DOL-ILAB SDC - Section_6
Pablo Diego-Rosell, PhD
2021-10-02
- Setup filenames
- Setup data, functions and create dictionary for dataset review
- Direct PII: variables to be removed
- Direct PII-team: Encode field team names
- Small locations: Encode locations with pop <100,000 using random large numbers
- Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
- Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
- Matching and crosstabulations: Run automated PII check
- Open-ends: review responses for any sensitive information, redact as necessary
- GPS data: Displace
- Save processed data in Stata and SPSS format
rm(list=ls(all=t))Setup filenames
filename <- "Section_6" # !!!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 ("s6q12count", break_point=4, missing=c(888, 999999)) ## [1] "Frequency table before encoding"
## s6q12count. How many crops did you grow In the last 12 months? Ilang panahim ang iyong tina
## 0 1 2 3 4 5 6 10 19 <NA>
## 4 302 124 42 29 22 8 1 1 1763
## [1] "Frequency table after encoding"
## s6q12count. How many crops did you grow In the last 12 months? Ilang panahim ang iyong tina
## 0 1 2 3 4 or more <NA>
## 4 302 124 42 61 1763
# Top code high values to the 99.5 percentile
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q2)[na.exclude(mydata$s6q2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q2. How many units is this land? Ilang pangkat ang lupang ito?
## 0 1 2 3 4 5 6 7 8 10 12 15 16 18 20 24 25 30
## 4 38 9 6 2 1 1 1 2 2 1 2 3 1 3 1 7 6
## 33 35 40 41 42 45 46 47 48 50 54 56 57 60 63 64 70 72
## 1 4 6 1 2 2 1 1 3 20 1 2 1 14 1 1 2 2
## 75 80 84 90 95 96 100 104 105 108 117 120 135 140 144 147 150 168
## 2 9 1 4 2 2 30 1 2 1 1 7 1 1 2 2 18 3
## 180 200 218 220 225 238 240 250 255 278 288 300 308 330 360 386 393 400
## 4 11 1 1 5 1 2 8 1 1 2 14 1 1 2 1 1 6
## 406 430 450 481 499 500 600 624 695 700 750 800 840 900 996 1000 1200 1300
## 1 1 3 1 1 10 6 1 1 1 1 3 1 2 1 2 1 1
## 1424 1500 1575 1800 1884 2000 2500 3000 4000 5000 6250 7000 8000 15000 <NA>
## 1 3 1 1 1 3 6 1 2 9 1 1 3 1 1917
## [1] "Frequency table after encoding"
## s6q2. How many units is this land? Ilang pangkat ang lupang ito?
## 0 1 2 3 4 5 6 7
## 4 38 9 6 2 1 1 1
## 8 10 12 15 16 18 20 24
## 2 2 1 2 3 1 3 1
## 25 30 33 35 40 41 42 45
## 7 6 1 4 6 1 2 2
## 46 47 48 50 54 56 57 60
## 1 1 3 20 1 2 1 14
## 63 64 70 72 75 80 84 90
## 1 1 2 2 2 9 1 4
## 95 96 100 104 105 108 117 120
## 2 2 30 1 2 1 1 7
## 135 140 144 147 150 168 180 200
## 1 1 2 2 18 3 4 11
## 218 220 225 238 240 250 255 278
## 1 1 5 1 2 8 1 1
## 288 300 308 330 360 386 393 400
## 2 14 1 1 2 1 1 6
## 406 430 450 481 499 500 600 624
## 1 1 3 1 1 10 6 1
## 695 700 750 800 840 900 996 1000
## 1 1 1 3 1 2 1 2
## 1200 1300 1424 1500 1575 1800 1884 2000
## 1 1 1 3 1 1 1 3
## 2500 3000 4000 5000 6250 7000 8000 or more <NA>
## 6 1 2 9 1 1 4 1917
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q4a)[na.exclude(mydata$s6q4a)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q4a", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q4a. How many units is this land? Ilang yunits ang lupang ito?
## 0 1 2 3 4 5 6 7 8 15 20 25 28 30 36 40 50 68
## 1 44 20 9 4 3 2 2 2 2 1 1 1 4 1 3 2 1
## 75 96 98 100 105 150 200 250 280 384 406 500 510 700 1000 1500 1600 1800
## 1 1 1 5 1 2 3 5 2 1 1 11 1 1 3 3 1 1
## 2000 2400 2500 3000 5000 5800 6000 6500 7000 7500 10000 13000 14000 15000 <NA>
## 1 1 8 1 12 1 3 1 3 1 4 1 1 2 2109
## [1] "Frequency table after encoding"
## s6q4a. How many units is this land? Ilang yunits ang lupang ito?
## 0 1 2 3 4 5 6
## 1 44 20 9 4 3 2
## 7 8 15 20 25 28 30
## 2 2 2 1 1 1 4
## 36 40 50 68 75 96 98
## 1 3 2 1 1 1 1
## 100 105 150 200 250 280 384
## 5 1 2 3 5 2 1
## 406 500 510 700 1000 1500 1600
## 1 11 1 1 3 3 1
## 1800 2000 2400 2500 3000 5000 5800
## 1 1 1 8 1 12 1
## 6000 6500 7000 7500 10000 13000 14000
## 3 1 3 1 4 1 1
## 15000 or more <NA>
## 2 2109
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q7)[na.exclude(mydata$s6q7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q7. How much did your household pay to rent this land in the last 12 months? Magkan
## 0 200 305 350 400 440 500 600 950 1000 1320 1500 1545 1800 2000
## 12 1 1 1 1 1 3 2 1 7 1 2 1 1 6
## 2063 2100 2200 2400 2500 2800 2880 3000 3125 3300 3750 3900 4000 4032 4200
## 1 2 1 4 2 1 1 4 1 1 1 1 5 1 1
## 4800 5000 5208 5250 5525 6000 6720 6800 7000 7200 7320 8182 8700 9350 10000
## 1 7 1 1 1 2 1 1 1 1 1 1 1 1 2
## 10800 11200 12000 12600 14000 17600 20000 24000 25000 31000 31775 40000 45000 57600 127500
## 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## <NA>
## 2190
## [1] "Frequency table after encoding"
## s6q7. How much did your household pay to rent this land in the last 12 months? Magkan
## 0 200 305 350 400 440 500
## 12 1 1 1 1 1 3
## 600 950 1000 1320 1500 1545 1800
## 2 1 7 1 2 1 1
## 2000 2063 2100 2200 2400 2500 2800
## 6 1 2 1 4 2 1
## 2880 3000 3125 3300 3750 3900 4000
## 1 4 1 1 1 1 5
## 4032 4200 4800 5000 5208 5250 5525
## 1 1 1 7 1 1 1
## 6000 6720 6800 7000 7200 7320 8182
## 2 1 1 1 1 1 1
## 8700 9350 10000 10800 11200 12000 12600
## 1 1 2 1 1 1 1
## 14000 17600 20000 24000 25000 31000 31775
## 1 1 1 1 1 1 1
## 40000 45000 57600 90802 or more <NA>
## 1 1 1 1 2190
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q9)[na.exclude(mydata$s6q9)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q9", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q9. What was your household's share as a percentage of output? Ano ang parte ng iyo
## 0 1 2 3 5 7 8 10 12 13 15 16 17 20 25 30 40 50 60 66 70 75
## 6 3 1 1 1 1 1 18 2 3 4 1 1 8 10 3 1 25 5 1 9 9
## 80 83 85 90 91 100 <NA>
## 12 1 2 6 1 10 2150
## [1] "Frequency table after encoding"
## s6q9. What was your household's share as a percentage of output? Ano ang parte ng iyo
## 0 1 2 3 5 7 8 10 12
## 6 3 1 1 1 1 1 18 2
## 13 15 16 17 20 25 30 40 50
## 3 4 1 1 8 10 3 1 25
## 60 66 70 75 80 83 85 90 91
## 5 1 9 9 12 1 2 6 1
## 100 or more <NA>
## 10 2150
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q9a)[na.exclude(mydata$s6q9a)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q9a", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q9a. How much did your household earn from sharecropping in the last 12 months? Magk
