12 1 1 2 6 2
## 1800 1900 2000 2100 2200 2300 3000 3007 3027 3200 3600 3900 4000 4200 4300 4400 5000 5200 6000
## 2 1 8 1 1 2 10 1 1 1 1 1 5 1 1 1 11 1 1
## 7000 8000 9000 10000 11000 12000 13000 13818 15000 18000 19000 20000 22000 23000 25000 30000 40000 50000 60000
## 1 1 1 8 1 1 2 1 2 2 1 7 1 1 2 4 2 2 1
## 1e+05 <NA>
## 1 2120
## [1] "Frequency table after encoding"
## eh_s11q26. Q819: What is the total amount currently saved in these bank accounts by you and
## -999 -998 0 32 100 150 300 400
## 8 12 7 1 1 1 3 2
## 500 600 700 800 900 1000 1200 1300
## 9 2 2 1 2 12 1 1
## 1400 1500 1700 1800 1900 2000 2100 2200
## 2 6 2 2 1 8 1 1
## 2300 3000 3007 3027 3200 3600 3900 4000
## 2 10 1 1 1 1 1 5
## 4200 4300 4400 5000 5200 6000 7000 8000
## 1 1 1 11 1 1 1 1
## 9000 10000 11000 12000 13000 13818 15000 18000
## 1 8 1 1 2 1 2 2
## 19000 20000 22000 23000 25000 30000 40000 50000
## 1 7 1 1 2 4 2 2
## 60000 66599 or more <NA>
## 1 1 2120
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q27)[na.exclude(mydata$eh_s11q27)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q27", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q27. Q820: In the past 12 months, what is the total amount added to these bank accoun
## -999 -998 0 15 38 100 120 240 300 400 500 600 1000 1300 1500 1900
## 4 13 97 1 1 1 1 1 1 1 2 1 4 1 3 1
## 2000 2200 2400 2500 3000 3300 3360 3500 4000 4800 5000 6000 6560 7200 7300 9600
## 9 1 1 1 1 1 1 1 1 2 4 2 1 1 1 1
## 10000 20000 110000 134400 <NA>
## 3 1 1 1 2120
## [1] "Frequency table after encoding"
## eh_s11q27. Q820: In the past 12 months, what is the total amount added to these bank accoun
## -999 -998 0 15 38 100 120
## 4 13 97 1 1 1 1
## 240 300 400 500 600 1000 1300
## 1 1 1 2 1 4 1
## 1500 1900 2000 2200 2400 2500 3000
## 3 1 9 1 1 1 1
## 3300 3360 3500 4000 4800 5000 6000
## 1 1 1 1 2 4 2
## 6560 7200 7300 9600 10000 20000 110000
## 1 1 1 1 3 1 1
## 114025 or more <NA>
## 1 2120
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q28)[na.exclude(mydata$eh_s11q28)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q28", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q28. Q821: In the past 12 months, what is the total amount withdrawn from these accou
## -999 -998 0 200 300 390 500 600 700 800 1000 1300 1500 1800 2000 3000
## 3 13 100 1 1 1 4 3 2 2 3 1 1 2 3 6
## 4000 5000 5500 6000 7000 7600 10000 16500 20000 25000 37000 44000 110000 126000 132400 <NA>
## 2 4 1 1 2 1 3 1 1 1 1 1 1 1 1 2120
## [1] "Frequency table after encoding"
## eh_s11q28. Q821: In the past 12 months, what is the total amount withdrawn from these accou
## -999 -998 0 200 300 390 500
## 3 13 100 1 1 1 4
## 600 700 800 1000 1300 1500 1800
## 3 2 2 3 1 1 2
## 2000 3000 4000 5000 5500 6000 7000
## 3 6 2 4 1 1 2
## 7600 10000 16500 20000 25000 37000 44000
## 1 3 1 1 1 1 1
## 110000 126000 127055 or more <NA>
## 1 1 1 2120
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q30)[na.exclude(mydata$eh_s11q30)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q30", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q30. Q823: In the past 12 months, how much income did you earn from interest on these
