DOL-ILAB SDC - Section_5
Pablo Diego-Rosell, PhD
2021-08-27
- 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_5" # !!!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.
mydata <- top_recode ("s5q1", break_point=3, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q1. How many houses does your household own? Ilang bahay ang pag-aari ng iyong kasa
## 0 1 2 3 4 <NA>
## 274 1979 40 1 1 1
## [1] "Frequency table after encoding"
## s5q1. How many houses does your household own? Ilang bahay ang pag-aari ng iyong kasa
## 0 1 2 3 or more <NA>
## 274 1979 40 2 1
mydata <- top_recode ("s5q3", break_point=1, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q3. How many landline/wireless telephones does your household own? Ilang telepono/w
## 0 1 8 <NA>
## 2290 4 1 1
## [1] "Frequency table after encoding"
## s5q3. How many landline/wireless telephones does your household own? Ilang telepono/w
## 0 1 or more <NA>
## 2290 5 1
mydata <- top_recode ("s5q5", break_point=6, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q5. How many cell phones does your household own? Ilang cell phone ang pag mamay-a
## 0 1 2 3 4 5 6 7 8 9 10 12 <NA>
## 210 830 653 348 144 64 29 8 5 1 1 2 1
## [1] "Frequency table after encoding"
## s5q5. How many cell phones does your household own? Ilang cell phone ang pag mamay-a
## 0 1 2 3 4 5 6 or more <NA>
## 210 830 653 348 144 64 46 1
mydata <- top_recode ("s5q7", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q7. How many sofas does your household own? Ilang sofa ang pag mamay-ari ng iyong
## 0 1 2 3 4 5 <NA>
## 1619 558 69 38 8 3 1
## [1] "Frequency table after encoding"
## s5q7. How many sofas does your household own? Ilang sofa ang pag mamay-ari ng iyong
## 0 1 2 3 4 or more <NA>
## 1619 558 69 38 11 1
mydata <- top_recode ("s5q9", break_point=9, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q9. How many chairs does your household own? Ilang upuan ang pag mamay-ari ng iyong
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 16 20 <NA>
## 533 275 408 355 290 146 158 39 39 10 23 5 10 1 1 1 1 1
## [1] "Frequency table after encoding"
## s5q9. How many chairs does your household own? Ilang upuan ang pag mamay-ari ng iyong
## 0 1 2 3 4 5 6 7 8 9 or more <NA>
## 533 275 408 355 290 146 158 39 39 52 1
mydata <- top_recode ("s5q11", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q11. How many tables does your household own? Ilang lamesa ang pag mamay-ari ng iyon
## 0 1 2 3 4 5 6 7 8 13 <NA>
## 379 1331 449 99 29 4 1 1 1 1 1
## [1] "Frequency table after encoding"
## s5q11. How many tables does your household own? Ilang lamesa ang pag mamay-ari ng iyon
## 0 1 2 3 4 or more <NA>
## 379 1331 449 99 37 1
mydata <- top_recode ("s5q13", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q13. How many clocks/watches does your household own? Ilang orasan/relos ang pag mam
## 0 1 2 3 4 5 6 7 8 9 <NA>
## 1167 916 141 44 16 4 3 1 2 1 1
## [1] "Frequency table after encoding"
## s5q13. How many clocks/watches does your household own? Ilang orasan/relos ang pag mam
## 0 1 2 3 4 or more <NA>
## 1167 916 141 44 27 1
mydata <- top_recode ("s5q15", break_point=3, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q15. How many bicycles does your household own? Ilang bisikleta ang pag mamay-ari ng
## 0 1 2 3 4 5 9 <NA>
## 1754 464 58 13 4 1 1 1
## [1] "Frequency table after encoding"
## s5q15. How many bicycles does your household own? Ilang bisikleta ang pag mamay-ari ng
## 0 1 2 3 or more <NA>
## 1754 464 58 19 1
mydata <- top_recode ("s5q17", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q17. How many tricycles does your household own? Ilang traysikel ang pag mamay-ari n
## 0 1 2 4 5 <NA>
## 2141 149 3 1 1 1
## [1] "Frequency table after encoding"
## s5q17. How many tricycles does your household own? Ilang traysikel ang pag mamay-ari n
## 0 1 2 or more <NA>
## 2141 149 5 1
mydata <- top_recode ("s5q19", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q19. How many motorbikes does your household own? Ilang motorsiklo ang pag mamay-ari
## 0 1 2 3 4 8 <NA>
## 1878 386 27 1 2 1 1
## [1] "Frequency table after encoding"
## s5q19. How many motorbikes does your household own? Ilang motorsiklo ang pag mamay-ari
## 0 1 2 or more <NA>
## 1878 386 31 1
mydata <- top_recode ("s5q21", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q21. How many motorized boats/bancas does your household own? Ilang bangkang de-moto
## 0 1 2 <NA>
## 2178 108 9 1
## [1] "Frequency table after encoding"
## s5q21. How many motorized boats/bancas does your household own? Ilang bangkang de-moto
## 0 1 2 or more <NA>
## 2178 108 9 1
mydata <- top_recode ("s5q23", break_point=1, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q23. How many other motorized vehicles does your household own? Ilang sasakyang de-m
## 0 1 8 <NA>
## 2273 21 1 1
## [1] "Frequency table after encoding"
## s5q23. How many other motorized vehicles does your household own? Ilang sasakyang de-m
## 0 1 or more <NA>
## 2273 22 1
mydata <- top_recode ("s5q25", break_point=3, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q25. How many radio, tape, or CD players does your household own? Ilang radyo, teyp
## 0 1 2 3 5 7 8 <NA>
## 1320 914 52 6 1 1 1 1
## [1] "Frequency table after encoding"
## s5q25. How many radio, tape, or CD players does your household own? Ilang radyo, teyp
## 0 1 2 3 or more <NA>
## 1320 914 52 9 1
mydata <- top_recode ("s5q27", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q27. How many beds does your household own? Ilang kama ang pag mamay-ari ng iyong ka
## 0 1 2 3 4 5 8 <NA>
## 1342 542 305 84 19 2 1 1
## [1] "Frequency table after encoding"
## s5q27. How many beds does your household own? Ilang kama ang pag mamay-ari ng iyong ka
## 0 1 2 3 4 or more <NA>
## 1342 542 305 84 22 1
mydata <- top_recode ("s5q29", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q29. How many mattresses does your household own? Ilang kutson ang pag mamay-ari ng
## 0 1 2 3 4 5 6 8 <NA>
## 1316 684 229 53 10 1 1 1 1
## [1] "Frequency table after encoding"
## s5q29. How many mattresses does your household own? Ilang kutson ang pag mamay-ari ng
## 0 1 2 3 4 or more <NA>
## 1316 684 229 53 13 1
mydata <- top_recode ("s5q33", break_point=1, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q33. How many generators does your household own? Ilang generator ang pag mamay-ari
## 0 1 8 <NA>
## 2287 5 3 1
## [1] "Frequency table after encoding"
## s5q33. How many generators does your household own? Ilang generator ang pag mamay-ari
## 0 1 or more <NA>
## 2287 8 1
mydata <- top_recode ("s5q35", break_point=3, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q35. How many televisions does your household own? Ilang telebisyon ang pag mamay-ar
## 0 1 2 3 4 <NA>
## 598 1624 68 4 1 1
## [1] "Frequency table after encoding"
## s5q35. How many televisions does your household own? Ilang telebisyon ang pag mamay-ar
## 0 1 2 3 or more <NA>
## 598 1624 68 5 1
mydata <- top_recode ("s5q37", break_point=3, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q37. How many VCRs/DVD players does your household own? Ilang VCRs/pangtugtog ng DVD
## 0 1 2 3 8 <NA>
## 1550 701 39 3 2 1
## [1] "Frequency table after encoding"
## s5q37. How many VCRs/DVD players does your household own? Ilang VCRs/pangtugtog ng DVD
## 0 1 2 3 or more <NA>
## 1550 701 39 5 1
mydata <- top_recode ("s5q39", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q39. How many computers does your household own? Ilang kompyuter ang pag mamay-ari n
## 0 1 2 8 <NA>
## 2236 51 4 4 1
## [1] "Frequency table after encoding"
## s5q39. How many computers does your household own? Ilang kompyuter ang pag mamay-ari n
## 0 1 2 or more <NA>
## 2236 51 8 1
mydata <- top_recode ("s5q41", break_point=6, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q41. How many farm tools does your household own? Ilang kagamitang pansaka ang pag m
## 0 1 2 3 4 5 6 7 8 9 10 12 14 15 <NA>
## 1636 248 136 109 69 44 24 7 8 6 5 1 1 1 1
## [1] "Frequency table after encoding"
## s5q41. How many farm tools does your household own? Ilang kagamitang pansaka ang pag m
## 0 1 2 3 4 5 6 or more <NA>
## 1636 248 136 109 69 44 53 1
mydata <- top_recode ("s5q43", break_point=1, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q43. How many wheelbarrows does your household own? Ilang kartilya ang pag mamay-ari
## 0 1 2 3 <NA>
## 2266 26 2 1 1
## [1] "Frequency table after encoding"
## s5q43. How many wheelbarrows does your household own? Ilang kartilya ang pag mamay-ari
## 0 1 or more <NA>
## 2266 29 1
mydata <- top_recode ("s5q45", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q45. How many carts does your household own? Ilang kariton ang pag mamay-ari ng iyon