## 0 200 300 440 500 800 1200 1475 1500 1700 1800 1850 2000 2100 2250
## 19 1 1 1 1 1 2 1 1 1 1 1 4 1 1
## 2400 2700 2904 3000 3130 3150 3300 3500 3900 4000 4186 5000 5400 5600 5850
## 1 1 1 4 1 1 1 2 1 5 1 5 1 1 1
## 6000 7000 7200 7650 8000 8400 9000 9375 9750 9800 10000 11400 11900 12000 12800
## 5 2 1 1 6 1 3 1 1 1 8 1 1 4 1
## 13000 13500 14000 14480 15000 15300 16000 17000 17500 18000 18720 18900 19200 19500 20000
## 1 1 1 1 1 1 1 1 1 2 1 1 1 1 6
## 20418 22500 24000 25000 25500 27000 29124 29750 30000 32000 34000 36000 37350 38500 38640
## 1 1 1 1 1 1 1 1 4 2 1 1 1 1 1
## 45750 50000 70000 72000 80000 82800 168000 <NA>
## 1 1 1 1 1 1 1 2148
## [1] "Frequency table after encoding"
## s6q9a. How much did your household earn from sharecropping in the last 12 months? Magk
## 0 200 300 440 500 800 1200
## 19 1 1 1 1 1 2
## 1475 1500 1700 1800 1850 2000 2100
## 1 1 1 1 1 4 1
## 2250 2400 2700 2904 3000 3130 3150
## 1 1 1 1 4 1 1
## 3300 3500 3900 4000 4186 5000 5400
## 1 2 1 5 1 5 1
## 5600 5850 6000 7000 7200 7650 8000
## 1 1 5 2 1 1 6
## 8400 9000 9375 9750 9800 10000 11400
## 1 3 1 1 1 8 1
## 11900 12000 12800 13000 13500 14000 14480
## 1 4 1 1 1 1 1
## 15000 15300 16000 17000 17500 18000 18720
## 1 1 1 1 1 2 1
## 18900 19200 19500 20000 20418 22500 24000
## 1 1 1 6 1 1 1
## 25000 25500 27000 29124 29750 30000 32000
## 1 1 1 1 1 4 2
## 34000 36000 37350 38500 38640 45750 50000
## 1 1 1 1 1 1 1
## 70000 72000 80000 82800 105377 or more <NA>
## 1 1 1 1 1 2148
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q11)[na.exclude(mydata$s6q11)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q11", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q11. How much did your household receive as rental payment for this land in the last
## 0 200 800 1000 4000 5000 45000 60000 <NA>
## 2 1 1 2 1 1 1 1 2286
## [1] "Frequency table after encoding"
## s6q11. How much did your household receive as rental payment for this land in the last
## 0 200 800 1000 4000 5000 45000
## 2 1 1 2 1 1 1
## 59325 or more <NA>
## 1 2286
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q17_1)[na.exclude(mydata$s6q17_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q17_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q17_1. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 84 90 100 120 150 200 220 250 300 450 500 574 600 750
## 4 1 2 4 1 1 3 2 3 2 1 4 1 4 1
## 776 800 860 900 950 1000 1050 1085 1100 1150 1200 1300 1500 1545 1580
## 1 1 1 3 1 12 1 1 1 1 4 1 11 1 1
## 1600 2000 2160 2250 2300 2400 2500 2800 3000 3400 3500 3940 4000 4500 4650
## 1 17 1 1 1 2 3 1 17 1 2 1 11 3 1
## 5000 5800 6000 6350 6600 6750 7000 8000 9000 9800 10000 10250 10500 12000 12750
## 34 1 8 1 1 1 4 2 2 1 37 1 1 8 1
## 13000 14000 15000 15690 16600 18800 20000 21000 24160 25000 27000 28000 30000 31000 33000
## 2 2 14 1 1 1 16 1 1 10 1 1 14 1 1
## 35000 37500 40000 42000 42400 48000 50000 65000 66000 80000 1e+05 180000 2e+05 <NA>
## 1 1 4 1 1 1 1 1 1 3 1 1 1 1970
## [1] "Frequency table after encoding"
## s6q17_1. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 84 90 100 120 150 200
## 4 1 2 4 1 1 3
## 220 250 300 450 500 574 600
## 2 3 2 1 4 1 4
## 750 776 800 860 900 950 1000
## 1 1 1 1 3 1 12
## 1050 1085 1100 1150 1200 1300 1500
## 1 1 1 1 4 1 11
## 1545 1580 1600 2000 2160 2250 2300
## 1 1 1 17 1 1 1
## 2400 2500 2800 3000 3400 3500 3940
## 2 3 1 17 1 2 1
## 4000 4500 4650 5000 5800 6000 6350
## 11 3 1 34 1 8 1
## 6600 6750 7000 8000 9000 9800 10000
## 1 1 4 2 2 1 37
## 10250 10500 12000 12750 13000 14000 15000
## 1 1 8 1 2 2 14
## 15690 16600 18800 20000 21000 24160 25000
## 1 1 1 16 1 1 10
## 27000 28000 30000 31000 33000 35000 37500
## 1 1 14 1 1 1 1
## 40000 42000 42400 48000 50000 65000 66000
## 4 1 1 1 1 1 1
## 80000 1e+05 130000 or more <NA>
## 3 1 2 1970
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_1)[na.exclude(mydata$s6q19_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_1. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 4 5 6 7 8 10 11 12 13 14 15
## 13 19 14 12 7 6 10 8 10 24 4 4 2 4 13
## 16 17 18 19 20 21 22 24 25 26 27 28 30 31 32
## 3 2 5 1 16 6 4 5 6 2 5 2 17 2 4
## 33 35 36 37 38 39 40 41 42 43 44 45 47 48 50
## 1 4 2 1 1 1 18 2 2 1 2 3 2 1 23
## 51 56 58 59 60 61 62 63 64 65 66 68 69 70 73
## 1 4 2 1 9 1 1 1 1 1 1 1 2 8 1
## 74 75 77 79 80 85 86 88 90 93 94 95 99 100 105
## 1 1 1 1 10 2 1 1 2 1 1 1 1 25 2
## 110 111 114 120 140 144 150 153 158 160 168 175 180 192 200
## 1 1 1 3 1 1 8 1 1 1 1 1 2 1 8
## 210 223 240 268 280 288 300 310 350 360 370 385 400 431 480
## 1 1 4 1 1 1 7 1 1 2 1 1 1 1 1
## 500 560 576 590 600 700 767 800 864 900 1000 1200 1333 1500 1590
## 6 1 1 1 2 2 1 3 1 1 9 1 1 3 1
## 1750 1800 2000 2400 2582 3000 3250 3500 4000 4500 5000 6000 6400 8100 8775
## 1 3 4 2 1 4 1 1 1 1 4 2 1 1 1
## 9000 10000 11200 12000 13200 14000 18000 19200 20000 21000 24000 25000 30800 32000 35000
## 1 3 1 2 1 1 1 1 2 1 2 1 1 1 1
## 36000 50000 60000 133000 277500 <NA>
## 1 1 1 1 1 1772
## [1] "Frequency table after encoding"
## s6q19_1. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 4 5 6
## 13 19 14 12 7 6 10
## 7 8 10 11 12 13 14
## 8 10 24 4 4 2 4
## 15 16 17 18 19 20 21
## 13 3 2 5 1 16 6
## 22 24 25 26 27 28 30
## 4 5 6 2 5 2 17
## 31 32 33 35 36 37 38
## 2 4 1 4 2 1 1
## 39 40 41 42 43 44 45
## 1 18 2 2 1 2 3
## 47 48 50 51 56 58 59
## 2 1 23 1 4 2 1
## 60 61 62 63 64 65 66
## 9 1 1 1 1 1 1
## 68 69 70 73 74 75 77
## 1 2 8 1 1 1 1
## 79 80 85 86 88 90 93
## 1 10 2 1 1 2 1
## 94 95 99 100 105 110 111
## 1 1 1 25 2 1 1
## 114 120 140 144 150 153 158
## 1 3 1 1 8 1 1
## 160 168 175 180 192 200 210
## 1 1 1 2 1 8 1
## 223 240 268 280 288 300 310
## 1 4 1 1 1 7 1
## 350 360 370 385 400 431 480
## 1 2 1 1 1 1 1
## 500 560 576 590 600 700 767
## 6 1 1 1 2 2 1
## 800 864 900 1000 1200 1333 1500
## 3 1 1 9 1 1 3
## 1590 1750 1800 2000 2400 2582 3000
## 1 1 3 4 2 1 4
## 3250 3500 4000 4500 5000 6000 6400
## 1 1 1 1 4 2 1
## 8100 8775 9000 10000 11200 12000 13200
## 1 1 1 3 1 2 1
## 14000 18000 19200 20000 21000 24000 25000
## 1 1 1 2 1 2 1
## 30800 32000 35000 36000 50000 53849 or more <NA>
## 1 1 1 1 1 3 1772
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_1)[na.exclude(mydata$s6q20_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_1. What is the total market value of the quantity harvested in the last 12 months?