## -999 -998 0 4 5 7 10 12 13 14 15 17 18 20 21 24 25 27 30
## 2 15 2 1 1 1 1 1 1 1 5 1 1 1 1 1 1 1 1
## 32 38 50 52 66 100 106 120 140 200 288 300 400 500 600 700 1000 1200 2000
## 1 1 3 1 1 1 1 1 1 2 1 2 1 1 1 1 2 1 1
## 3000 5000 13200 <NA>
## 1 1 1 2222
## [1] "Frequency table after encoding"
## eh_s11q30. Q823: In the past 12 months, how much income did you earn from interest on these
## -999 -998 0 4 5 7 10 12
## 2 15 2 1 1 1 1 1
## 13 14 15 17 18 20 21 24
## 1 1 5 1 1 1 1 1
## 25 27 30 32 38 50 52 66
## 1 1 1 1 1 3 1 1
## 100 106 120 140 200 288 300 400
## 1 1 1 1 2 1 2 1
## 500 600 700 1000 1200 2000 3000 5000
## 1 1 1 2 1 1 1 1
## 10534 or more <NA>
## 1 2222
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q32)[na.exclude(mydata$eh_s11q32)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q32", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q32. Q825: What is the total amount currently saved with coops and MFIs (microfinance
## -999 -998 0 16 20 30 40 50 70 80 100 105 120 150 200 250 300 310 350
## 1 23 8 1 1 2 1 2 1 1 2 1 2 2 9 1 10 1 3
## 390 400 410 420 456 480 500 520 575 600 640 650 680 700 720 750 800 813 825
## 1 5 1 1 1 2 12 1 1 12 1 1 1 7 2 1 3 1 1
## 850 880 886 900 1000 1001 1005 1070 1100 1200 1220 1240 1250 1293 1300 1400 1410 1440 1450
## 1 1 1 4 45 1 1 1 2 17 1 1 1 1 6 8 1 1 1
## 1470 1500 1575 1600 1680 1700 1800 1900 2000 2017 2100 2132 2200 2300 2400 2430 2500 2600 2700
## 1 22 1 7 1 4 12 1 47 1 2 1 3 2 3 1 13 5 3
## 2800 2850 2900 3000 3014 3020 3040 3100 3200 3300 3335 3371 3400 3496 3500 3568 3600 3610 3700
## 7 2 2 49 1 1 1 1 4 2 1 1 2 1 8 1 6 1 1
## 3789 3800 3831 3870 3900 3910 4000 4200 4300 4310 4312 4330 4399 4500 4560 4570 4600 4700 4800
## 1 4 1 1 2 1 38 2 1 1 1 1 1 4 1 1 2 2 3
## 4860 4900 5000 5006 5100 5400 5500 5550 5680 5700 5709 5800 6000 6075 6092 6300 6340 6400 6500
## 1 1 36 1 1 1 6 1 1 1 1 1 21 1 1 1 1 1 2
## 6700 6800 7000 7110 7200 7334 7883 8000 8500 8640 8800 9000 9463 9900 10000 10700 11000 11600 12000
## 1 3 17 1 1 1 1 14 1 1 1 6 1 1 10 1 4 1 5
## 12400 12740 14000 15000 15900 16000 17000 18000 19000 20000 21000 22000 24000 25000 30000 32500 80000 1e+05 <NA>
## 1 1 4 5 1 2 1 1 2 4 1 1 1 1 2 1 1 1 1594
## [1] "Frequency table after encoding"
## eh_s11q32. Q825: What is the total amount currently saved with coops and MFIs (microfinance
## -999 -998 0 16 20 30 40 50
## 1 23 8 1 1 2 1 2
## 70 80 100 105 120 150 200 250
## 1 1 2 1 2 2 9 1
## 300 310 350 390 400 410 420 456
## 10 1 3 1 5 1 1 1
## 480 500 520 575 600 640 650 680
## 2 12 1 1 12 1 1 1
## 700 720 750 800 813 825 850 880
## 7 2 1 3 1 1 1 1