## 0 1 2 3 8 <NA>
## 2193 97 3 1 1 1
## [1] "Frequency table after encoding"
## s5q45. How many carts does your household own? Ilang kariton ang pag mamay-ari ng iyon
## 0 1 2 or more <NA>
## 2193 97 5 1
mydata <- top_recode ("s5q47", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q47. How many kerosene or propane stoves does your household own? Ilang kalang de-pe
## 0 1 2 3 8 <NA>
## 2029 258 5 2 1 1
## [1] "Frequency table after encoding"
## s5q47. How many kerosene or propane stoves does your household own? Ilang kalang de-pe
## 0 1 2 or more <NA>
## 2029 258 8 1
mydata <- top_recode ("s5q49", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q49. How many stoves with oven/gas ranges does your household own? Ilang kalang mayr
## 0 1 2 8 <NA>
## 2014 273 7 1 1
## [1] "Frequency table after encoding"
## s5q49. How many stoves with oven/gas ranges does your household own? Ilang kalang mayr
## 0 1 2 or more <NA>
## 2014 273 8 1
mydata <- top_recode ("s5q51", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q51. How many refrigerators does your household own? Ilang refigerator ang pag mamay
## 0 1 2 19 <NA>
## 2012 276 6 1 1
## [1] "Frequency table after encoding"
## s5q51. How many refrigerators does your household own? Ilang refigerator ang pag mamay
## 0 1 2 or more <NA>
## 2012 276 7 1
mydata <- top_recode ("s5q53", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q53. How many clothes washing machines does your household own? Ilang washing machin
## 0 1 2 4 8 <NA>
## 1850 436 5 1 3 1
## [1] "Frequency table after encoding"
## s5q53. How many clothes washing machines does your household own? Ilang washing machin
## 0 1 2 or more <NA>
## 1850 436 9 1
mydata <- top_recode ("s5q55", break_point=1, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q55. How many air conditioners does your household own? Ilang aircon ang pag mamay-
## 0 1 <NA>
## 2292 3 1
## [1] "Frequency table after encoding"
## s5q55. How many air conditioners does your household own? Ilang aircon ang pag mamay-
## 0 1 or more <NA>
## 2292 3 1
mydata <- top_recode ("s5q56a", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q56a. How many electric fans does your household own? Ilang bentilador ang pag mamay-
## 0 1 2 3 4 5 <NA>
## 809 1011 404 56 9 6 1
## [1] "Frequency table after encoding"
## s5q56a. How many electric fans does your household own? Ilang bentilador ang pag mamay-
## 0 1 2 3 4 or more <NA>
## 809 1011 404 56 15 1
mydata <- top_recode ("s5q56fishnet", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q56fishnet. How many fishing nets does your household own? Ilang lambat ang pagmamay-ari ng
## 0 1 2 3 4 5 6 8 10 12 13 15 17 18 20 21 22 25 26 28 29 <NA>
## 2060 132 27 17 5 7 5 4 13 4 2 3 1 2 6 1 1 1 1 1 1 2
## [1] "Frequency table after encoding"
## s5q56fishnet. How many fishing nets does your household own? Ilang lambat ang pagmamay-ari ng
## 0 1 2 or more <NA>
## 2060 132 102 2
mydata <- top_recode ("s5q56pedicab", break_point=2, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q56pedicab. How many pedicabs does your household own? Ilang pedicabs ang pagmamay-ari ng i
## 0 1 2 3 8 <NA>
## 2207 80 4 3 1 1
## [1] "Frequency table after encoding"
## s5q56pedicab. How many pedicabs does your household own? Ilang pedicabs ang pagmamay-ari ng i
## 0 1 2 or more <NA>
## 2207 80 8 1
mydata <- top_recode ("s5q56ricestock", break_point=4, missing=c(888, 999999))## [1] "Frequency table before encoding"
## s5q56ricestock. How many rice stocks does your household own? Ilang ipon na bigas ang pagmamay-
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
## 1804 129 68 41 15 58 9 6 9 4 57 1 8 3 1 10 1 1 4 2 16 1
## 25 27 28 <NA>
## 42 1 1 4
## [1] "Frequency table after encoding"
## s5q56ricestock. How many rice stocks does your household own? Ilang ipon na bigas ang pagmamay-
## 0 1 2 3 4 or more <NA>
## 1804 129 68 41 250 4
# Top code high values to the 99.5 percentile
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q2)[na.exclude(mydata$s5q2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q2. What is the total value of this/these houses ? Magkano ang kabuuang halaga ng/n
## 0 20 25 30 35 70 80 100 110 120 150 200 300
## 277 1 2 3 1 1 1 2 1 1 2 4 2
## 500 700 1000 1500 2000 2500 2900 3000 3500 4000 4500 5000 6000
## 10 1 15 11 38 6 1 39 2 10 1 138 20
## 6500 7000 8000 9000 10000 11000 12000 13000 14000 14500 15000 16000 16500
## 1 18 13 6 231 3 12 1 5 1 106 3 1
## 17000 18000 19500 20000 25000 27000 29000 30000 35000 36000 40000 45000 48000
## 3 6 1 193 33 1 1 136 19 2 55 8 1
## 50000 53000 55000 56000 57000 58000 60000 62000 65000 70000 73000 75000 80000
## 230 1 3 1 1 1 34 1 1 36 1 6 47
## 85000 90000 92800 95000 1e+05 105000 110000 115000 118000 120000 125000 126000 130000
## 2 2 1 1 154 1 6 1 1 10 2 1 4
## 150000 155000 165000 190000 2e+05 250000 270000 3e+05 4e+05 450000 5e+05 550000 650000
## 54 1 1 1 58 14 1 22 7 2 19 1 1
## 7e+05 8e+05 1e+06 2e+06 2500000 4e+06 1e+07 1.5e+07 <NA>
## 3 3 5 1 1 1 1 1 99
## [1] "Frequency table after encoding"
## s5q2. What is the total value of this/these houses ? Magkano ang kabuuang halaga ng/n
## 0 20 25 30 35 70 80
## 277 1 2 3 1 1 1
## 100 110 120 150 200 300 500
## 2 1 1 2 4 2 10
## 700 1000 1500 2000 2500 2900 3000
## 1 15 11 38 6 1 39
## 3500 4000 4500 5000 6000 6500 7000
## 2 10 1 138 20 1 18
## 8000 9000 10000 11000 12000 13000 14000
## 13 6 231 3 12 1 5
## 14500 15000 16000 16500 17000 18000 19500
## 1 106 3 1 3 6 1
## 20000 25000 27000 29000 30000 35000 36000
## 193 33 1 1 136 19 2
## 40000 45000 48000 50000 53000 55000 56000
## 55 8 1 230 1 3 1
## 57000 58000 60000 62000 65000 70000 73000
## 1 1 34 1 1 36 1
## 75000 80000 85000 90000 92800 95000 1e+05
## 6 47 2 2 1 1 154
## 105000 110000 115000 118000 120000 125000 126000
## 1 6 1 1 10 2 1
## 130000 150000 155000 165000 190000 2e+05 250000
## 4 54 1 1 1 58 14
## 270000 3e+05 4e+05 450000 5e+05 550000 650000
## 1 22 7 2 19 1 1
## 7e+05 8e+05 or more <NA>
## 3 13 99
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q4)[na.exclude(mydata$s5q4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q4. What is the total value of the landline/wireless telephone? Magkano ang kabuuan
## 0 8 300 1500 20000 <NA>
## 2285 3 1 1 1 5
## [1] "Frequency table after encoding"
## s5q4. What is the total value of the landline/wireless telephone? Magkano ang kabuuan
## 0 or more <NA>
## 2291 5
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q6)[na.exclude(mydata$s5q6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q6. What is the total value of these cell phones ? Magkano ang kabuuang halaga ng m
## 0 50 60 100 150 200 250 300 350 370 380 399 400 450 458 495 499 500
## 230 4 1 14 7 54 9 81 3 1 1 9 44 5 1 2 9 271
## 550 599 600 650 700 710 750 760 790 800 850 899 900 950 999 1000 1050 1099
## 4 1 61 2 49 1 3 1 1 53 2 1 26 1 1 239 3 1
## 1100 1180 1199 1200 1250 1299 1300 1350 1400 1497 1500 1600 1700 1800 1898 1900 1999 2000
## 15 1 1 52 3 2 11 1 19 1 143 10 8 18 1 12 1 143
## 2100 2200 2250 2300 2400 2500 2600 2650 2700 2800 2900 2966 3000 3100 3200 3300 3345 3350
## 5 8 1 8 10 47 1 1 7 8 5 1 103 1 9 4 1 1
## 3400 3500 3600 3700 3800 3900 3990 4000 4100 4200 4300 4390 4400 4500 4600 4700 4800 5000
## 4 23 4 3 1 3 1 56 2 3 3 1 2 14 2 2 2 53
## 5200 5300 5499 5500 5800 6000 6050 6200 6500 6700 7000 7300 7500 7800 7998 8000 8400 8500
## 1 2 1 8 1 28 1 3 3 1 22 1 4 1 1 12 1 2
## 8700 9000 9300 9500 10000 10200 10300 10400 10500 10600 10800 11000 11800 12000 12300 15000 16000 17000
## 1 2 1 2 22 1 1 1 2 1 1 1 1 7 1 8 1 1
## 20000 25000 26000 28000 30000 40000 50000 <NA>
## 7 1 1 1 1 1 1 97
## [1] "Frequency table after encoding"
## s5q6. What is the total value of these cell phones ? Magkano ang kabuuang halaga ng m
## 0 50 60 100 150 200 250
## 230 4 1 14 7 54 9
## 300 350 370 380 399 400 450
## 81 3 1 1 9 44 5
## 458 495 499 500 550 599 600
## 1 2 9 271 4 1 61
## 650 700 710 750 760 790 800
## 2 49 1 3 1 1 53
## 850 899 900 950 999 1000 1050
## 2 1 26 1 1 239 3
## 1099 1100 1180 1199 1200 1250 1299
## 1 15 1 1 52 3 2
## 1300 1350 1400 1497 1500 1600 1700
## 11 1 19 1 143 10 8
## 1800 1898 1900 1999 2000 2100 2200
## 18 1 12 1 143 5 8
## 2250 2300 2400 2500 2600 2650 2700
## 1 8 10 47 1 1 7
## 2800 2900 2966 3000 3100 3200 3300
## 8 5 1 103 1 9 4
## 3345 3350 3400 3500 3600 3700 3800
## 1 1 4 23 4 3 1
## 3900 3990 4000 4100 4200 4300 4390
## 3 1 56 2 3 3 1
## 4400 4500 4600 4700 4800 5000 5200
## 2 14 2 2 2 53 1
## 5300 5499 5500 5800 6000 6050 6200
## 2 1 8 1 28 1 3
## 6500 6700 7000 7300 7500 7800 7998
## 3 1 22 1 4 1 1
## 8000 8400 8500 8700 9000 9300 9500
## 12 1 2 1 2 1 2
## 10000 10200 10300 10400 10500 10600 10800
## 22 1 1 1 2 1 1
## 11000 11800 12000 12300 15000 16000 17000
## 1 1 7 1 8 1 1
## 20000 or more <NA>
## 13 97
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q8)[na.exclude(mydata$s5q8)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q8", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q8. What is the total value of sofas ? Magkano ang kabuuang halaga ng mga sofa?