## 0 10 11 15 16 20 30 31 50 90 100 105 135 150 168
## 14 2 1 1 1 1 1 1 2 1 2 1 1 2 1
## 180 200 225 240 250 300 360 375 400 417 450 500 525 544 600
## 1 3 1 2 1 8 1 1 4 1 1 7 1 1 2
## 629 660 700 720 750 784 795 800 820 900 920 950 980 1000 1050
## 1 1 2 2 2 1 1 1 1 3 1 2 1 7 1
## 1120 1200 1250 1280 1300 1350 1360 1400 1440 1500 1560 1600 1740 1755 1800
## 2 1 1 1 1 1 1 1 1 10 1 1 1 1 4
## 1980 2000 2025 2145 2240 2250 2300 2400 2432 2500 2700 3000 3060 3120 3200
## 1 7 1 1 1 1 1 5 1 4 1 6 2 1 1
## 3360 3450 3500 3600 3700 3760 4000 4200 4320 4500 4608 4680 4800 4900 5000
## 2 1 5 1 1 1 6 1 1 1 1 1 1 3 7
## 5500 5600 5920 5985 5986 6000 6050 6100 6300 6400 6438 6500 6825 6900 7000
## 1 2 1 1 1 9 1 1 3 1 1 3 1 1 2
## 7200 7425 7500 8000 8250 8450 8704 8772 9000 9350 9500 9625 9800 9984 10000
## 2 1 2 9 1 1 1 1 8 1 2 1 1 1 6
## 10200 10500 10556 10944 11000 11040 11250 11500 11505 11600 11900 12000 12168 12288 12440
## 1 3 1 1 2 1 1 1 1 1 1 11 1 1 1
## 12500 12600 12960 13000 13120 13156 13200 13300 13800 14000 14560 15000 15120 15300 15600
## 1 1 2 1 1 1 1 1 1 3 1 2 2 1 1
## 16150 16200 16500 16800 16905 17280 17550 17600 17640 18000 18600 18900 19200 19500 19840
## 1 1 1 3 1 1 1 1 1 4 1 2 4 2 1
## 20000 20800 20832 21000 21060 21600 22000 22320 22344 22400 22500 22680 23400 24000 24050
## 8 1 1 2 1 2 1 1 1 2 4 1 1 4 1
## 24518 24960 25000 25200 25819 26000 26190 26312 26400 26464 26565 26600 27000 27300 28000
## 1 1 1 1 1 2 1 1 2 1 1 1 5 1 1
## 28500 29000 29750 30000 30132 30800 31000 31110 31320 31500 32000 32300 32480 33000 33331
## 1 2 1 3 1 1 1 1 1 1 5 1 1 1 1
## 33600 34000 34500 35000 35400 36000 37500 37856 38000 38250 39000 39990 40000 40800 41400
## 2 1 1 2 1 3 2 1 1 1 2 1 2 2 1
## 42000 45000 45750 45800 46116 46200 47376 47500 47600 48000 48600 50000 50400 52000 52091
## 3 1 1 1 1 2 1 1 1 2 1 3 1 3 1
## 52500 53000 53760 54000 54400 55000 56000 58212 58500 59500 59800 60000 60060 60885 62100
## 1 1 1 2 1 2 1 1 1 1 1 2 1 1 1
## 62400 62480 63000 63200 64416 64500 72000 73080 75000 75600 79800 80000 81000 84000 85000
## 1 1 1 1 1 1 2 1 1 1 1 2 1 1 1
## 87500 93795 100800 110160 111000 119700 120000 125568 130000 134300 144000 150000 153600 173940 175000
## 1 1 1 1 1 1 1 1 1 1 1 3 1 1 1
## 186000 210000 277500 340000 343750 413000 450000 455000 540000 <NA>
## 1 1 1 1 1 1 1 1 1 1786
## [1] "Frequency table after encoding"
## s6q20_1. What is the total market value of the quantity harvested in the last 12 months?
## 0 10 11 15 16 20 30
## 14 2 1 1 1 1 1
## 31 50 90 100 105 135 150
## 1 2 1 2 1 1 2
## 168 180 200 225 240 250 300
## 1 1 3 1 2 1 8
## 360 375 400 417 450 500 525
## 1 1 4 1 1 7 1
## 544 600 629 660 700 720 750
## 1 2 1 1 2 2 2
## 784 795 800 820 900 920 950
## 1 1 1 1 3 1 2
## 980 1000 1050 1120 1200 1250 1280
## 1 7 1 2 1 1 1
## 1300 1350 1360 1400 1440 1500 1560
## 1 1 1 1 1 10 1
## 1600 1740 1755 1800 1980 2000 2025
## 1 1 1 4 1 7 1
## 2145 2240 2250 2300 2400 2432 2500
## 1 1 1 1 5 1 4
## 2700 3000 3060 3120 3200 3360 3450
## 1 6 2 1 1 2 1
## 3500 3600 3700 3760 4000 4200 4320
## 5 1 1 1 6 1 1
## 4500 4608 4680 4800 4900 5000 5500
## 1 1 1 1 3 7 1
## 5600 5920 5985 5986 6000 6050 6100
## 2 1 1 1 9 1 1
## 6300 6400 6438 6500 6825 6900 7000
## 3 1 1 3 1 1 2
## 7200 7425 7500 8000 8250 8450 8704
## 2 1 2 9 1 1 1
## 8772 9000 9350 9500 9625 9800 9984
## 1 8 1 2 1 1 1
## 10000 10200 10500 10556 10944 11000 11040
## 6 1 3 1 1 2 1
## 11250 11500 11505 11600 11900 12000 12168
## 1 1 1 1 1 11 1
## 12288 12440 12500 12600 12960 13000 13120
## 1 1 1 1 2 1 1
## 13156 13200 13300 13800 14000 14560 15000
## 1 1 1 1 3 1 2
## 15120 15300 15600 16150 16200 16500 16800
## 2 1 1 1 1 1 3
## 16905 17280 17550 17600 17640 18000 18600
## 1 1 1 1 1 4 1
## 18900 19200 19500 19840 20000 20800 20832
## 2 4 2 1 8 1 1
## 21000 21060 21600 22000 22320 22344 22400
## 2 1 2 1 1 1 2
## 22500 22680 23400 24000 24050 24518 24960
## 4 1 1 4 1 1 1
## 25000 25200 25819 26000 26190 26312 26400
## 1 1 1 2 1 1 2
## 26464 26565 26600 27000 27300 28000 28500
## 1 1 1 5 1 1 1
## 29000 29750 30000 30132 30800 31000 31110
## 2 1 3 1 1 1 1
## 31320 31500 32000 32300 32480 33000 33331
## 1 1 5 1 1 1 1
## 33600 34000 34500 35000 35400 36000 37500
## 2 1 1 2 1 3 2
## 37856 38000 38250 39000 39990 40000 40800
## 1 1 1 2 1 2 2
## 41400 42000 45000 45750 45800 46116 46200
## 1 3 1 1 1 1 2
## 47376 47500 47600 48000 48600 50000 50400
## 1 1 1 2 1 3 1
## 52000 52091 52500 53000 53760 54000 54400
## 3 1 1 1 1 2 1
## 55000 56000 58212 58500 59500 59800 60000
## 2 1 1 1 1 1 2
## 60060 60885 62100 62400 62480 63000 63200
## 1 1 1 1 1 1 1
## 64416 64500 72000 73080 75000 75600 79800
## 1 1 2 1 1 1 1
## 80000 81000 84000 85000 87500 93795 100800
## 2 1 1 1 1 1 1
## 110160 111000 119700 120000 125568 130000 134300
## 1 1 1 1 1 1 1
## 144000 150000 153600 173940 175000 186000 210000
## 1 3 1 1 1 1 1
## 277500 340000 343750 413000 429834 or more <NA>
## 1 1 1 1 3 1786
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_1)[na.exclude(mydata$s6q21_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_1. What was the total revenue received from this crop harvest (sold in market trans