## 886 900 1000 1001 1005 1070 1100 1200
## 1 4 45 1 1 1 2 17
## 1220 1240 1250 1293 1300 1400 1410 1440
## 1 1 1 1 6 8 1 1
## 1450 1470 1500 1575 1600 1680 1700 1800
## 1 1 22 1 7 1 4 12
## 1900 2000 2017 2100 2132 2200 2300 2400
## 1 47 1 2 1 3 2 3
## 2430 2500 2600 2700 2800 2850 2900 3000
## 1 13 5 3 7 2 2 49
## 3014 3020 3040 3100 3200 3300 3335 3371
## 1 1 1 1 4 2 1 1
## 3400 3496 3500 3568 3600 3610 3700 3789
## 2 1 8 1 6 1 1 1
## 3800 3831 3870 3900 3910 4000 4200 4300
## 4 1 1 2 1 38 2 1
## 4310 4312 4330 4399 4500 4560 4570 4600
## 1 1 1 1 4 1 1 2
## 4700 4800 4860 4900 5000 5006 5100 5400
## 2 3 1 1 36 1 1 1
## 5500 5550 5680 5700 5709 5800 6000 6075
## 6 1 1 1 1 1 21 1
## 6092 6300 6340 6400 6500 6700 6800 7000
## 1 1 1 1 2 1 3 17
## 7110 7200 7334 7883 8000 8500 8640 8800
## 1 1 1 1 14 1 1 1
## 9000 9463 9900 10000 10700 11000 11600 12000
## 6 1 1 10 1 4 1 5
## 12400 12740 14000 15000 15900 16000 17000 18000
## 1 1 4 5 1 2 1 1
## 19000 20000 21000 22000 24000 25000 30000 or more <NA>
## 2 4 1 1 1 1 5 1594
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q33)[na.exclude(mydata$eh_s11q33)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q33", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q33. Q826: In the past 12 months, what is the total amount added to these accounts by
## -999 -998 0 12 14 20 30 40 50 68 72 80 85 90 100 120 125 140 150
## 7 37 393 1 1 1 1 1 9 1 1 3 1 1 4 2 1 2 4
## 195 200 228 240 250 300 370 400 420 480 500 557 600 640 720 800 880 900 1000
## 1 11 1 4 5 8 1 5 1 1 14 1 6 1 4 4 1 1 27
## 1100 1200 1300 1344 1400 1440 1470 1500 1550 1570 1575 1600 1680 1700 1800 2000 2122 2240 2400
## 1 9 1 1 4 2 1 3 1 1 1 1 2 1 1 10 1 1 23
## 2460 2600 2650 2700 2800 2850 2880 3000 3360 3500 3600 3800 3840 3900 4000 4200 4320 4462 4600
## 1 2 1 2 3 1 1 5 4 2 1 1 1 1 4 1 1 1 1
## 4800 5000 5500 5760 6300 6720 7000 7200 8000 8593 9000 9120 9600 12000 13000 13500 14000 30000 36000
## 3 6 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1
## <NA>
## 1594
## [1] "Frequency table after encoding"
## eh_s11q33. Q826: In the past 12 months, what is the total amount added to these accounts by
## -999 -998 0 12 14 20 30 40
## 7 37 393 1 1 1 1 1
## 50 68 72 80 85 90 100 120
## 9 1 1 3 1 1 4 2
## 125 140 150 195 200 228 240 250
## 1 2 4 1 11 1 4 5
## 300 370 400 420 480 500 557 600
## 8 1 5 1 1 14 1 6
## 640 720 800 880 900 1000 1100 1200
## 1 4 4 1 1 27 1 9
## 1300 1344 1400 1440 1470 1500 1550 1570
## 1 1 4 2 1 3 1 1
## 1575 1600 1680 1700 1800 2000 2122 2240
## 1 1 2 1 1 10 1 1
## 2400 2460 2600 2650 2700 2800 2850 2880
## 23 1 2 1 2 3 1 1
## 3000 3360 3500 3600 3800 3840 3900 4000
## 5 4 2 1 1 1 1 4
## 4200 4320 4462 4600 4800 5000 5500 5760
## 1 1 1 1 3 6 1 1
## 6300 6720 7000 7200 8000 8593 9000 9120
## 1 1 1 1 1 1 1 1
## 9600 12000 13000 13267 or more <NA>
## 1 2 1 4 1594
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q34)[na.exclude(mydata$eh_s11q34)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q34", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q34. Q827: In the past 12 months, what is the total amount withdrawn from these accou