## 0 8 20 30 40 50 100 150 200 210 250 300 350 400 470 500 600 700
## 1633 4 3 1 3 13 25 6 29 1 2 35 1 10 1 85 5 17
## 750 800 900 1000 1050 1100 1200 1300 1500 1600 1700 1800 2000 2100 2200 2300 2400 2500
## 3 7 3 74 1 1 17 4 39 1 4 7 50 1 5 2 3 24
## 2600 2700 2800 3000 3100 3200 3450 3500 3800 4000 4500 5000 5800 6000 6600 7000 8000 10000
## 1 2 3 31 1 1 1 9 2 8 4 20 1 7 1 9 4 7
## 11000 11500 12000 15000 18000 20000 <NA>
## 2 1 3 5 1 2 50
## [1] "Frequency table after encoding"
## s5q8. What is the total value of sofas ? Magkano ang kabuuang halaga ng mga sofa?
## 0 8 20 30 40 50 100
## 1633 4 3 1 3 13 25
## 150 200 210 250 300 350 400
## 6 29 1 2 35 1 10
## 470 500 600 700 750 800 900
## 1 85 5 17 3 7 3
## 1000 1050 1100 1200 1300 1500 1600
## 74 1 1 17 4 39 1
## 1700 1800 2000 2100 2200 2300 2400
## 4 7 50 1 5 2 3
## 2500 2600 2700 2800 3000 3100 3200
## 24 1 2 3 31 1 1
## 3450 3500 3800 4000 4500 5000 5800
## 1 9 2 8 4 20 1
## 6000 6600 7000 8000 10000 11000 11387 or more
## 7 1 9 4 7 2 12
## <NA>
## 50
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q10)[na.exclude(mydata$s5q10)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q10", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q10. What is the total value of the chairs ? Magkano ang kabuuang halaga ng (mga) up
## 0 1 2 4 5 7 8 10 15 20 25 30 40 48 50 60 70 80
## 578 3 1 1 2 1 1 13 1 21 2 10 12 1 96 13 2 6
## 90 100 110 120 125 130 135 140 150 160 170 180 200 210 220 236 240 250
## 6 157 1 4 1 1 1 2 70 2 1 3 131 2 2 1 3 21
## 270 276 300 320 338 350 360 375 390 400 440 450 480 500 508 525 540 550
## 1 1 133 1 1 8 5 2 1 56 1 26 4 129 2 1 6 2
## 560 570 580 600 630 640 660 690 700 710 720 750 780 800 855 875 900 920
## 1 1 1 73 1 5 3 1 24 1 2 23 1 39 1 1 19 1
## 930 960 1000 1050 1080 1090 1100 1140 1150 1155 1200 1250 1300 1320 1350 1400 1440 1500
## 1 2 108 3 2 1 2 1 2 1 20 8 3 1 3 3 1 73
## 1505 1550 1600 1620 1623 1650 1700 1750 1780 1800 1875 1900 1950 1980 2000 2100 2200 2400
## 1 1 4 2 1 1 5 1 1 13 1 3 1 1 41 6 3 3
## 2500 2600 2640 2700 2730 2800 2900 3000 3200 3250 3500 3550 3600 3700 3800 4000 4400 4450
## 19 2 1 7 1 7 2 26 1 1 8 1 1 1 2 7 1 1
## 4500 4700 5000 5040 5150 5200 6200 7000 7500 9700 10000 11000 12000 12500 19680 28000 <NA>
## 2 1 12 1 1 1 1 4 1 1 2 1 1 1 1 1 100
## [1] "Frequency table after encoding"
## s5q10. What is the total value of the chairs ? Magkano ang kabuuang halaga ng (mga) up
## 0 1 2 4 5 7 8 10
## 578 3 1 1 2 1 1 13
## 15 20 25 30 40 48 50 60
## 1 21 2 10 12 1 96 13
## 70 80 90 100 110 120 125 130
## 2 6 6 157 1 4 1 1
## 135 140 150 160 170 180 200 210
## 1 2 70 2 1 3 131 2
## 220 236 240 250 270 276 300 320
## 2 1 3 21 1 1 133 1
## 338 350 360 375 390 400 440 450
## 1 8 5 2 1 56 1 26
## 480 500 508 525 540 550 560 570
## 4 129 2 1 6 2 1 1
## 580 600 630 640 660 690 700 710
## 1 73 1 5 3 1 24 1
## 720 750 780 800 855 875 900 920
## 2 23 1 39 1 1 19 1
## 930 960 1000 1050 1080 1090 1100 1140
## 1 2 108 3 2 1 2 1
## 1150 1155 1200 1250 1300 1320 1350 1400
## 2 1 20 8 3 1 3 3
## 1440 1500 1505 1550 1600 1620 1623 1650
## 1 73 1 1 4 2 1 1
## 1700 1750 1780 1800 1875 1900 1950 1980
## 5 1 1 13 1 3 1 1
## 2000 2100 2200 2400 2500 2600 2640 2700
## 41 6 3 3 19 2 1 7
## 2730 2800 2900 3000 3200 3250 3500 3550
## 1 7 2 26 1 1 8 1
## 3600 3700 3800 4000 4400 4450 4500 4700
## 1 1 2 7 1 1 2 1
## 5000 5040 5150 5200 6200 7000 or more <NA>
## 12 1 1 1 1 13 100
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q12)[na.exclude(mydata$s5q12)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q12", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q12. What is the total value of these tables? Magkano ang kabuuang halaga ng (mga) l
## 0 10 15 20 25 30 35 40 50 60 70 75 80 100 108 120 135 150
## 458 4 1 34 2 12 1 4 122 3 2 1 1 226 1 1 1 69
## 200 240 250 300 350 400 450 500 570 600 640 700 750 800 850 900 950 1000
## 211 1 27 153 21 53 8 267 2 50 1 50 14 25 2 12 3 115
## 1100 1150 1200 1300 1350 1400 1495 1500 1550 1600 1650 1700 1800 1900 1950 2000 2100 2200
## 3 1 15 4 1 4 1 56 1 5 1 1 2 1 1 20 3 2
## 2400 2500 2700 2800 3000 3100 3300 3500 4000 4500 4800 5000 5050 6000 7000 8000 8100 8300
## 1 11 1 1 20 1 1 4 10 1 1 11 1 3 2 1 1 1
## 9000 10000 15000 <NA>
## 1 7 1 135
## [1] "Frequency table after encoding"
## s5q12. What is the total value of these tables? Magkano ang kabuuang halaga ng (mga) l
## 0 10 15 20 25 30 35 40
## 458 4 1 34 2 12 1 4
## 50 60 70 75 80 100 108 120
## 122 3 2 1 1 226 1 1
## 135 150 200 240 250 300 350 400
## 1 69 211 1 27 153 21 53
## 450 500 570 600 640 700 750 800
## 8 267 2 50 1 50 14 25
## 850 900 950 1000 1100 1150 1200 1300
## 2 12 3 115 3 1 15 4
## 1350 1400 1495 1500 1550 1600 1650 1700
## 1 4 1 56 1 5 1 1
## 1800 1900 1950 2000 2100 2200 2400 2500
## 2 1 1 20 3 2 1 11
## 2700 2800 3000 3100 3300 3500 4000 4500
## 1 1 20 1 1 4 10 1
## 4800 5000 5050 6000 7000 8000 8019 or more <NA>
## 1 11 1 3 2 1 11 135
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q14)[na.exclude(mydata$s5q14)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q14", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q14. What is the total value of these clock/watch ? Magkano ang kabuuang halaga ng (
## 0 1 2 5 8 10 15 20 25 30 35 40 45 50 55 60 65 70
## 1180 3 1 5 2 6 1 21 1 13 8 2 5 132 2 17 10 8
## 75 80 85 89 90 95 99 100 103 108 110 118 119 120 125 130 138 140
## 31 15 7 1 5 3 2 220 1 1 4 1 1 31 2 4 1 4
## 150 159 160 170 175 179 180 185 190 200 210 220 225 230 240 250 260 300
## 165 1 4 1 2 1 9 1 2 72 1 2 1 2 3 24 1 47
## 308 330 350 360 400 440 450 470 500 550 565 600 700 750 800 820 900 996
## 1 1 15 1 7 1 3 1 33 2 1 7 7 1 4 1 1 1
## 1000 1100 1150 1200 1500 1550 1600 1800 2000 2100 2500 2800 3000 3200 3600 3700 4000 5000
## 23 2 1 2 6 1 1 1 8 1 4 1 5 1 1 2 1 1
## 5100 14300 <NA>
## 1 1 54
## [1] "Frequency table after encoding"
## s5q14. What is the total value of these clock/watch ? Magkano ang kabuuang halaga ng (
## 0 1 2 5 8 10 15 20
## 1180 3 1 5 2 6 1 21
## 25 30 35 40 45 50 55 60
## 1 13 8 2 5 132 2 17
## 65 70 75 80 85 89 90 95
## 10 8 31 15 7 1 5 3
## 99 100 103 108 110 118 119 120
## 2 220 1 1 4 1 1 31
## 125 130 138 140 150 159 160 170
## 2 4 1 4 165 1 4 1
## 175 179 180 185 190 200 210 220
## 2 1 9 1 2 72 1 2
## 225 230 240 250 260 300 308 330
## 1 2 3 24 1 47 1 1
## 350 360 400 440 450 470 500 550
## 15 1 7 1 3 1 33 2
## 565 600 700 750 800 820 900 996
## 1 7 7 1 4 1 1 1
## 1000 1100 1150 1200 1500 1550 1600 1800
## 23 2 1 2 6 1 1 1
## 2000 2100 2500 2800 3000 or more <NA>
## 8 1 4 1 13 54
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q16)[na.exclude(mydata$s5q16)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q16", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q16. What is the total value of these bicycles ? Magkano ang kabuuang halaga ng (mga
## 0 3 8 15 20 30 50 100 108 150 200 250 300 350 400 450 500 600
## 1755 1 1 1 1 1 8 7 1 2 12 2 25 3 5 1 71 6
## 700 750 800 850 900 1000 1100 1200 1250 1300 1400 1500 1600 1700 1800 1900 2000 2100
## 12 1 14 1 1 71 1 14 1 7 1 62 1 9 12 1 33 3
## 2200 2300 2400 2500 2600 2700 2800 3000 3150 3200 3500 3600 4000 4100 4200 4500 4700 5000
## 4 5 5 26 2 4 6 29 1 1 7 2 3 1 2 4 2 5
## 5500 6000 6800 7000 10000 17000 18000 20000 32000 50000 <NA>
## 1 3 1 3 2 1 1 1 1 1 24
## [1] "Frequency table after encoding"
## s5q16. What is the total value of these bicycles ? Magkano ang kabuuang halaga ng (mga
## 0 3 8 15 20 30 50 100
## 1755 1 1 1 1 1 8 7
## 108 150 200 250 300 350 400 450
## 1 2 12 2 25 3 5 1
## 500 600 700 750 800 850 900 1000
## 71 6 12 1 14 1 1 71
## 1100 1200 1250 1300 1400 1500 1600 1700
## 1 14 1 7 1 62 1 9
## 1800 1900 2000 2100 2200 2300 2400 2500
## 12 1 33 3 4 5 5 26
## 2600 2700 2800 3000 3150 3200 3500 3600
## 2 4 6 29 1 1 7 2
## 4000 4100 4200 4500 4700 5000 5500 6000 or more
## 3 1 2 4 2 5 1 14
## <NA>
## 24
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q18)[na.exclude(mydata$s5q18)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q18", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q18. What is the total value of these tricycles ? Magkano ang kabuuang halaga ng (mg