## 0 20 74 75 100 105 135 140 150 200 240 250 300 320 330
## 124 1 1 1 2 1 1 1 4 1 1 1 3 1 1
## 360 375 400 417 475 480 500 525 600 700 720 800 840 920 930
## 1 1 1 1 1 1 4 1 4 1 2 3 1 1 2
## 1000 1040 1120 1280 1360 1400 1500 1560 1590 1600 1740 1750 1800 2000 2320
## 13 1 2 2 1 1 7 1 1 2 1 1 6 12 1
## 2400 2500 2565 2600 2625 2640 2700 2765 2800 2950 2980 2990 3000 3120 3200
## 1 3 1 1 1 1 2 1 1 1 1 1 11 1 1
## 3290 3500 3700 3900 4000 4140 4186 4200 4500 4690 4800 4900 5000 5103 5400
## 1 6 1 1 8 1 1 1 3 1 1 3 10 1 2
## 5500 5986 6000 6090 6250 6500 6688 6750 7000 7200 7425 7500 7650 8000 8500
## 2 1 4 1 1 1 1 1 3 1 1 4 1 3 1
## 9000 9360 9450 9500 9600 9800 10000 10400 10500 10800 10944 11000 11100 11200 11500
## 4 1 2 1 2 1 11 1 1 1 1 2 1 1 1
## 11885 12000 12600 13156 13200 13650 13800 14000 14250 14400 14560 15000 15288 16000 16100
## 1 13 1 1 1 1 1 2 1 1 1 6 1 1 1
## 16150 16200 16800 16905 17000 18000 18500 18846 19000 19200 19300 19440 19500 20000 20160
## 1 1 1 1 2 4 1 1 1 1 1 1 2 7 1
## 20800 20832 21000 22000 22320 22680 22875 23680 24000 24464 25000 25200 25500 25616 25819
## 1 1 2 1 1 1 1 1 3 1 2 2 1 1 1
## 26364 26400 26565 27000 29000 29750 30000 31000 31110 31500 32000 33331 33500 33600 34000
## 1 1 1 4 1 1 5 1 1 1 2 1 1 1 2
## 35400 36000 37500 37800 38500 39000 39600 40000 40320 40800 41000 42000 43750 45000 46080
## 1 2 2 1 2 1 1 3 1 1 1 1 1 1 1
## 47500 48000 48600 48608 50000 50250 50880 51040 52500 52780 53000 58000 58212 58500 60000
## 1 1 1 1 4 1 1 1 1 1 1 1 1 1 3
## 62100 64000 64416 66000 70000 74400 76000 78000 82800 83778 87500 91800 100800 115300 116220
## 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1
## 120000 125568 140000 150000 206250 450000 455000 540000 <NA>
## 1 1 1 2 1 1 1 1 1781
## [1] "Frequency table after encoding"
## s6q21_1. What was the total revenue received from this crop harvest (sold in market trans
## 0 20 74 75 100 105 135
## 124 1 1 1 2 1 1
## 140 150 200 240 250 300 320
## 1 4 1 1 1 3 1
## 330 360 375 400 417 475 480
## 1 1 1 1 1 1 1
## 500 525 600 700 720 800 840
## 4 1 4 1 2 3 1
## 920 930 1000 1040 1120 1280 1360
## 1 2 13 1 2 2 1
## 1400 1500 1560 1590 1600 1740 1750
## 1 7 1 1 2 1 1
## 1800 2000 2320 2400 2500 2565 2600
## 6 12 1 1 3 1 1
## 2625 2640 2700 2765 2800 2950 2980
## 1 1 2 1 1 1 1
## 2990 3000 3120 3200 3290 3500 3700
## 1 11 1 1 1 6 1
## 3900 4000 4140 4186 4200 4500 4690
## 1 8 1 1 1 3 1
## 4800 4900 5000 5103 5400 5500 5986
## 1 3 10 1 2 2 1
## 6000 6090 6250 6500 6688 6750 7000
## 4 1 1 1 1 1 3
## 7200 7425 7500 7650 8000 8500 9000
## 1 1 4 1 3 1 4
## 9360 9450 9500 9600 9800 10000 10400
## 1 2 1 2 1 11 1
## 10500 10800 10944 11000 11100 11200 11500
## 1 1 1 2 1 1 1
## 11885 12000 12600 13156 13200 13650 13800
## 1 13 1 1 1 1 1
## 14000 14250 14400 14560 15000 15288 16000
## 2 1 1 1 6 1 1
## 16100 16150 16200 16800 16905 17000 18000
## 1 1 1 1 1 2 4
## 18500 18846 19000 19200 19300 19440 19500
## 1 1 1 1 1 1 2
## 20000 20160 20800 20832 21000 22000 22320
## 7 1 1 1 2 1 1
## 22680 22875 23680 24000 24464 25000 25200
## 1 1 1 3 1 2 2
## 25500 25616 25819 26364 26400 26565 27000
## 1 1 1 1 1 1 4
## 29000 29750 30000 31000 31110 31500 32000
## 1 1 5 1 1 1 2
## 33331 33500 33600 34000 35400 36000 37500
## 1 1 1 2 1 2 2
## 37800 38500 39000 39600 40000 40320 40800
## 1 2 1 1 3 1 1
## 41000 42000 43750 45000 46080 47500 48000
## 1 1 1 1 1 1 1
## 48600 48608 50000 50250 50880 51040 52500
## 1 1 4 1 1 1 1
## 52780 53000 58000 58212 58500 60000 62100
## 1 1 1 1 1 3 1
## 64000 64416 66000 70000 74400 76000 78000
## 1 1 1 2 1 1 1
## 82800 83778 87500 91800 100800 115300 116220
## 1 1 1 1 1 1 1
## 120000 125568 140000 150000 206250 311062 or more <NA>
## 1 1 1 2 1 3 1781
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q17_2)[na.exclude(mydata$s6q17_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q17_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q17_2. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 40 50 56 90 100 150 200 250 300 400 500 525 600 750 776 800 860
## 5 2 1 1 1 2 1 1 1 1 4 2 1 1 1 1 1 1
## 1000 1400 2000 2200 2350 2500 3000 3720 4000 5000 5350 5500 7000 7500 7600 8180 10000 10616
## 4 2 10 1 1 2 1 1 4 10 1 1 1 1 1 1 6 1
## 11740 12000 13000 15000 18000 18660 19000 20000 21000 23000 24000 30000 40000 50000 52000 60000 81000 <NA>
## 1 1 1 6 1 1 1 2 1 1 1 5 2 2 1 1 1 2190
## [1] "Frequency table after encoding"
## s6q17_2. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 40 50 56 90 100 150
## 5 2 1 1 1 2 1
## 200 250 300 400 500 525 600
## 1 1 1 4 2 1 1
## 750 776 800 860 1000 1400 2000
## 1 1 1 1 4 2 10
## 2200 2350 2500 3000 3720 4000 5000
## 1 1 2 1 1 4 10
## 5350 5500 7000 7500 7600 8180 10000
## 1 1 1 1 1 1 6
## 10616 11740 12000 13000 15000 18000 18660
## 1 1 1 1 6 1 1
## 19000 20000 21000 23000 24000 30000 40000
## 1 2 1 1 1 5 2
## 50000 52000 60000 69974 or more <NA>
## 2 1 1 1 2190
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_2)[na.exclude(mydata$s6q19_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_2. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 4 5 6 7 8 9 10 11 12 14 15
## 19 11 8 9 4 5 1 3 5 2 6 2 1 1 6
## 16 17 18 19 20 21 25 26 27 30 32 33 34 35 39
## 1 1 4 1 15 1 2 1 1 6 1 1 1 1 1
## 40 45 46 48 49 50 53 55 60 61 69 70 74 75 80
## 4 1 1 1 1 13 1 1 2 1 1 1 1 1 2
## 90 96 97 100 120 130 135 140 150 160 180 200 220 240 250
## 2 1 1 10 1 1 1 1 4 2 1 3 1 1 1
## 252 300 320 365 400 480 500 600 630 714 720 750 800 1000 1200
## 1 6 1 1 2 1 4 2 1 1 1 1 2 1 1
## 2000 3000 3750 4000 5500 6000 7500 9000 13500 19000 45000 50000 250000 <NA>
## 1 3 1 1 1 1 1 1 1 1 1 1 1 2071
## [1] "Frequency table after encoding"
## s6q19_2. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 4 5 6
## 19 11 8 9 4 5 1
## 7 8 9 10 11 12 14
## 3 5 2 6 2 1 1
## 15 16 17 18 19 20 21
## 6 1 1 4 1 15 1
## 25 26 27 30 32 33 34
## 2 1 1 6 1 1 1
## 35 39 40 45 46 48 49
## 1 1 4 1 1 1 1
## 50 53 55 60 61 69 70
## 13 1 1 2 1 1 1
## 74 75 80 90 96 97 100
## 1 1 2 2 1 1 10
## 120 130 135 140 150 160 180
## 1 1 1 1 4 2 1
## 200 220 240 250 252 300 320
## 3 1 1 1 1 6 1
## 365 400 480 500 600 630 714
## 1 2 1 4 2 1 1
## 720 750 800 1000 1200 2000 3000
## 1 1 2 1 1 1 3
## 3750 4000 5500 6000 7500 9000 13500
## 1 1 1 1 1 1 1
## 19000 45000 49399 or more <NA>
## 1 1 2 2071
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_2)[na.exclude(mydata$s6q20_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_2. What is the total market value of the quantity harvested in the last 12 months?