## -999 -998 0 60 100 150 200 240 270 300 340 400 410 450 500 520 600 650 679
## 7 17 408 1 1 1 9 1 1 19 1 14 1 1 31 1 7 1 1
## 700 710 720 730 750 800 852 900 1000 1050 1120 1200 1225 1300 1400 1500 1600 1620 1650
## 3 1 1 1 1 8 1 6 30 1 1 4 1 3 1 12 5 1 1
## 1700 1800 1900 2000 2100 2200 2360 2400 2500 2700 2900 3000 3500 3700 3800 4000 4500 4700 4750
## 1 2 1 20 1 2 1 2 6 2 1 8 2 2 3 5 1 1 1
## 4800 5000 6000 6880 7000 7300 7500 8000 8500 10000 10500 12600 16000 32000 40000 42000 1e+05 <NA>
## 1 5 3 1 2 1 1 2 1 3 1 1 1 1 1 1 1 1594
## [1] "Frequency table after encoding"
## eh_s11q34. Q827: In the past 12 months, what is the total amount withdrawn from these accou
## -999 -998 0 60 100 150 200 240
## 7 17 408 1 1 1 9 1
## 270 300 340 400 410 450 500 520
## 1 19 1 14 1 1 31 1
## 600 650 679 700 710 720 730 750
## 7 1 1 3 1 1 1 1
## 800 852 900 1000 1050 1120 1200 1225
## 8 1 6 30 1 1 4 1
## 1300 1400 1500 1600 1620 1650 1700 1800
## 3 1 12 5 1 1 1 2
## 1900 2000 2100 2200 2360 2400 2500 2700
## 1 20 1 2 1 2 6 2
## 2900 3000 3500 3700 3800 4000 4500 4700
## 1 8 2 2 3 5 1 1
## 4750 4800 5000 6000 6880 7000 7300 7500
## 1 1 5 3 1 2 1 1
## 8000 8500 10000 10500 12600 16000 24559 or more <NA>
## 2 1 3 1 1 1 4 1594
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q36)[na.exclude(mydata$eh_s11q36)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q36", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q36. Q829: In the past 12 months, how much income did you earn from interest on these
## -999 -998 0 2 3 4 5 6 8 9 10 11 12 13 14 15 17 18 20
## 3 77 11 1 2 1 5 5 1 1 2 2 2 1 1 3 2 1 8
## 21 23 25 28 30 32 33 35 36 38 40 44 45 47 48 50 53 54 60
## 1 2 4 1 7 1 1 3 3 1 4 1 2 1 1 9 1 1 4
## 66 70 80 85 90 96 100 105 120 123 125 136 150 168 175 180 200 210 215
## 1 3 1 1 2 1 15 1 2 1 1 1 5 1 1 3 15 3 1
## 224 225 228 240 245 246 250 280 288 299 300 320 350 358 360 370 390 400 435
## 1 1 1 1 1 1 1 1 1 1 7 2 2 1 1 1 1 4 1
## 487 500 588 600 624 750 760 800 845 1000 1075 1200 1300 1500 1800 2000 3000 5000 12000
## 1 5 1 5 1 1 2 4 1 6 1 2 1 4 1 4 1 1 1
## <NA>
## 1979
## [1] "Frequency table after encoding"
## eh_s11q36. Q829: In the past 12 months, how much income did you earn from interest on these
## -999 -998 0 2 3 4 5 6 8
## 3 77 11 1 2 1 5 5 1
## 9 10 11 12 13 14 15 17 18
## 1 2 2 2 1 1 3 2 1
## 20 21 23 25 28 30 32 33 35
## 8 1 2 4 1 7 1 1 3
## 36 38 40 44 45 47 48 50 53
## 3 1 4 1 2 1 1 9 1
## 54 60 66 70 80 85 90 96 100
## 1 4 1 3 1 1 2 1 15
## 105 120 123 125 136 150 168 175 180
## 1 2 1 1 1 5 1 1 3
## 200 210 215 224 225 228 240 245 246
## 15 3 1 1 1 1 1 1 1
## 250 280 288 299 300 