## 0 8 150 3000 5000 6000 7000 8000 10000 11500 12000 15000 20000 24000 25000
## 2134 5 2 1 2 2 1 2 3 1 2 4 7 3 2
## 26992 27000 30000 32000 34000 35000 38000 40000 42000 45000 47000 49000 49500 50000 52000
## 1 1 9 1 1 4 1 11 1 5 1 1 1 12 1
## 52500 53800 54000 55000 56000 57000 57600 58000 60000 64800 65000 70000 72000 74000 74124
## 1 1 1 1 1 1 1 1 4 1 2 10 1 1 1
## 75000 76000 76416 78660 80000 80700 82800 89000 90000 93000 96000 1e+05 105000 109500 118000
## 7 1 1 1 5 1 2 1 1 1 1 12 1 1 1
## 120000 130000 150000 168000 218980 <NA>
## 1 1 1 1 1 4
## [1] "Frequency table after encoding"
## s5q18. What is the total value of these tricycles ? Magkano ang kabuuang halaga ng (mg
## 0 8 150 3000 5000 6000 7000
## 2134 5 2 1 2 2 1
## 8000 10000 11500 12000 15000 20000 24000
## 2 3 1 2 4 7 3
## 25000 26992 27000 30000 32000 34000 35000
## 2 1 1 9 1 1 4
## 38000 40000 42000 45000 47000 49000 49500
## 1 11 1 5 1 1 1
## 50000 52000 52500 53800 54000 55000 56000
## 12 1 1 1 1 1 1
## 57000 57600 58000 60000 64800 65000 70000
## 1 1 1 4 1 2 10
## 72000 74000 74124 75000 76000 76416 78660
## 1 1 1 7 1 1 1
## 80000 80700 82800 89000 90000 93000 96000
## 5 1 2 1 1 1 1
## 1e+05 or more <NA>
## 20 4
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q20)[na.exclude(mydata$s5q20)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q20", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q20. What is the total value of these motorbikes? Magkano ang kabuuang halaga ng (mg
## 0 5 8 15 17 1500 2000 2500 3000 4000 4500 4600 5000 6000 7000
## 1875 1 1 1 1 1 5 1 6 3 2 1 18 3 2
## 7800 8000 10000 10500 11600 12000 13000 14000 14700 15000 16000 17000 18000 20000 21000
## 1 6 33 3 1 8 2 1 1 21 3 4 5 28 1
## 21600 23000 24000 25000 25200 26000 27000 27200 28000 28500 28800 29000 30000 31000 31200
## 1 2 3 11 1 1 1 1 1 1 1 1 30 2 1
## 32000 32400 33000 34000 35000 36000 37000 37560 38000 40000 41000 42000 43000 43200 43740
## 5 1 1 3 8 2 2 1 3 13 2 1 1 3 1
## 44000 45000 46000 46800 47000 48000 48780 49800 50000 52000 52380 52800 53000 54000 55000
## 2 7 2 1 2 3 1 1 19 1 1 1 1 6 2
## 56000 57000 57600 60000 62000 63800 64000 64800 65000 65550 66060 67000 68000 68400 70000
## 2 1 1 14 1 1 2 3 1 1 1 1 2 1 9
## 72000 72540 74000 75000 75600 76000 77000 79200 80000 82000 82800 84000 85000 89000 90000
## 2 1 1 3 2 1 2 1 4 1 2 1 1 1 1
## 92000 93000 93600 97000 97200 1e+05 104600 110000 111600 120000 126900 130000 131000 140000 150000
## 1 1 1 1 1 5 1 1 1 1 1 1 1 1 2
## 2e+05 240000 320000 <NA>
## 1 1 1 14
## [1] "Frequency table after encoding"
## s5q20. What is the total value of these motorbikes? Magkano ang kabuuang halaga ng (mg
## 0 5 8 15 17 1500 2000
## 1875 1 1 1 1 1 5
## 2500 3000 4000 4500 4600 5000 6000
## 1 6 3 2 1 18 3
## 7000 7800 8000 10000 10500 11600 12000
## 2 1 6 33 3 1 8
## 13000 14000 14700 15000 16000 17000 18000
## 2 1 1 21 3 4 5
## 20000 21000 21600 23000 24000 25000 25200
## 28 1 1 2 3 11 1
## 26000 27000 27200 28000 28500 28800 29000
## 1 1 1 1 1 1 1
## 30000 31000 31200 32000 32400 33000 34000
## 30 2 1 5 1 1 3
## 35000 36000 37000 37560 38000 40000 41000
## 8 2 2 1 3 13 2
## 42000 43000 43200 43740 44000 45000 46000
## 1 1 3 1 2 7 2
## 46800 47000 48000 48780 49800 50000 52000
## 1 2 3 1 1 19 1
## 52380 52800 53000 54000 55000 56000 57000
## 1 1 1 6 2 2 1
## 57600 60000 62000 63800 64000 64800 65000
## 1 14 1 1 2 3 1
## 65550 66060 67000 68000 68400 70000 72000
## 1 1 1 2 1 9 2
## 72540 74000 75000 75600 76000 77000 79200
## 1 1 3 2 1 2 1
## 80000 82000 82800 84000 85000 89000 90000
## 4 1 2 1 1 1 1
## 92000 93000 93600 97000 97200 1e+05 104600
## 1 1 1 1 1 5 1
## 107812 or more <NA>
## 12 14
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q22)[na.exclude(mydata$s5q22)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q22", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q22. What is the total value of these motorized boats/bancas ? Magkano ang kabuuang
## 0 8 1000 1400 1500 2000 2300 3000 4000 4500 5000 7000 8000 10000 12000 12500 13000 14000
## 2173 3 2 1 2 3 1 1 1 1 5 2 2 14 2 1 1 1
## 15000 16000 18000 19000 20000 23000 24000 25000 26800 29000 30000 32000 35000 39500 40000 45000 50000 56000
## 15 1 2 1 12 1 1 6 1 1 9 1 2 1 6 1 4 1
## 60000 68000 70000 75000 1e+05 <NA>
## 4 1 4 1 1 3
## [1] "Frequency table after encoding"
## s5q22. What is the total value of these motorized boats/bancas ? Magkano ang kabuuang
## 0 8 1000 1400 1500 2000 2300
## 2173 3 2 1 2 3 1
## 3000 4000 4500 5000 7000 8000 10000
## 1 1 1 5 2 2 14
## 12000 12500 13000 14000 15000 16000 18000
## 2 1 1 1 15 1 2
## 19000 20000 23000 24000 25000 26800 29000
## 1 12 1 1 6 1 1
## 30000 32000 35000 39500 40000 45000 50000
## 9 1 2 1 6 1 4
## 53239 or more <NA>
## 12 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q24)[na.exclude(mydata$s5q24)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q24", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q24. What is the total value of these other motorized vehicles? Magkano ang kabuuang
## 0 8 1000 2000 2500 3000 5000 6000 8000 10000 12000 20000 25000 35000 70000
## 2271 1 1 1 1 1 1 1 1 1 1 3 2 2 1
## 2e+05 250000 <NA>
## 2 1 4
## [1] "Frequency table after encoding"
## s5q24. What is the total value of these other motorized vehicles? Magkano ang kabuuang
## 0 8 1000 2000 2500 3000 5000
## 2271 1 1 1 1 1 1
## 6000 8000 10000 11090 or more <NA>
## 1 1 1 12 4
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q26)[na.exclude(mydata$s5q26)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q26", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q26. What is the total value of these radio, tape, or CD player ? Magkano ang kabuua
## 0 10 20 30 35 40 50 55 64 100 120 150 180 200 250 270 275 300
## 1327 2 4 1 1 1 19 1 1 47 2 31 1 57 27 1 1 69
## 320 350 380 400 450 495 499 500 520 580 600 640 700 750 790 800 900 1000
## 2 27 3 19 7 1 1 106 1 1 22 1 22 3 1 14 3 78
## 1100 1200 1250 1300 1349 1400 1500 1600 1700 1800 1900 2000 2050 2150 2200 2400 2500 2700
## 2 25 1 7 1 2 84 9 7 7 3 64 2 1 5 2 31 3
## 2750 2800 3000 3200 3400 3500 3900 4000 4100 4500 5000 5400 5500 6000 7000 7800 8000 9000
## 1 4 28 3 1 9 2 4 1 5 9 1 1 6 2 1 2 3
## 10000 15000 19000 20000 <NA>
## 2 5 1 1 43
## [1] "Frequency table after encoding"
## s5q26. What is the total value of these radio, tape, or CD player ? Magkano ang kabuua
## 0 10 20 30 35 40 50 55
## 1327 2 4 1 1 1 19 1
## 64 100 120 150 180 200 250 270
## 1 47 2 31 1 57 27 1
## 275 300 320 350 380 400 450 495
## 1 69 2 27 3 19 7 1
## 499 500 520 580 600 640 700 750
## 1 106 1 1 22 1 22 3
## 790 800 900 1000 1100 1200 1250 1300
## 1 14 3 78 2 25 1 7
## 1349 1400 1500 1600 1700 1800 1900 2000
## 1 2 84 9 7 7 3 64
## 2050 2150 2200 2400 2500 2700 2750 2800
## 2 1 5 2 31 3 1 4
## 3000 3200 3400 3500 3900 4000 4100 4500
## 28 3 1 9 2 4 1 5
## 5000 5400 5500 6000 7000 7800 8000 8739 or more
## 9 1 1 6 2 1 2 12
## <NA>
## 43
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q28)[na.exclude(mydata$s5q28)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q28", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q28. What is the total value of beds ? Magkano ang kabuuang halaga ng (mga) kama?