## 0 5 20 25 35 40 50 60 70 80 100 135 150 200 250
## 19 1 2 1 1 2 2 2 1 2 1 1 4 1 1
## 300 350 360 400 473 480 500 600 640 700 720 750 770 800 900
## 7 2 1 8 1 1 5 1 1 3 1 2 1 4 1
## 1000 1200 1250 1350 1400 1500 1600 1680 1750 1783 1800 1856 2000 2400 2800
## 5 4 1 1 1 5 2 1 1 1 1 1 6 2 1
## 2880 3000 3120 3200 3500 3600 3720 4050 4200 4500 5000 5200 5500 5986 6000
## 1 3 1 1 1 1 1 1 1 2 3 1 2 1 7
## 6250 6330 6400 7000 7020 7290 7500 7800 8000 8280 8400 8550 9000 9600 10000
## 1 1 2 1 1 1 1 1 5 1 1 1 2 1 2
## 10800 11700 11760 11808 11880 12000 12020 12500 12750 13500 15000 15232 15980 18000 20000
## 1 1 1 1 1 4 1 1 1 1 1 1 1 1 1
## 20250 21600 23750 24000 25000 26400 26950 27258 28000 30000 33000 36000 40000 40320 42000
## 1 1 1 2 1 1 1 1 1 2 1 1 1 1 1
## 43200 45000 45540 50000 50880 52000 55000 62050 63000 70000 72000 75600 78104 80000 81250
## 1 3 1 3 1 1 1 1 1 1 1 1 1 1 1
## 130000 192800 <NA>
## 1 1 2078
## [1] "Frequency table after encoding"
## s6q20_2. What is the total market value of the quantity harvested in the last 12 months?
## 0 5 20 25 35 40 50
## 19 1 2 1 1 2 2
## 60 70 80 100 135 150 200
## 2 1 2 1 1 4 1
## 250 300 350 360 400 473 480
## 1 7 2 1 8 1 1
## 500 600 640 700 720 750 770
## 5 1 1 3 1 2 1
## 800 900 1000 1200 1250 1350 1400
## 4 1 5 4 1 1 1
## 1500 1600 1680 1750 1783 1800 1856
## 5 2 1 1 1 1 1
## 2000 2400 2800 2880 3000 3120 3200
## 6 2 1 1 3 1 1
## 3500 3600 3720 4050 4200 4500 5000
## 1 1 1 1 1 2 3
## 5200 5500 5986 6000 6250 6330 6400
## 1 2 1 7 1 1 2
## 7000 7020 7290 7500 7800 8000 8280
## 1 1 1 1 1 5 1
## 8400 8550 9000 9600 10000 10800 11700
## 1 1 2 1 2 1 1
## 11760 11808 11880 12000 12020 12500 12750
## 1 1 1 4 1 1 1
## 13500 15000 15232 15980 18000 20000 20250
## 1 1 1 1 1 1 1
## 21600 23750 24000 25000 26400 26950 27258
## 1 1 2 1 1 1 1
## 28000 30000 33000 36000 40000 40320 42000
## 1 2 1 1 1 1 1
## 43200 45000 45540 50000 50880 52000 55000
## 1 3 1 3 1 1 1
## 62050 63000 70000 72000 75600 78104 80000
## 1 1 1 1 1 1 1
## 81250 125856 or more <NA>
## 1 2 2078
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_2)[na.exclude(mydata$s6q21_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_2. What was the total revenue received from this crop harvest (sold in market trans
## 0 20 50 60 80 120 135 150 160 200 240 250 280 300 350
## 65 1 1 1 1 1 1 3 1 2 1 1 2 4 1
## 360 400 500 600 625 700 800 840 1000 1100 1200 1280 1300 1350 1400
## 2 2 6 6 1 3 5 1 5 1 4 1 1 1 1
## 1440 1500 1600 1680 1750 1783 1800 1950 2000 2600 2860 3000 3500 3600 4000
## 1 4 2 1 1 1 1 1 7 1 1 4 2 1 3
## 4200 4500 4800 5000 5986 6000 6400 6650 7000 7020 7200 7290 8000 8400 9000
## 2 1 1 5 1 6 1 1 1 1 2 1 1 1 1
## 9600 10000 11500 11700 11760 11880 12000 12500 12600 15000 15232 15400 15980 16000 20250
## 1 3 1 1 1 1 4 1 1 1 1 1 1 1 1
## 23757 25000 26950 27000 27258 29700 30000 35000 36500 37140 40000 45540 50200 50400 55000
## 1 1 1 1 1 1 2 1 1 1 4 1 1 2 1
## 72000 78104 80000 130000 160000 <NA>
## 1 1 1 1 1 2068
## [1] "Frequency table after encoding"
## s6q21_2. What was the total revenue received from this crop harvest (sold in market trans
## 0 20 50 60 80 120 135
## 65 1 1 1 1 1 1
## 150 160 200 240 250 280 300
## 3 1 2 1 1 2 4
## 350 360 400 500 600 625 700
## 1 2 2 6 6 1 3
## 800 840 1000 1100 1200 1280 1300
## 5 1 5 1 4 1 1
## 1350 1400 1440 1500 1600 1680 1750
## 1 1 1 4 2 1 1
## 1783 1800 1950 2000 2600 2860 3000
## 1 1 1 7 1 1 4
## 3500 3600 4000 4200 4500 4800 5000
## 2 1 3 2 1 1 5
## 5986 6000 6400 6650 7000 7020 7200
## 1 6 1 1 1 1 2
## 7290 8000 8400 9000 9600 10000 11500
## 1 1 1 1 1 3 1
## 11700 11760 11880 12000 12500 12600 15000
## 1 1 1 4 1 1 1
## 15232 15400 15980 16000 20250 23757 25000
## 1 1 1 1 1 1 1
## 26950 27000 27258 29700 30000 35000 36500
## 1 1 1 1 2 1 1
## 37140 40000 45540 50200 50400 55000 72000
## 1 4 1 1 2 1 1
## 78104 80000 123250 or more <NA>
## 1 1 2 2068
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q17_3)[na.exclude(mydata$s6q17_3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q17_3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q17_3. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 50 100 150 200 300 390 500 600 750 776 1000 1350 1800 2000 2780 4000 5000
## 2 1 1 3 1 2 1 1 1 1 1 2 1 1 1 1 2 2
## 6000 30000 <NA>
## 1 1 2269
## [1] "Frequency table after encoding"
## s6q17_3. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 50 100 150 200 300 390
## 2 1 1 3 1 2 1
## 500 600 750 776 1000 1350 1800
## 1 1 1 1 2 1 1
## 2000 2780 4000 5000 6000 26880 or more <NA>
## 1 1 2 2 1 1 2269
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_3)[na.exclude(mydata$s6q19_3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_3. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 4 5 6 7 10 11 15 17 20 30 35
## 15 4 2 3 4 5 1 2 5 1 3 1 3 6 1
## 40 48 50 70 72 74 80 90 100 115 160 180 200 300 480
## 4 2 4 1 1 1 1 1 4 1 1 1 5 5 1
## 500 540 900 1000 1500 2000 2400 4710 6000 9000 105000 <NA>
## 1 1 1 3 1 1 1 1 1 1 1 2194
## [1] "Frequency table after encoding"
## s6q19_3. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 4 5 6
## 15 4 2 3 4 5 1
## 7 10 11 15 17 20 30
## 2 5 1 3 1 3 6
## 35 40 48 50 70 72 74
## 1 4 2 4 1 1 1
## 80 90 100 115 160 180 200
## 1 1 4 1 1 1 5
## 300 480 500 540 900 1000 1500
## 5 1 1 1 1 3 1
## 2000 2400 4710 6000 9000 56520 or more <NA>
## 1 1 1 1 1 1 2194
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_3)[na.exclude(mydata$s6q20_3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_3. What is the total market value of the quantity harvested in the last 12 months?