320 350 358 360
## 1 1 1 1 7 2 2 1 1
## 370 390 400 435 487 500 588 600 624
## 1 1 4 1 1 5 1 5 1
## 750 760 800 845 1000 1075 1200 1300 1500
## 1 2 4 1 6 1 2 1 4
## 1800 2000 3000 3919 or more <NA>
## 1 4 1 2 1979
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q38)[na.exclude(mydata$eh_s11q38)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q38", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q38. Q831: What is the total amount currently saved with the 'paluwagan' by you and a
## -999 -998 0 70 75 200 300 400 420 450 500 600 700 800 840 900 1000 1020 1050
## 1 2 2 1 1 2 2 1 1 1 3 6 1 5 1 2 5 1 1
## 1180 1200 1400 1500 1600 1750 1900 2300 2600 2800 3000 3080 3100 3150 3200 3300 3500 3600 3900
## 1 7 1 2 1 1 1 2 2 3 8 1 1 1 2 1 1 1 1
## 4000 4200 4500 4600 4800 5000 5200 5600 6000 6300 6600 6900 7000 7200 8000 8400 8500 8800 9000
## 5 2 1 1 2 9 1 1 7 1 1 1 5 1 3 1 1 1 1
## 9600 10000 10700 11000 11500 11600 12000 13000 13500 14700 15000 15400 15800 17000 17800 18000 19000 20000 22000
## 1 2 1 2 1 1 4 1 1 1 3 2 1 1 1 2 1 2 1
## 30000 34000 52000 <NA>
## 1 1 1 2134
## [1] "Frequency table after encoding"
## eh_s11q38. Q831: What is the total amount currently saved with the 'paluwagan' by you and a
## -999 -998 0 70 75 200 300 400
## 1 2 2 1 1 2 2 1
## 420 450 500 600 700 800 840 900
## 1 1 3 6 1 5 1 2
## 1000 1020 1050 1180 1200 1400 1500 1600
## 5 1 1 1 7 1 2 1
## 1750 1900 2300 2600 2800 3000 3080 3100
## 1 1 2 2 3 8 1 1
## 3150 3200 3300 3500 3600 3900 4000 4200
## 1 2 1 1 1 1 5 2
## 4500 4600 4800 5000 5200 5600 6000 6300
## 1 1 2 9 1 1 7 1
## 6600 6900 7000 7200 8000 8400 8500 8800
## 1 1 5 1 3 1 1 1
## 9000 9600 10000 10700 11000 11500 11600 12000
## 1 1 2 1 2 1 1 4
## 13000 13500 14700 15000 15400 15800 17000 17800
## 1 1 1 3 2 1 1 1
## 18000 19000 20000 22000 30000 34000 38229 or more <NA>
## 2 1 2 1 1 1 1 2134
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q39)[na.exclude(mydata$eh_s11q39)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q39", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q39. Q832: In the past 12 months, what is the total amount added to these accounts by
## -999 -998 0 100 200 280 300 350 400 500 600 840 900 1000 1200 1300 2000 2400 2500
## 3 6 101 4 5 2 1 1 1 1 3 2 1 1 3 1 3 1 1
## 2660 3000 3100 3600 5000 6400 7000 8000 14700 <NA>
## 1 2 1 1 4 1 1 1 1 2134
## [1] "Frequency table after encoding"
## eh_s11q39. Q832: In the past 12 months, what is the total amount added to these accounts by
## -999 -998 0 100 200 280 300 350 400
## 3 6 101 4 5 2 1 1 1
## 500 600 840 900 1000 1200 1300 2000 2400
## 1 3 2 1 1 3 1 3 1
## 2500 2660 3000 3100 3600 5000 6400 7000 8000
## 1 1 2 1 1 4 1 1 1
## 9574 or more <NA>
## 1 2134
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q40)[na.exclude(mydata$eh_s11q40)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q40", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q40. Q833: In the past 12 months, what is the total amount withdrawn from these accou