## 0 2 20 30 40 50 100 150 160 200 250 300 350 400 405 500 550 600
## 1392 1 3 1 1 12 49 19 1 86 9 65 2 30 1 147 1 24
## 640 700 750 800 900 1000 1150 1200 1300 1400 1440 1500 1550 1600 1700 1800 1900 2000
## 1 20 3 19 7 112 1 12 2 3 1 54 1 1 2 2 3 36
## 2100 2200 2250 2300 2500 2600 2800 3000 3200 3500 3550 3600 3800 4000 4400 4500 4700 5000
## 2 3 1 1 10 1 1 36 2 10 1 1 1 8 1 7 1 17
## 5500 6000 6500 6900 7000 8000 8500 9000 10000 10500 11000 12000 13000 13500 15000 17000 <NA>
## 2 3 1 1 3 3 1 1 5 1 1 2 2 1 2 1 38
## [1] "Frequency table after encoding"
## s5q28. What is the total value of beds ? Magkano ang kabuuang halaga ng (mga) kama?
## 0 2 20 30 40 50 100
## 1392 1 3 1 1 12 49
## 150 160 200 250 300 350 400
## 19 1 86 9 65 2 30
## 405 500 550 600 640 700 750
## 1 147 1 24 1 20 3
## 800 900 1000 1150 1200 1300 1400
## 19 7 112 1 12 2 3
## 1440 1500 1550 1600 1700 1800 1900
## 1 54 1 1 2 2 3
## 2000 2100 2200 2250 2300 2500 2600
## 36 2 3 1 1 10 1
## 2800 3000 3200 3500 3550 3600 3800
## 1 36 2 10 1 1 1
## 4000 4400 4500 4700 5000 5500 6000
## 8 1 7 1 17 2 3
## 6500 6900 7000 8000 8500 9000 10000 or more
## 1 1 3 3 1 1 15
## <NA>
## 38
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q30)[na.exclude(mydata$s5q30)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q30", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q30. What is the total value of these mattresses ? Magkano ang kabuuang halaga ng (m
## 0 5 8 10 20 50 60 100 120 150 200 250 300 350 400 450 500 550
## 1331 1 2 1 3 15 1 35 1 5 43 3 30 3 9 2 83 1
## 600 650 700 800 900 960 1000 1100 1200 1300 1350 1400 1440 1450 1500 1600 1700 1800
## 11 1 16 28 9 1 114 3 26 3 1 6 1 1 63 6 1 13
## 1950 1999 2000 2100 2200 2250 2300 2400 2500 2600 2700 2800 2900 3000 3200 3300 3400 3500
## 1 1 64 2 3 1 2 8 23 4 2 11 3 60 13 4 1 24
## 3550 3600 3800 3900 4000 4100 4200 4400 4500 4600 4700 4800 4900 5000 5200 5400 5500 5600
## 1 3 4 2 21 1 1 1 18 2 1 7 7 20 1 1 2 2
## 5900 6000 6500 6800 7000 7200 7500 7600 7800 8000 8500 9000 10000 10500 11900 12800 13500 14800
## 1 10 1 1 6 1 2 1 2 5 1 2 6 3 1 1 1 1
## 16000 18000 <NA>
## 1 1 53
## [1] "Frequency table after encoding"
## s5q30. What is the total value of these mattresses ? Magkano ang kabuuang halaga ng (m
## 0 5 8 10 20 50 60
## 1331 1 2 1 3 15 1
## 100 120 150 200 250 300 350
## 35 1 5 43 3 30 3
## 400 450 500 550 600 650 700
## 9 2 83 1 11 1 16
## 800 900 960 1000 1100 1200 1300
## 28 9 1 114 3 26 3
## 1350 1400 1440 1450 1500 1600 1700
## 1 6 1 1 63 6 1
## 1800 1950 1999 2000 2100 2200 2250
## 13 1 1 64 2 3 1
## 2300 2400 2500 2600 2700 2800 2900
## 2 8 23 4 2 11 3
## 3000 3200 3300 3400 3500 3550 3600
## 60 13 4 1 24 1 3
## 3800 3900 4000 4100 4200 4400 4500
## 4 2 21 1 1 1 18
## 4600 4700 4800 4900 5000 5200 5400
## 2 1 7 7 20 1 1
## 5500 5600 5900 6000 6500 6800 7000
## 2 2 1 10 1 1 6
## 7200 7500 7600 7800 8000 8500 9000
## 1 2 1 2 5 1 2
## 10000 or more <NA>
## 15 53
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q32)[na.exclude(mydata$s5q32)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q32", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q32. What is the total value of these solar panels? Magkano ang kabuuang halaga ng (
## 0 8 25 100 150 200 250 255 280 285 300 350 500 600 800 1000 1500 2000
## 2250 3 1 5 2 3 3 1 1 1 4 2 2 1 1 2 2 3
## 2800 3000 3500 4800 9500 20000 <NA>
## 1 1 1 1 1 1 3
## [1] "Frequency table after encoding"
## s5q32. What is the total value of these solar panels? Magkano ang kabuuang halaga ng (
## 0 8 25 100 150 200 250 255
## 2250 3 1 5 2 3 3 1
## 280 285 300 350 500 600 800 1000 or more
## 1 1 4 2 2 1 1 13
## <NA>
## 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q34)[na.exclude(mydata$s5q34)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q34", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q34. What is the total value of the generators? Magkano ang kabuuang halaga ng (mga)
## 0 8 5000 10000 11000 80000 <NA>
## 2285 3 1 2 1 1 3
## [1] "Frequency table after encoding"
## s5q34. What is the total value of the generators? Magkano ang kabuuang halaga ng (mga)
## 0 or more <NA>
## 2293 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q36)[na.exclude(mydata$s5q36)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q36", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q36. What is the total value of these televisions ? Magkano ang kabuuang halaga ng (
## 0 1 20 25 40 50 60 75 100 150 200 250 300 400 450 500 550 600
## 615 1 4 2 1 16 1 1 20 5 14 5 21 5 1 92 2 6
## 650 700 800 900 1000 1030 1100 1200 1300 1400 1500 1550 1600 1700 1750 1799 1800 1900
## 1 18 23 4 183 1 4 49 8 13 215 1 18 34 1 1 50 11
## 1950 2000 2003 2100 2199 2200 2300 2400 2500 2600 2700 2800 2900 3000 3100 3200 3295 3300
## 1 187 1 7 1 20 7 7 85 3 8 13 8 113 1 5 1 2
## 3400 3408 3500 3600 3700 3800 3900 3999 4000 4200 4500 4600 4700 4800 5000 5100 5300 5600
## 3 1 34 3 2 2 1 1 48 2 12 1 1 1 50 1 1 1
## 5700 6000 6500 7000 7500 7800 8000 8200 8500 8680 9000 9500 9900 10000 10500 11000 12000 13000
## 1 14 2 20 2 1 16 1 1 1 6 2 1 25 1 5 8 1
## 14000 15000 16000 17000 18000 19000 19500 20000 21000 22000 23000 24000 25000 26000 27000 30000 <NA>
## 6 9 2 1 3 3 1 5 1 2 1 1 4 1 1 2 63
## [1] "Frequency table after encoding"
## s5q36. What is the total value of these televisions ? Magkano ang kabuuang halaga ng (
## 0 1 20 25 40 50 60
## 615 1 4 2 1 16 1
## 75 100 150 200 250 300 400
## 1 20 5 14 5 21 5
## 450 500 550 600 650 700 800
## 1 92 2 6 1 18 23
## 900 1000 1030 1100 1200 1300 1400
## 4 183 1 4 49 8 13
## 1500 1550 1600 1700 1750 1799 1800
## 215 1 18 34 1 1 50
## 1900 1950 2000 2003 2100 2199 2200
## 11 1 187 1 7 1 20
## 2300 2400 2500 2600 2700 2800 2900
## 7 7 85 3 8 13 8
## 3000 3100 3200 3295 3300 3400 3408
## 113 1 5 1 2 3 1
## 3500 3600 3700 3800 3900 3999 4000
## 34 3 2 2 1 1 48
## 4200 4500 4600 4700 4800 5000 5100
## 2 12 1 1 1 50 1
## 5300 5600 5700 6000 6500 7000 7500
## 1 1 1 14 2 20 2
## 7800 8000 8200 8500 8680 9000 9500
## 1 16 1 1 1 6 2
## 9900 10000 10500 11000 12000 13000 14000
## 1 25 1 5 8 1 6
## 15000 16000 17000 18000 19000 19500 20000
## 9 2 1 3 3 1 5
## 21000 21840 or more <NA>
## 1 12 63
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q38)[na.exclude(mydata$s5q38)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q38", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q38. What is the total value of these VCRs/DVD players? Magkano ang kabuuang halaga
## 0 8 10 20 30 40 50 100 150 200 208 210 250 300 350 400 500 520
## 1549 3 4 3 3 1 16 14 6 11 1 1 1 20 2 9 109 1
## 550 600 700 750 800 900 1000 1100 1200 1250 1300 1349 1365 1400 1450 1500 1600 1700
## 1 6 12 1 15 3 120 6 52 2 14 1 1 9 1 128 8 10
## 1750 1800 1900 2000 2200 2300 2400 2500 2700 2800 3000 3200 3300 3500 3600 3700 3800 3900
## 1 9 3 45 4 1 3 12 1 2 15 1 1 2 1 1 1 2
## 4000 4500 5000 6000 8000 10000 13000 16000 50000 <NA>
## 7 1 6 3 1 4 1 1 1 22
## [1] "Frequency table after encoding"
## s5q38. What is the total value of these VCRs/DVD players? Magkano ang kabuuang halaga
## 0 8 10 20 30 40 50 100
## 1549 3 4 3 3 1 16 14
## 150 200 208 210 250 300 350 400
## 6 11 1 1 1 20 2 9
## 500 520 550 600 700 750 800 900
## 109 1 1 6 12 1 15 3
## 1000 1100 1200 1250 1300 1349 1365 1400
## 120 6 52 2 14 1 1 9
## 1450 1500 1600 1700 1750 1800 1900 2000
## 1 128 8 10 1 9 3 45
## 2200 2300 2400 2500 2700 2800 3000 3200
## 4 1 3 12 1 2 15 1
## 3300 3500 3600 3700 3800 3900 4000 4500
## 1 2 1 1 1 2 7 1
## 5000 or more <NA>
## 17 22
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q40)[na.exclude(mydata$s5q40)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q40", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q40. What is the total value of these computer ? Magkano ang kabuuang halaga ng (mga