## 0 5 15 25 30 50 54 60 100 120 125 200 240 300 400
## 17 1 1 1 1 1 1 1 1 1 1 3 2 3 5
## 450 500 550 560 700 750 800 900 1000 1080 1150 1190 1200 1440 1500
## 2 2 2 1 2 1 2 2 5 1 1 1 2 1 1
## 1700 1800 2000 2200 2400 2500 3000 3500 4000 4070 4500 5000 5250 6000 8400
## 1 3 4 1 1 2 3 2 2 1 1 3 1 1 1
## 8800 9000 10000 12000 15200 24000 28800 47100 58500 105000 <NA>
## 1 1 2 1 1 1 1 1 1 1 2192
## [1] "Frequency table after encoding"
## s6q20_3. What is the total market value of the quantity harvested in the last 12 months?
## 0 5 15 25 30 50 54
## 17 1 1 1 1 1 1
## 60 100 120 125 200 240 300
## 1 1 1 1 3 2 3
## 400 450 500 550 560 700 750
## 5 2 2 2 1 2 1
## 800 900 1000 1080 1150 1190 1200
## 2 2 5 1 1 1 2
## 1440 1500 1700 1800 2000 2200 2400
## 1 1 1 3 4 1 1
## 2500 3000 3500 4000 4070 4500 5000
## 2 3 2 2 1 1 3
## 5250 6000 8400 8800 9000 10000 12000
## 1 1 1 1 1 2 1
## 15200 24000 28800 47100 58500 81052 or more <NA>
## 1 1 1 1 1 1 2192
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_3)[na.exclude(mydata$s6q21_3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_3. What was the total revenue received from this crop harvest (sold in market trans
## 0 30 50 100 150 200 240 250 300 400 432 440 450 500 600
## 33 1 1 2 1 4 1 1 2 3 1 1 3 2 2
## 700 720 800 840 900 1000 1200 1500 1600 1750 1800 2000 2400 2500 3000
## 2 1 2 1 1 5 2 2 2 1 1 3 1 1 2
## 3500 4000 4070 4200 4500 5000 5200 5250 9600 10000 11400 12000 24000 47100 58500
## 1 1 1 1 2 2 1 1 1 2 1 1 1 1 1
## 110000 <NA>
## 1 2192
## [1] "Frequency table after encoding"
## s6q21_3. What was the total revenue received from this crop harvest (sold in market trans
## 0 30 50 100 150 200 240
## 33 1 1 2 1 4 1
## 250 300 400 432 440 450 500
## 1 2 3 1 1 3 2
## 600 700 720 800 840 900 1000
## 2 2 1 2 1 1 5
## 1200 1500 1600 1750 1800 2000 2400
## 2 2 2 1 1 3 1
## 2500 3000 3500 4000 4070 4200 4500
## 1 2 1 1 1 1 2
## 5000 5200 5250 9600 10000 11400 12000
## 2 1 1 1 2 1 1
## 24000 47100 58500 83477 or more <NA>
## 1 1 1 1 2192
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q17_4)[na.exclude(mydata$s6q17_4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q17_4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q17_4. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 50 150 200 250 300 400 730 750 776 1200 1350 2000 2500 3000 4000 5000 <NA>
## 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 2279
## [1] "Frequency table after encoding"
## s6q17_4. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 50 150 200 250 300 400 730 750
## 1 1 2 1 1 1 1 1
## 776 1200 1350 2000 2500 3000 4000 4920 or more
## 1 1 1 1 1 1 1 1
## <NA>
## 2279
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_4)[na.exclude(mydata$s6q19_4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_4. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 5 6 9 10 17 18 20 25 30 40 48
## 8 4 1 1 4 1 1 3 1 1 4 1 3 1 1
## 50 90 96 100 143 150 160 180 250 300 400 412 600 720 900
## 4 1 1 1 1 2 1 1 3 2 1 1 1 1 1
## 1000 2000 250000 <NA>
## 2 1 1 2235
## [1] "Frequency table after encoding"
## s6q19_4. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 2 3 5 6 9
## 8 4 1 1 4 1 1
## 10 17 18 20 25 30 40
## 3 1 1 4 1 3 1
## 48 50 90 96 100 143 150
## 1 4 1 1 1 1 2
## 160 180 250 300 400 412 600
## 1 1 3 2 1 1 1
## 720 900 1000 2000 175600 or more <NA>
## 1 1 2 1 1 2235
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_4)[na.exclude(mydata$s6q20_4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_4. What is the total market value of the quantity harvested in the last 12 months?
## 0 40 50 75 81 120 150 240 250 300 350 400 500 600 750 900 960 1000
## 7 1 2 1 1 1 2 1 1 3 1 2 2 1 1 1 1 3
## 1152 1200 1500 1800 2000 2145 2400 2500 3000 3500 3840 4200 5000 6000 6250 7000 8000 8500
## 1 1 2 1 1 1 2 1 1 1 1 1 2 1 1 1 1 1
## 10800 12000 18600 21600 <NA>
## 1 1 1 1 2239
## [1] "Frequency table after encoding"
## s6q20_4. What is the total market value of the quantity harvested in the last 12 months?
## 0 40 50 75 81 120 150
## 7 1 2 1 1 1 2
## 240 250 300 350 400 500 600
## 1 1 3 1 2 2 1
## 750 900 960 1000 1152 1200 1500
## 1 1 1 3 1 1 2
## 1800 2000 2145 2400 2500 3000 3500
## 1 1 1 2 1 1 1
## 3840 4200 5000 6000 6250 7000 8000
## 1 1 2 1 1 1 1
## 8500 10800 12000 18600 20759 or more <NA>
## 1 1 1 1 1 2239
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_4)[na.exclude(mydata$s6q21_4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_4. What was the total revenue received from this crop harvest (sold in market trans
## 0 50 75 120 150 200 240 250 300 400 500 540 1000 1050 1500 1600 1800 2160
## 16 2 1 1 1 1 1 1 4 2 2 1 4 1 2 1 1 1
## 2400 2500 2760 2880 3000 3500 3750 4000 6000 7000 7200 8500 8982 11500 <NA>
## 2 1 1 1 1 1 1 1 1 1 1 1 1 1 2238
## [1] "Frequency table after encoding"
## s6q21_4. What was the total revenue received from this crop harvest (sold in market trans
## 0 50 75 120 150 200 240
## 16 2 1 1 1 1 1
## 250 300 400 500 540 1000 1050
## 1 4 2 2 1 4 1
## 1500 1600 1800 2160 2400 2500 2760
## 2 1 1 1 2 1 1
## 2880 3000 3500 3750 4000 6000 7000
## 1 1 1 1 1 1 1
## 7200 8500 8982 10782 or more <NA>
## 1 1 1 1 2238
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q17_5)[na.exclude(mydata$s6q17_5)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q17_5", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q17_5. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 50 140 150 200 750 776 900 2000 <NA>
## 1 1 2 1 2 1 1 1 2286
## [1] "Frequency table after encoding"
## s6q17_5. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 50 140 150 200 750 776 900 1950 or more
## 1 1 2 1 2 1 1 1
## <NA>
## 2286
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_5)[na.exclude(mydata$s6q19_5)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_5", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_5. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 4 5 6 10 20 30 33 35 40 50 60 100 450 500 1200 1500 <NA>
## 8 2 1 3 2 3 2 1 1 1 2 1 1 1 1 1 1 1 2263
## [1] "Frequency table after encoding"
## s6q19_5. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 1 4 5 6 10 20 30
## 8 2 1 3 2 3 2 1
## 33 35 40 50 60 100 450 500
## 1 1 2 1 1 1 1 1
## 1200 1452 or more <NA>
## 1 1 2263
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_5)[na.exclude(mydata$s6q20_5)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_5", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_5. What is the total market value of the quantity harvested in the last 12 months?
## 0 10 60 75 90 100 200 250 400 500 600 700 750 900 1200 1320 1400 1500
## 8 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2
## 1750 1800 2500 5000 32400 <NA>
## 1 2 1 1 1 2264
## [1] "Frequency table after encoding"
## s6q20_5. What is the total market value of the quantity harvested in the last 12 months?
## 0 10 60 75 90 100 200
## 8 1 1 1 1 1 1
## 250 400 500 600 700 750 900
## 1 1 1 1 1 1 1
## 1200 1320 1400 1500 1750 1800 2500
## 1 1 1 2 1 2 1
## 5000 28152 or more <NA>
## 1 1 2264
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_5)[na.exclude(mydata$s6q21_5)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_5", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_5. What was the total revenue received from this crop harvest (sold in market trans
## 0 60 75 100 240 400 450 500 700 750 1000 1200 1260 1300 1500 1600 5000 32400
## 12 1 1 1 1 2 1 1 2 2 1 1 1 1 1 1 1 1
## <NA>
## 2264
## [1] "Frequency table after encoding"
## s6q21_5. What was the total revenue received from this crop harvest (sold in market trans
## 0 60 75 100 240 400 450
## 12 1 1 1 1 2 1
## 500 700 750 1000 1200 1260 1300
## 1 2 2 1 1 1 1
## 1500 1600 5000 28152 or more <NA>
## 1 1 1 1 2264
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q17_6)[na.exclude(mydata$s6q17_6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q17_6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q17_6. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 50 776 2000 <NA>
## 1 1 1 1 2292
## [1] "Frequency table after encoding"
## s6q17_6. How much was this start-up capital? Magkano ang panimulang kapital na ito?
## 0 50 776 1981 or more <NA>
## 1 1 1 1 2292
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_6)[na.exclude(mydata$s6q19_6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_6. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 2 7 15 30 40 100 500 <NA>
## 2 1 1 1 1 2 1 1 2286
## [1] "Frequency table after encoding"
## s6q19_6. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 2 7 15 30 40 100 482 or more <NA>
## 2 1 1 1 1 2 1 1 2286
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_6)[na.exclude(mydata$s6q20_6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_6. What is the total market value of the quantity harvested in the last 12 months?