## -999 -998 0 600 700 1000 1500 1600 2000 2200 2600 3000 3500 4000 4200 4600 5000 5600 7200
## 2 4 120 1 1 2 1 1 2 1 1 2 1 1 2 1 2 1 1
## 8000 11000 13500 15000 22000 <NA>
## 2 1 1 2 1 2134
## [1] "Frequency table after encoding"
## eh_s11q40. Q833: In the past 12 months, what is the total amount withdrawn from these accou
## -999 -998 0 600 700 1000 1500 1600
## 2 4 120 1 1 2 1 1
## 2000 2200 2600 3000 3500 4000 4200 4600
## 2 1 1 2 1 1 2 1
## 5000 5600 7200 8000 11000 13500 15000 16644 or more
## 2 1 1 2 1 1 2 1
## <NA>
## 2134
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q42)[na.exclude(mydata$eh_s11q42)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q42", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q42. Q835: In the past 12 months, how much income did you earn from interest on these
## 0 50 150 250 300 400 500 2000 3000 <NA>
## 2 1 1 1 1 2 1 1 1 2277
## [1] "Frequency table after encoding"
## eh_s11q42. Q835: In the past 12 months, how much income did you earn from interest on these
## 0 50 150 250 300 400 500 2000 2949 or more
## 2 1 1 1 1 2 1 1 1
## <NA>
## 2277
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q44)[na.exclude(mydata$eh_s11q44)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q44", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q44. Q837: What is the current amount of these other savings? Ano ang kasalukuyang h
## -999 -998 0 20 50 60 89 100 120 140 150 190 200 220 250 300
## 3 16 6 1 4 1 1 5 1 1 5 1 11 1 1 10
## 340 350 360 400 450 500 555 560 600 700 800 900 1000 1150 1156 1200
## 1 1 1 4 1 41 1 2 3 5 3 1 47 1 1 4
## 1500 1600 1700 1800 2000 2300 2400 2500 2717 2800 3000 3100 3500 3800 4000 4100
## 18 2 1 1 29 1 2 8 1 1 22 1 2 1 8 1
## 4200 5000 5790 6000 7000 7500 8000 9000 10000 11000 12000 14500 15000 16000 18000 20000
## 1 22 1 9 6 1 4 1 12 1 1 1 3 1 3 5
## 26000 50000 60000 72000 90000 1e+05 120000 <NA>
## 1 2 1 1 1 3 1 1922
## [1] "Frequency table after encoding"
## eh_s11q44. Q837: What is the current amount of these other savings? Ano ang kasalukuyang h
## -999 -998 0 20 50 60 89 100
## 3 16 6 1 4 1 1 5
## 120 140 150 190 200 220 250 300
## 1 1 5 1 11 1 1 10
## 340 350 360 400 450 500 555 560
## 1 1 1 4 1 41 1 2
## 600 700 800 900 1000 1150 1156 1200
## 3 5 3 1 47 1 1 4
## 1500 1600 1700 1800 2000 2300 2400 2500
## 18 2 1 1 29 1 2 8
## 2717 2800 3000 3100 3500 3800 4000 4100
## 1 1 22 1 2 1 8 1
## 4200 5000 5790 6000 7000 7500 8000 9000
## 1 22 1 9 6 1 4 1
## 10000 11000 12000 14500 15000 16000 18000 20000
## 12 1 1 1 3 1 3 5
## 26000 50000 60000 72000 90000 1e+05 or more <NA>
## 1 2 1 1 1 4 1922
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q45)[na.exclude(mydata$eh_s11q45)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q45", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q45. Q838: In the past 12 months, what is the total amount added to this savings by y