## 0 1 200 1000 1500 1600 2000 2500 3000 4000 4500 5000 6000 6500 7000 12000 13000 13500
## 2240 1 2 2 1 1 2 1 2 1 2 7 1 1 3 3 1 1
## 15000 16000 17000 18000 22000 24000 26000 34000 57000 60000 <NA>
## 5 1 1 1 1 1 1 1 1 1 10
## [1] "Frequency table after encoding"
## s5q40. What is the total value of these computer ? Magkano ang kabuuang halaga ng (mga
## 0 1 200 1000 1500 1600 2000
## 2240 1 2 2 1 1 2
## 2500 3000 4000 4500 5000 6000 6500
## 1 2 1 2 7 1 1
## 7000 12000 13000 13500 15000 or more <NA>
## 3 3 1 1 14 10
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q42)[na.exclude(mydata$s5q42)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q42", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q42. What is the total value of farm tools ? Magkano ang kabuuang halaga ng (mga) ka
## 0 5 8 20 30 35 50 60 75 100 120 150 180 200 230
## 1637 1 1 2 3 1 17 1 1 41 2 25 2 35 1
## 250 280 300 320 350 360 380 400 440 450 500 520 540 550 594
## 13 2 32 1 10 2 2 23 1 15 53 1 1 1 1
## 600 610 620 650 700 720 750 770 780 800 840 850 900 940 950
## 22 1 1 2 15 1 4 1 1 12 1 3 6 1 2
## 1000 1050 1100 1130 1150 1200 1245 1250 1300 1350 1400 1420 1500 1550 1600
## 48 1 2 1 1 6 1 1 5 1 6 1 30 1 1
## 1700 1750 1800 1900 2000 2050 2100 2200 2250 2400 2500 2550 2600 2700 2800
## 3 1 2 3 25 1 3 1 1 1 14 1 1 2 3
## 2850 2900 3000 3150 3400 3500 3550 3800 4000 4100 4500 4600 4800 4950 5000
## 1 3 25 1 1 4 1 1 10 1 4 1 1 1 13
## 5200 5300 5500 5750 6000 6300 6600 7000 7500 8000 9000 9600 10000 12000 15000
## 1 1 1 1 5 1 1 1 1 2 1 1 4 1 7
## 17000 18000 20000 25000 26000 27000 30000 31350 33000 35000 42000 45000 75000 80000 111700
## 1 2 1 1 1 1 2 1 1 2 1 1 1 1 1
## 189000 <NA>
## 1 11
## [1] "Frequency table after encoding"
## s5q42. What is the total value of farm tools ? Magkano ang kabuuang halaga ng (mga) ka
## 0 5 8 20 30 35 50
## 1637 1 1 2 3 1 17
## 60 75 100 120 150 180 200
## 1 1 41 2 25 2 35
## 230 250 280 300 320 350 360
## 1 13 2 32 1 10 2
## 380 400 440 450 500 520 540
## 2 23 1 15 53 1 1
## 550 594 600 610 620 650 700
## 1 1 22 1 1 2 15
## 720 750 770 780 800 840 850
## 1 4 1 1 12 1 3
## 900 940 950 1000 1050 1100 1130
## 6 1 2 48 1 2 1
## 1150 1200 1245 1250 1300 1350 1400
## 1 6 1 1 5 1 6
## 1420 1500 1550 1600 1700 1750 1800
## 1 30 1 1 3 1 2
## 1900 2000 2050 2100 2200 2250 2400
## 3 25 1 3 1 1 1
## 2500 2550 2600 2700 2800 2850 2900
## 14 1 1 2 3 1 3
## 3000 3150 3400 3500 3550 3800 4000
## 25 1 1 4 1 1 10
## 4100 4500 4600 4800 4950 5000 5200
## 1 4 1 1 1 13 1
## 5300 5500 5750 6000 6300 6600 7000
## 1 1 1 5 1 1 1
## 7500 8000 9000 9600 10000 12000 15000
## 1 2 1 1 4 1 7
## 17000 18000 20000 25000 26000 27000 28739 or more
## 1 2 1 1 1 1 12
## <NA>
## 11
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q44)[na.exclude(mydata$s5q44)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q44", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q44. What is the total value of wheelbarrows ? Magkano ang kabuuang halaga ng (mga)
## 0 8 100 150 200 500 600 700 800 900 1000 1500 1700 2000 2500 2600 4000 24000
## 2262 2 2 2 1 5 1 2 1 1 5 1 1 1 2 1 2 1
## <NA>
## 3
## [1] "Frequency table after encoding"
## s5q44. What is the total value of wheelbarrows ? Magkano ang kabuuang halaga ng (mga)
## 0 8 100 150 200 500 600 700
## 2262 2 2 2 1 5 1 2
## 800 900 1000 or more <NA>
## 1 1 14 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q46)[na.exclude(mydata$s5q46)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q46", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q46. What is the total value of these carts ? Magkano ang kabuuang halaga ng (mga) k
## 0 8 50 100 150 200 250 300 500 600 780 1000 1500 1800 2000 2500 3000 3500
## 2188 4 2 2 1 2 1 2 2 1 1 8 6 1 9 7 13 1
## 4000 4500 5000 5500 6000 7000 7500 8000 9000 10000 13500 17000 <NA>
## 5 3 14 1 3 4 1 1 1 4 1 1 6
## [1] "Frequency table after encoding"
## s5q46. What is the total value of these carts ? Magkano ang kabuuang halaga ng (mga) k
## 0 8 50 100 150 200 250 300
## 2188 4 2 2 1 2 1 2
## 500 600 780 1000 1500 1800 2000 2500
## 2 1 1 8 6 1 9 7
## 3000 3500 4000 4500 5000 5500 6000 7000 or more
## 13 1 5 3 14 1 3 13
## <NA>
## 6
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q48)[na.exclude(mydata$s5q48)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q48", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q48. What is the total value of these kerosene or propane stove ? Magkano ang kabuua
## 0 5 8 30 50 150 200 250 300 350 375 380 400 420 425 430 435 450
## 2027 1 5 1 1 2 5 2 9 3 1 1 4 2 1 1 1 4
## 480 490 500 530 550 580 595 600 700 750 800 900 1000 1100 1146 1200 1250 1300
## 1 1 39 1 1 1 1 5 12 2 5 5 32 5 1 21 1 3
## 1400 1500 1600 1700 1750 1800 1900 2000 2100 2200 2250 2300 2400 2500 2700 2900 3000 3100
## 2 15 2 5 1 5 2 14 1 2 1 1 1 7 1 1 9 2
## 3400 3600 4500 15000 <NA>
## 1 1 1 1 12
## [1] "Frequency table after encoding"
## s5q48. What is the total value of these kerosene or propane stove ? Magkano ang kabuua
## 0 5 8 30 50 150 200 250
## 2027 1 5 1 1 2 5 2
## 300 350 375 380 400 420 425 430
## 9 3 1 1 4 2 1 1
## 435 450 480 490 500 530 550 580
## 1 4 1 1 39 1 1 1
## 595 600 700 750 800 900 1000 1100
## 1 5 12 2 5 5 32 5
## 1146 1200 1250 1300 1400 1500 1600 1700
## 1 21 1 3 2 15 2 5
## 1750 1800 1900 2000 2100 2200 2250 2300
## 1 5 2 14 1 2 1 1
## 2400 2500 2700 2900 3000 or more <NA>
## 1 7 1 1 15 12
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q50)[na.exclude(mydata$s5q50)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q50", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q50. What is the total value of these stoves with ovens/gas ranges ? Magkano ang kab
## 0 8 9 10 20 30 40 50 75 80 100 130 150 200 230 250 300 400
## 2011 4 1 1 3 1 1 9 1 2 2 1 3 9 1 1 12 4
## 420 450 500 550 599 600 650 700 750 800 850 900 950 995 1000 1100 1200 1300
## 1 2 25 3 1 12 2 19 3 16 2 4 1 1 22 2 15 3
## 1400 1500 1600 1700 1900 2000 2200 2300 2400 2500 2800 3000 3200 3500 3700 4100 4500 5000
## 2 25 4 3 2 15 2 1 1 11 3 6 2 1 1 1 1 1
## 5500 6000 13000 <NA>
## 1 1 1 10
## [1] "Frequency table after encoding"
## s5q50. What is the total value of these stoves with ovens/gas ranges ? Magkano ang kab
## 0 8 9 10 20 30 40 50
## 2011 4 1 1 3 1 1 9
## 75 80 100 130 150 200 230 250
## 1 2 2 1 3 9 1 1
## 300 400 420 450 500 550 599 600
## 12 4 1 2 25 3 1 12
## 650 700 750 800 850 900 950 995
## 2 19 3 16 2 4 1 1
## 1000 1100 1200 1300 1400 1500 1600 1700
## 22 2 15 3 2 25 4 3
## 1900 2000 2200 2300 2400 2500 2800 3000 or more
## 2 15 2 1 1 11 3 16
## <NA>
## 10
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q52)[na.exclude(mydata$s5q52)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q52", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q52. What is the total value of these refrigerators ? Magkano ang kabuuang halaga ng