## 0 30 360 400 1600 4900 5000 25000 <NA>
## 2 1 1 1 1 1 1 1 2287
## [1] "Frequency table after encoding"
## s6q20_6. What is the total market value of the quantity harvested in the last 12 months?
## 0 30 360 400 1600 4900 5000
## 2 1 1 1 1 1 1
## 24200 or more <NA>
## 1 2287
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_6)[na.exclude(mydata$s6q21_6)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_6", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_6. What was the total revenue received from this crop harvest (sold in market trans
## 0 360 400 1600 3000 5000 13250 25000 <NA>
## 2 1 1 1 1 1 1 1 2287
## [1] "Frequency table after encoding"
## s6q21_6. What was the total revenue received from this crop harvest (sold in market trans
## 0 360 400 1600 3000 5000 13250
## 2 1 1 1 1 1 1
## 24530 or more <NA>
## 1 2287
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q19_7)[na.exclude(mydata$s6q19_7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q19_7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q19_7. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 400 <NA>
## 1 1 2294
## [1] "Frequency table after encoding"
## s6q19_7. What is the quantity of the crop harvested in the last 12 months? Please give th
## 0 398 or more <NA>
## 1 1 2294
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q20_7)[na.exclude(mydata$s6q20_7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q20_7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q20_7. What is the total market value of the quantity harvested in the last 12 months?
## 0 400 <NA>
## 1 1 2294
## [1] "Frequency table after encoding"
## s6q20_7. What is the total market value of the quantity harvested in the last 12 months?
## 0 398 or more <NA>
## 1 1 2294
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q21_7)[na.exclude(mydata$s6q21_7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q21_7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q21_7. What was the total revenue received from this crop harvest (sold in market trans
## 0 400 <NA>
## 1 1 2294
## [1] "Frequency table after encoding"
## s6q21_7. What was the total revenue received from this crop harvest (sold in market trans
## 0 398 or more <NA>
## 1 1 2294
mydata <- top_recode (variable="s6q22", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q22. In the last 12 months, how much in total did your household spend on Seeds ? Sa
## 0 6 25 40 75 100 150 175 200 224 250 300 360 400 420
## 240 1 1 3 1 3 2 1 2 1 3 5 1 3 2
## 500 528 576 590 600 650 675 800 880 900 910 1000 1030 1050 1100
## 7 1 1 1 2 1 1 2 1 3 1 12 1 2 1
## 1200 1300 1400 1500 1550 1560 1600 1650 2000 2100 2400 2500 2550 2580 2600
## 8 4 2 7 1 1 3 1 15 2 3 4 1 1 1
## 2660 2700 2800 3000 3100 3300 3500 3600 3750 3900 4000 4050 4100 4500 4770
## 1 2 2 14 1 2 3 2 1 1 5 1 1 3 1
## 4800 4900 5000 5010 5200 5300 5500 5700 6000 6600 7000 7200 7500 7600 7700
## 4 1 17 1 1 2 2 1 7 1 4 2 2 1 1
## 8000 8300 8800 9000 9400 10000 11000 11500 12000 13500 13980 14000 15000 15300 15600
## 6 1 2 1 1 15 5 1 5 1 1 1 4 1 1
## 16000 16500 17500 17850 20000 21000 21400 21600 22600 25000 29400 29800 30000 33000 35000
## 2 1 2 1 3 1 1 1 1 2 1 1 5 1 2
## 45000 60000 60600 66000 76725 78500 208000 <NA>
## 1 1 1 1 1 1 1 1771
## [1] "Frequency table after encoding"
## s6q22. In the last 12 months, how much in total did your household spend on Seeds ? Sa
## 0 6 25 40 75 100 150 175 200
## 240 1 1 3 1 3 2 1 2
## 224 250 300 360 398 or more <NA>
## 1 3 5 1 261 1771
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q24)[na.exclude(mydata$s6q24)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q24", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q24. In the last 12 months, how much in total did your household spend on Fertilizers
## 0 47 50 90 93 100 120 140 150 160 180 200 250 280 300 325 330 350
## 194 1 1 1 1 1 2 1 2 1 1 2 1 1 5 2 1 1
## 432 435 450 500 600 620 700 730 800 890 900 1000 1040 1065 1085 1100 1150 1180
## 1 1 2 11 5 1 1 1 1 1 1 18 1 1 1 1 1 1
## 1200 1230 1350 1360 1400 1500 1530 1600 1700 1770 1780 1800 1900 1990 2000 2050 2150 2200
## 6 1 1 1 2 8 1 1 2 1 1 3 2 1 14 3 1 6
## 2220 2250 2270 2300 2310 2330 2340 2380 2400 2460 2500 2600 2700 2800 2840 2900 3000 3016
## 1 1 1 1 1 1 1 1 1 1 7 2 1 2 1 1 13 1
## 3150 3200 3280 3300 3400 3500 3620 3638 3680 3700 3800 4000 4100 4200 4500 4800 5000 5050
## 1 1 1 1 1 4 1 1 1 1 1 9 1 3 2 1 10 1
## 5400 5418 5500 5600 5760 5880 6000 6250 6300 6500 6506 6600 6720 6790 7000 7100 7150 7170
## 1 1 1 1 1 1 8 1 1 1 1 2 1 1 8 1 1 1
## 7200 7700 8000 8400 8800 9400 9500 9600 10000 10650 11000 11350 11900 12000 12360 12600 12800 13000
## 1 1 8 3 2 1 1 1 16 1 1 1 1 9 1 1 1 1
## 14000 14500 14730 15000 15200 15600 16000 17000 17100 18000 18600 20000 20140 21000 21200 22200 23350 23800
## 3 1 1 1 1 1 1 1 1 3 1 4 1 2 1 1 1 1
## 24200 25000 25600 29400 30000 36000 50000 55860 60000 66000 76000 <NA>
## 1 1 1 1 2 1 1 1 1 1 1 1771
## [1] "Frequency table after encoding"
## s6q24. In the last 12 months, how much in total did your household spend on Fertilizers
## 0 47 50 90 93 100 120
## 194 1 1 1 1 1 2
## 140 150 160 180 200 250 280
## 1 2 1 1 2 1 1
## 300 325 330 350 432 435 450
## 5 2 1 1 1 1 2
## 500 600 620 700 730 800 890
## 11 5 1 1 1 1 1
## 900 1000 1040 1065 1085 1100 1150
## 1 18 1 1 1 1 1
## 1180 1200 1230 1350 1360 1400 1500
## 1 6 1 1 1 2 8
## 1530 1600 1700 1770 1780 1800 1900
## 1 1 2 1 1 3 2
## 1990 2000 2050 2150 2200 2220 2250
## 1 14 3 1 6 1 1
## 2270 2300 2310 2330 2340 2380 2400
## 1 1 1 1 1 1 1
## 2460 2500 2600 2700 2800 2840 2900
## 1 7 2 1 2 1 1
## 3000 3016 3150 3200 3280 3300 3400
## 13 1 1 1 1 1 1
## 3500 3620 3638 3680 3700 3800 4000
## 4 1 1 1 1 1 9
## 4100 4200 4500 4800 5000 5050 5400
## 1 3 2 1 10 1 1
## 5418 5500 5600 5760 5880 6000 6250
## 1 1 1 1 1 8 1
## 6300 6500 6506 6600 6720 6790 7000
## 1 1 1 2 1 1 8
## 7100 7150 7170 7200 7700 8000 8400
## 1 1 1 1 1 8 3
## 8800 9400 9500 9600 10000 10650 11000
## 2 1 1 1 16 1 1
## 11350 11900 12000 12360 12600 12800 13000
## 1 1 9 1 1 1 1
## 14000 14500 14730 15000 15200 15600 16000
## 3 1 1 1 1 1 1
## 17000 17100 18000 18600 20000 20140 21000
## 1 1 3 1 4 1 2
## 21200 22200 23350 23800 24200 25000 25600
## 1 1 1 1 1 1 1
## 29400 30000 36000 50000 55860 57433 or more <NA>
## 1 2 1 1 1 3 1771
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q26)[na.exclude(mydata$s6q26)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q26", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q26. In the last 12 months, how much in total did your household spend on Hire machin