## -999 -998 0 20 30 50 80 100 150 200 250 300 320 340 400 450 500 600 700
## 1 18 243 2 1 6 1 8 1 5 1 1 1 1 2 1 19 3 1
## 750 800 960 1000 1200 1500 2000 2300 2400 3000 3300 4000 5000 5790 6000 6300 7000 8000 9000
## 1 1 1 13 1 7 4 1 1 2 1 2 4 1 1 1 1 2 1
## 10000 10500 18000 20000 <NA>
## 1 1 1 1 1922
## [1] "Frequency table after encoding"
## eh_s11q45. Q838: In the past 12 months, what is the total amount added to this savings by y
## -999 -998 0 20 30 50 80 100
## 1 18 243 2 1 6 1 8
## 150 200 250 300 320 340 400 450
## 1 5 1 1 1 1 2 1
## 500 600 700 750 800 960 1000 1200
## 19 3 1 1 1 1 13 1
## 1500 2000 2300 2400 3000 3300 4000 5000
## 7 4 1 1 2 1 2 4
## 5790 6000 6300 7000 8000 9000 10000 10500
## 1 1 1 1 2 1 1 1
## 11812 or more <NA>
## 2 1922
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q46)[na.exclude(mydata$eh_s11q46)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q46", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q46. Q839: In the past 12 months, what is the total amount withdrawn from this saving
## -999 -998 0 15 20 80 100 200 300 400 500 520 600 700 800 1000 1200 1500 2000
## 2 10 298 1 1 1 1 9 2 3 13 1 1 1 2 6 1 1 4
## 3000 3500 4500 5000 10000 20000 <NA>
## 1 2 1 2 1 1 1922
## [1] "Frequency table after encoding"
## eh_s11q46. Q839: In the past 12 months, what is the total amount withdrawn from this saving
## -999 -998 0 15 20 80 100 200 300
## 2 10 298 1 1 1 1 9 2
## 400 500 520 600 700 800 1000 1200 1500
## 3 13 1 1 1 2 6 1 1
## 2000 3000 3500 4500 5000 5875 or more <NA>
## 4 1 2 1 2 2 1922
percentile_99.5 <- floor(quantile(na.exclude(mydata$eh_s11q48)[na.exclude(mydata$eh_s11q48)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="eh_s11q48", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## eh_s11q48. Q841: In the past 12 months, how much income did you earn from interest on this
## -998 100 150 200 350 500 1000 4000 <NA>
## 3 1 1 2 1 1 1 2 2276
## [1] "Frequency table after encoding"
## eh_s11q48. Q841: In the past 12 months, how much income did you earn from interest on this
## -998 100 150 200 350 500 1000 4000 or more <NA>
## 3 1 1 2 1 1 1 2 2276
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("eh_s11q1",
"eh_s11q2",
"eh_s11q5",
"eh_s11q8",
"eh_s11q11",
"eh_s11q14",
"eh_s11q17",
"eh_s11q20",
"eh_s11q23",
"eh_s11q25",
"eh_s11q29",
"eh_s11q31",
"eh_s11q35",
"eh_s11q37",
"eh_s11q41",
"eh_s11q43",
"eh_s11q47")
capture_tables (indirect_PII)
# Recode those with very specific values.
# !!!No very specific valuesMatching and crosstabulations: Run automated PII check
# !!!Insufficient demographic dataOpen-ends: review responses for any sensitive information, redact as necessary
# !!!No Open-endsGPS 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)