## 0 8 50 150 200 250 300 500 700 1000 1500 2000 2500 3000 3200 3500 4000 4300
## 2011 3 1 2 5 1 1 10 1 15 8 20 3 21 1 7 4 1
## 4500 5000 6000 6500 7000 7200 7500 8000 8500 8700 9000 9500 10000 10500 11000 11300 11500 12000
## 2 21 9 1 18 1 1 16 1 1 7 1 24 1 8 1 2 9
## 13000 14000 15000 16000 16500 17000 17500 18000 20000 21000 22000 24000 25000 30000 <NA>
## 7 4 1 4 1 1 1 7 3 2 2 1 1 2 20
## [1] "Frequency table after encoding"
## s5q52. What is the total value of these refrigerators ? Magkano ang kabuuang halaga ng
## 0 8 50 150 200 250 300
## 2011 3 1 2 5 1 1
## 500 700 1000 1500 2000 2500 3000
## 10 1 15 8 20 3 21
## 3200 3500 4000 4300 4500 5000 6000
## 1 7 4 1 2 21 9
## 6500 7000 7200 7500 8000 8500 8700
## 1 18 1 1 16 1 1
## 9000 9500 10000 10500 11000 11300 11500
## 7 1 24 1 8 1 2
## 12000 13000 14000 15000 16000 16500 17000
## 9 7 4 1 4 1 1
## 17500 18000 or more <NA>
## 1 18 20
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q54)[na.exclude(mydata$s5q54)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q54", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q54. What is the total value of these clothes washing machines ? Magkano ang kabuuan
## 0 8 30 50 100 150 200 300 400 500 700 800 1000 1200 1500 1600 1700 1800
## 1855 1 1 1 5 1 5 5 1 20 8 4 29 2 25 2 1 5
## 1900 2000 2100 2200 2300 2400 2500 2600 2700 2800 2850 2900 3000 3025 3100 3200 3400 3500
## 2 36 3 4 3 7 42 7 12 6 1 3 38 1 1 9 1 20
## 3600 3700 3900 4000 4100 4200 4250 4400 4500 4700 5000 5500 6000 6300 6500 7000 7200 7500
## 1 2 1 15 1 4 1 1 10 2 23 5 13 1 3 7 1 3
## 8000 9000 10000 11000 12000 13000 15000 45000 <NA>
## 3 3 4 1 3 2 1 1 17
## [1] "Frequency table after encoding"
## s5q54. What is the total value of these clothes washing machines ? Magkano ang kabuuan
## 0 8 30 50 100 150 200 300
## 1855 1 1 1 5 1 5 5
## 400 500 700 800 1000 1200 1500 1600
## 1 20 8 4 29 2 25 2
## 1700 1800 1900 2000 2100 2200 2300 2400
## 1 5 2 36 3 4 3 7
## 2500 2600 2700 2800 2850 2900 3000 3025
## 42 7 12 6 1 3 38 1
## 3100 3200 3400 3500 3600 3700 3900 4000
## 1 9 1 20 1 2 1 15
## 4100 4200 4250 4400 4500 4700 5000 5500
## 1 4 1 1 10 2 23 5
## 6000 6300 6500 7000 7200 7500 8000 9000
## 13 1 3 7 1 3 3 3
## 9610 or more <NA>
## 12 17
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q56)[na.exclude(mydata$s5q56)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q56", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q56. What is the total value of these air conditioners ? Magkano ang kabuuang halaga
## 0 8 3000 8000 <NA>
## 2290 1 1 1 3
## [1] "Frequency table after encoding"
## s5q56. What is the total value of these air conditioners ? Magkano ang kabuuang halaga
## 0 or more <NA>
## 2293 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q56b)[na.exclude(mydata$s5q56b)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q56b", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q56b. What is the total value of these electric fans ? Magkano ang kabuuang halaga ng
## 0 5 8 10 15 20 30 35 40 50 60 80 85 90 95 100 120 130
## 819 1 3 3 1 9 1 1 3 26 1 2 1 2 1 42 3 1
## 150 160 175 180 199 200 210 240 250 300 308 330 350 360 380 400 450 475
## 21 1 1 1 1 73 1 1 11 103 1 1 17 2 1 43 13 1
## 480 499 500 529 549 550 570 580 599 600 620 645 650 660 680 690 695 699
## 1 3 203 1 1 13 1 3 1 75 1 1 18 1 5 1 1 2
## 700 721 725 730 750 755 775 799 800 830 850 900 945 950 960 990 998 999
## 113 1 1 1 17 1 1 1 69 1 6 29 1 4 1 1 1 2
## 1000 1050 1064 1100 1150 1160 1200 1250 1280 1300 1350 1380 1400 1450 1470 1497 1500 1540
## 111 1 1 15 1 1 43 2 1 14 1 1 29 1 1 1 80 1
## 1550 1575 1600 1650 1700 1800 1900 2000 2100 2200 2250 2300 2350 2400 2500 2550 2600 2700
## 2 1 9 1 8 9 4 34 2 3 1 5 1 5 13 1 3 2
## 2750 2900 3000 3100 3200 3500 4000 4500 5000 5500 9000 17400 <NA>
## 1 2 15 4 1 2 1 3 2 1 1 1 57
## [1] "Frequency table after encoding"
## s5q56b. What is the total value of these electric fans ? Magkano ang kabuuang halaga ng
## 0 5 8 10 15 20 30 35
## 819 1 3 3 1 9 1 1
## 40 50 60 80 85 90 95 100
## 3 26 1 2 1 2 1 42
## 120 130 150 160 175 180 199 200
## 3 1 21 1 1 1 1 73
## 210 240 250 300 308 330 350 360
## 1 1 11 103 1 1 17 2
## 380 400 450 475 480 499 500 529
## 1 43 13 1 1 3 203 1
## 549 550 570 580 599 600 620 645
## 1 13 1 3 1 75 1 1
## 650 660 680 690 695 699 700 721
## 18 1 5 1 1 2 113 1
## 725 730 750 755 775 799 800 830
## 1 1 17 1 1 1 69 1
## 850 900 945 950 960 990 998 999
## 6 29 1 4 1 1 1 2
## 1000 1050 1064 1100 1150 1160 1200 1250
## 111 1 1 15 1 1 43 2
## 1280 1300 1350 1380 1400 1450 1470 1497
## 1 14 1 1 29 1 1 1
## 1500 1540 1550 1575 1600 1650 1700 1800
## 80 1 2 1 9 1 8 9
## 1900 2000 2100 2200 2250 2300 2350 2400
## 4 34 2 3 1 5 1 5
## 2500 2550 2600 2700 2750 2900 3000 3100
## 13 1 3 2 1 2 15 4
## 3180 or more <NA>
## 12 57
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q56fishnet2)[na.exclude(mydata$s5q56fishnet2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q56fishnet2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q56fishnet2. What is the total value of these fishing nets ? Ano ang kabuuang halaga ng mga
## 0 2 8 50 100 150 180 200 250 260 300 320 380 400 450 500 600 690
## 2062 1 1 4 4 2 1 3 1 1 8 1 1 2 1 13 2 1
## 700 750 800 900 980 990 1000 1010 1200 1500 1600 1650 1700 1750 2000 2100 2200 2400
## 3 1 4 2 1 1 26 1 4 19 2 1 1 1 13 1 1 1
## 2500 2600 2800 3000 3400 3500 3780 4000 4500 4700 4750 5000 6000 7000 8000 9500 10000 12000
## 9 1 2 21 1 1 1 6 1 1 1 14 3 4 3 1 8 1
## 13000 15000 18000 20000 24000 26000 30000 35000 40000 60000 1e+05 <NA>
## 1 5 1 6 2 1 2 1 1 1 1 3
## [1] "Frequency table after encoding"
## s5q56fishnet2. What is the total value of these fishing nets ? Ano ang kabuuang halaga ng mga
## 0 2 8 50 100 150 180
## 2062 1 1 4 4 2 1
## 200 250 260 300 320 380 400
## 3 1 1 8 1 1 2
## 450 500 600 690 700 750 800
## 1 13 2 1 3 1 4
## 900 980 990 1000 1010 1200 1500
## 2 1 1 26 1 4 19
## 1600 1650 1700 1750 2000 2100 2200
## 2 1 1 1 13 1 1
## 2400 2500 2600 2800 3000 3400 3500
## 1 9 1 2 21 1 1
## 3780 4000 4500 4700 4750 5000 6000
## 1 6 1 1 1 14 3
## 7000 8000 9500 10000 12000 13000 15000
## 4 3 1 8 1 1 5
## 18000 20000 or more <NA>
## 1 15 3
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q56pedicab2)[na.exclude(mydata$s5q56pedicab2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q56pedicab2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q56pedicab2. What is the total value of these pedicabs? Ano ang kabuuang halaga ng mga pedic
## 0 8 300 336 500 700 1000 1500 2000 2100 3000 3500 4000 4200 4500 5000 5600 6000
## 2203 3 1 1 3 1 4 5 5 1 9 1 6 1 4 14 1 5
## 7000 8000 9000 10000 12000 13000 14000 20000 21000 21600 25000 35000 80000 <NA>
## 3 3 1 3 2 1 1 1 1 4 2 1 1 4
## [1] "Frequency table after encoding"
## s5q56pedicab2. What is the total value of these pedicabs? Ano ang kabuuang halaga ng mga pedic
## 0 8 300 336 500 700 1000
## 2203 3 1 1 3 1 4
## 1500 2000 2100 3000 3500 4000 4200
## 5 5 1 9 1 6 1
## 4500 5000 5600 6000 7000 8000 9000
## 4 14 1 5 3 3 1
## 10000 12000 12545 or more <NA>
## 3 2 12 4
percentile_99.5 <- floor(quantile(na.exclude(mydata$s5q56ricestock2)[na.exclude(mydata$s5q56ricestock2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s5q56ricestock2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s5q56ricestock2. What is the total value of these rice stocks? Ano ang kabuuang halaga ng ipon n
## 0 7 8 20 32 34 35 36 38 40 45 50 51 56 60 62 64 66
## 1800 1 1 1 1 1 9 1 1 2 2 1 1 1 4 2 4 3
## 70 72 74 80 82 86 90 92 96 98 99 100 102 105 108 110 113 114
## 9 4 1 4 1 1 5 1 3 1 1 2 1 5 2 1 1 1
## 116 120 126 128 130 135 138 140 145 150 160 165 170 175 180 188 189 190
## 1 2 2 1 1 1 1 1 1 7 6 4 3 5 3 1 1 1
## 198 200 210 215 233 238 252 265 270 280 300 308 320 324 330 336 340 350
## 1 6 3 1 1 1 1 1 2 1 8 1 6 1 2 1 1 11
## 360 370 378 380 400 408 410 420 429 430 450 465 473 500 504 525 540 544
## 4 1 1 5 8 1 1 3 1 1 5 1 1 8 1 1 3 1
## 550 555 600 620 640 660 680 700 720 722 725 740 750 800 810 825 850 875
## 1 1 7 1 2 1 1 14 1 1 1 1 14 10 1 1 6 3
## 900 920 925 930 950 1000 1015 1025 1050 1100 1150 1155 1200 1250 1280 1300 1350 1400
## 10 2 1 1 1 16 1 1 4 2 1 1 12 1 1 1 1 1
## 1500 1550 1600 1700 1750 1800 1900 2000 2100 2200 2250 2300 2500 2520 2600 2800 3000 3060
## 20 1 6 1 1 9 1 19 4 1 1 1 4 1 1 1 10 1
## 3185 3440 3500 3600 3825 4000 4200 4400 4500 4550 4800 4900 5000 5400 5530 5600 5850 6000
## 1 1 1 2 1 3 4 1 4 1 3 1 4 1 1 1 1 2
## 6600 6700 6750 6800 7000 7176 7200 7400 7500 7650 7800 8000 8400 8800 9000 9180 9600 9750
## 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1
## 10000 10800 11200 12800 13500 14400 15000 18900 34200 <NA>
## 2 2 1 1 3 1 1 1 1 4
## [1] "Frequency table after encoding"
## s5q56ricestock2. What is the total value of these rice stocks? Ano ang kabuuang halaga ng ipon n
## 0 7 8 20 32 34 35
## 1800 1 1 1 1 1 9
## 36 38 40 45 50 51 56
## 1 1 2 2 1 1 1
## 60 62 64 66 70 72 74
## 4 2 4 3 9 4 1
## 80 82 86 90 92 96 98
## 4 1 1 5 1 3 1
## 99 100 102 105 108 110 113
## 1 2 1 5 2 1 1
## 114 116 120 126 128 130 135
## 1 1 2 2 1 1 1
## 138 140 145 150 160 165 170
## 1 1 1 7 6 4 3
## 175 180 188 189 190 198 200
## 5 3 1 1 1 1 6
## 210 215 233 238 252 265 270
## 3 1 1 1 1 1 2
## 280 300 308 320 324 330 336
## 1 8 1 6 1 2 1
## 340 350 360 370 378 380 400
## 1 11 4 1 1 5 8
## 408 410 420 429 430 450 465
## 1 1 3 1 1 5 1
## 473 500 504 525 540 544 550
## 1 8 1 1 3 1 1
## 555 600 620 640 660 680 700
## 1 7 1 2 1 1 14
## 720 722 725 740 750 800 810
## 1 1 1 1 14 10 1
## 825 850 875 900 920 925 930
## 1 6 3 10 2 1 1
## 950 1000 1015 1025 1050 1100 1150
## 1 16 1 1 4 2 1
## 1155 1200 1250 1280 1300 1350 1400
## 1 12 1 1 1 1 1
## 1500 1550 1600 1700 1750 1800 1900
## 20 1 6 1 1 9 1
## 2000 2100 2200 2250 2300 2500 2520
## 19 4 1 1 1 4 1
## 2600 2800 3000 3060 3185 3440 3500
## 1 1 10 1 1 1 1
## 3600 3825 4000 4200 4400 4500 4550
## 2 1 3 4 1 4 1
## 4800 4900 5000 5400 5530 5600 5850
## 3 1 4 1 1 1 1
## 6000 6600 6700 6750 6800 7000 7176
## 2 1 1 1 1 1 1
## 7200 7400 7500 7650 7800 8000 8400
## 1 1 1 1 1 2 2
## 8800 9000 9180 9600 9750 10000 or more <NA>
## 1 1 1 1 1 13 4
mydata <- mydata[!names(mydata) %in% "s5q58_month"]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("s5q57",
"s5q63",
"s5q65_1",
"s5q65_2")
capture_tables (indirect_PII)
# Recode those with very specific values.
val_labels(mydata$s5q65_1)## -999. No Response 1. GSIS 2. SSS 3. Scholarships 4. Other:Specify
## -999 1 2 3 4break_transfers <- c(1,2,3,4)
labels_tranfers <- c("GSIS"=1,
"Other" = 2,
"Scholarships" = 3,
"other: Specify"=4)
mydata <- ordinal_recode (variable="s5q65_1", break_points=break_transfers, missing=999999, value_labels=labels_tranfers)
## [1] "Frequency table before encoding"
## s5q65_1. In the past 12 months, what government transfers did you receive? Sa nakaraang
## 2. SSS 3. Scholarships 4. Other:Specify <NA>
## 26 82 46 2142
## recoded
## [1,2) [2,3) [3,4) [4,1e+06)
## 2 0 26 0 0
## 3 0 0 82 0
## 4 0 0 0 46
## [1] "Frequency table after encoding"
## s5q65_1. In the past 12 months, what government transfers did you receive? Sa nakaraang
## Other Scholarships other: Specify <NA>
## 26 82 46 2142
## [1] "Inspect value labels and relabel as necessary"
## GSIS Other Scholarships other: Specify
## 1 2 3 4Matching 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("s5q1whynoresponse",
"s5q3whynoresponse",
"s5q5whynoresponse",
"s5q7whynoresponse",
"s5q9whynoresponse",
"s5q11whynoresponse",
"s5q13whynoresponse",
"s5q15whynoresponse",
"s5q17whynoresponse",
"s5q19whynoresponse",
"s5q21whynoresponse",
"s5q23whynoresponse",
"s5q25whynoresponse",
"s5q27whynoresponse",
"s5q29whynoresponse",
"s5q31whynoresponse",
"s5q33whynoresponse",
"s5q35whynoresponse",
"s5q37whynoresponse",
"s5q39whynoresponse",
"s5q41whynoresponse",
"s5q43whynoresponse",
"s5q45whynoresponse",
"s5q47whynoresponse",
"s5q49whynoresponse",
"s5q51whynoresponse",
"s5q53whynoresponse",
"s5q55whynoresponse",
"s5q56awhynoresponse",
"s5q56fishnetwhynoresponse",
"s5q56pedicabwhynoresponse",
"s5q56ricestockwhynoresponse",
"s5q57whynoresponse",
"s5q59whynoresponse",
"s5q60whynoresponse",
"s5q61whynoresponse",
"s5q62whynoresponse",
"s5q63whynoresponse",
"s5q64whynoresponse",
"s5q65whynoresponse",
"s5q65other")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
mydata$s5q1whynoresponse[50] <- "Materials was provided by Gold sun"
mydata$s5q1whynoresponse[97] <- "[Tagalog]"
mydata$s5q1whynoresponse[745] <- "Father owned the house and [situation]"
mydata$s5q1whynoresponse[961] <- "She cannot estimate the price because of the quality of their house"
mydata$s5q1whynoresponse[1026] <- "She does not know and does not want to answer. The house is owned by the [person]."
mydata$s5q1whynoresponse[1100] <- "Cannot estimate because the house is made only in a [type of materials]"
mydata$s5q1whynoresponse[1156] <- "Their house is made by [object]."
mydata$s5q1whynoresponse[1161] <- "Cannot assess value inherited house and lot, but the house and lot is big I think is almost [amount] sq.m."
mydata$s5q1whynoresponse[1448] <- "Materials came from [site]."
mydata$s5q1whynoresponse[1449] <- "[Type of materials]"
mydata$s5q7whynoresponse[1512] <- "They dont want to give any amount even if ill tell is is it [amount redacted]???"
mydata$s5q9whynoresponse[139] <- "[name] only repaired it"
mydata$s5q13whynoresponse[157] <- "[Tagalog]"
mydata$s5q13whynoresponse[139] <- "Came from a [person]"
mydata$s5q29whynoresponse[1451] <- "Came from [foundation]"
mydata$s5q51whynoresponse[1294] <- "[Person redacted]"
mydata$s5q56awhynoresponse[615] <- "Raffle price ([amount redacted])"
mydata$s5q56fishnetwhynoresponse[1078] <- "2 or more"
mydata$s5q56ricestockwhynoresponse[55] <- "[amount redacted] rice stocks. Total value of [amount redacted]"
mydata$s5q56ricestockwhynoresponse[451] <- "[amount redacted]"
mydata$s5q56ricestockwhynoresponse[491] <- "[amount redacted] kilos of milled rice"
mydata$s5q57whynoresponse[740] <- "The mother of the 2 grandchildren is the member of the 4Ps. But the 2 children is [situation]"
mydata$s5q57whynoresponse[1237] <- "The member of the 4ps is [name] son of [name] she is the one who attended all the meetings of 4ps every now and then. [name] is not member of the roster because he is only once or every another month going back home."
mydata$s5q60whynoresponse[712] <- "He is not sure if it is more than [amount redacted] per 2 months, his wife knows"
mydata$s5q62whynoresponse[932] <- "It was stopped because they were transferred here in [site], [province] since 2012"
mydata$s5q65other[1083] <- "[Tagalog]"
mydata$s5q65other[1694] <- "[Tagalog]"
mydata$s5q65other[1812] <- "[Tagalog]"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)