## 0 25 130 150 160 220 300 308 350 400 500 600 700 715 800 805 880 900
## 340 1 1 1 1 1 3 1 1 2 7 9 3 1 5 1 1 2
## 1000 1100 1200 1300 1400 1450 1500 1600 1800 1920 2000 2178 2200 2250 2380 2400 2500 2600
## 13 1 8 3 4 1 12 5 2 1 21 1 1 1 1 5 5 1
## 2700 2736 2800 2870 2975 3000 3200 3250 3420 3600 3700 4000 4200 4500 5000 5100 5250 5600
## 1 1 3 1 1 6 1 1 1 2 1 7 2 4 5 1 1 1
## 5700 6000 7000 8000 8700 8960 9000 9500 9800 10000 10735 16000 16800 19000 30000 <NA>
## 1 3 3 1 1 1 2 1 1 1 1 1 1 1 1 1769
## [1] "Frequency table after encoding"
## s6q26. In the last 12 months, how much in total did your household spend on Hire machin
## 0 25 130 150 160 220 300
## 340 1 1 1 1 1 3
## 308 350 400 500 600 700 715
## 1 1 2 7 9 3 1
## 800 805 880 900 1000 1100 1200
## 5 1 1 2 13 1 8
## 1300 1400 1450 1500 1600 1800 1920
## 3 4 1 12 5 2 1
## 2000 2178 2200 2250 2380 2400 2500
## 21 1 1 1 1 5 5
## 2600 2700 2736 2800 2870 2975 3000
## 1 1 1 3 1 1 6
## 3200 3250 3420 3600 3700 4000 4200
## 1 1 1 2 1 7 2
## 4500 5000 5100 5250 5600 5700 6000
## 4 5 1 1 1 1 3
## 7000 8000 8700 8960 9000 9500 9800
## 3 1 1 1 2 1 1
## 10000 10735 16000 16296 or more <NA>
## 1 1 1 3 1769
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q28)[na.exclude(mydata$s6q28)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q28", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q28. In the last 12 months, how much in total did your household spend on Water (incl
## 0 15 20 96 200 216 260 300 400 480 500 600 700 800 840 900 934 1000
## 451 1 1 1 1 1 1 5 1 1 11 4 1 3 1 2 1 7
## 1100 1188 1200 1500 1550 1568 1600 1800 2000 2200 2400 3000 3200 4000 4342 5000 7000 7665
## 2 1 2 1 1 1 2 1 4 1 1 4 1 3 1 2 1 1
## 8000 9000 10000 12000 <NA>
## 2 1 4 1 1764
## [1] "Frequency table after encoding"
## s6q28. In the last 12 months, how much in total did your household spend on Water (incl
## 0 15 20 96 200 216 260
## 451 1 1 1 1 1 1
## 300 400 480 500 600 700 800
## 5 1 1 11 4 1 3
## 840 900 934 1000 1100 1188 1200
## 1 2 1 7 2 1 2
## 1500 1550 1568 1600 1800 2000 2200
## 1 1 1 2 1 4 1
## 2400 3000 3200 4000 4342 5000 7000
## 1 4 1 3 1 2 1
## 7665 8000 9000 10000 or more <NA>
## 1 2 1 5 1764
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q30)[na.exclude(mydata$s6q30)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q30", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q30. In the last 12 months, how much in total did your household spend on Hiring Labo
## 0 1 17 300 400 450 500 600 700 800 900 1000 1150 1200 1275 1352 1360 1500
## 292 1 1 5 2 7 6 9 1 9 4 14 1 4 1 1 2 3
## 1600 1800 1900 2000 2100 2200 2400 2500 3000 3200 3400 3500 3750 3980 4000 4450 4500 4800
## 4 2 3 16 2 3 7 3 25 2 2 2 1 1 15 1 6 2
## 5000 5100 5200 5250 5460 5600 6000 6100 7000 7200 7500 7933 8000 9000 9600 10000 10500 10800
## 9 1 1 1 1 1 9 1 2 1 1 1 6 2 1 6 1 1
## 11500 11840 12000 13000 13500 14000 15000 16000 16200 20000 21900 22000 24000 35000 38400 40000 47000 <NA>
## 1 1 4 1 1 1 3 1 1 1 1 1 1 1 1 1 1 1768
## [1] "Frequency table after encoding"
## s6q30. In the last 12 months, how much in total did your household spend on Hiring Labo
## 0 1 17 300 400 450 500
## 292 1 1 5 2 7 6
## 600 700 800 900 1000 1150 1200
## 9 1 9 4 14 1 4
## 1275 1352 1360 1500 1600 1800 1900
## 1 1 2 3 4 2 3
## 2000 2100 2200 2400 2500 3000 3200
## 16 2 3 7 3 25 2
## 3400 3500 3750 3980 4000 4450 4500
## 2 2 1 1 15 1 6
## 4800 5000 5100 5200 5250 5460 5600
## 2 9 1 1 1 1 1
## 6000 6100 7000 7200 7500 7933 8000
## 9 1 2 1 1 1 6
## 9000 9600 10000 10500 10800 11500 11840
## 2 1 6 1 1 1 1
## 12000 13000 13500 14000 15000 16000 16200
## 4 1 1 1 3 1 1
## 20000 21900 22000 24000 35000 36241 or more <NA>
## 1 1 1 1 1 3 1768
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q32)[na.exclude(mydata$s6q32)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q32", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q32. In the last 12 months, how much in total did your household spend on Other expen
## 0 40 50 60 75 80 100 128 150 200 264 271 300 400 500 600 665 800
## 433 1 1 1 1 1 4 1 2 4 1 1 6 1 6 4 1 2
## 1000 1008 1120 1200 1400 1500 1680 1800 2000 2050 2500 2800 3000 3190 4000 4200 4250 4500
## 11 1 1 1 1 5 1 2 6 1 1 2 3 1 2 1 1 1
## 4856 5000 5040 6000 6720 7000 9600 10000 11100 12000 15000 16800 45500 48000 <NA>
## 1 3 1 1 1 1 1 1 1 1 1 1 1 1 1767
## [1] "Frequency table after encoding"
## s6q32. In the last 12 months, how much in total did your household spend on Other expen
## 0 40 50 60 75 80 100
## 433 1 1 1 1 1 4
## 128 150 200 264 271 300 400
## 1 2 4 1 1 6 1
## 500 600 665 800 1000 1008 1120
## 6 4 1 2 11 1 1
## 1200 1400 1500 1680 1800 2000 2050
## 1 1 5 1 2 6 1
## 2500 2800 3000 3190 4000 4200 4250
## 1 2 3 1 2 1 1
## 4500 4856 5000 5040 6000 6720 7000
## 1 1 3 1 1 1 1
## 9600 10000 11100 12000 15000 15648 or more <NA>
## 1 1 1 1 1 3 1767
percentile_99.5 <- floor(quantile(na.exclude(mydata$s6q35)[na.exclude(mydata$s6q35)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s6q35", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s6q35. What are your household's total profits from farming in the last 12 months? Ma
## 0 100 140 150 200 270 300 350 360 400 417 475 480 500 585
## 146 1 1 3 2 1 1 1 1 1 1 1 1 2 1
## 600 636 640 650 700 710 750 800 840 890 945 1000 1111 1475 1500
## 1 1 1 1 1 1 1 1 1 1 1 9 1 1 4
## 1530 1600 1700 1720 1750 1760 1800 1960 2000 2100 2200 2250 2340 2400 2415
## 1 1 1 1 1 1 5 1 8 1 1 1 1 2 1
## 2500 2528 2560 2590 2640 2784 2900 2965 2990 3000 3100 3104 3120 3150 3350
## 2 1 1 1 1 1 2 1 2 6 1 1 2 1 1
## 3395 3400 3500 3680 3700 3750 4000 4080 4186 4300 4305 4500 4700 4750 4760
## 1 1 2 1 1 1 8 1 1 1 1 1 1 1 1
## 5000 5103 5500 5600 5626 5680 6000 6100 6464 6500 6550 6590 6600 6760 6800
## 17 1 1 1 1 1 10 1 1 1 1 1 1 1 1
## 6930 6978 7000 7050 7060 7185 7200 7500 7560 7570 7650 7866 7971 8000 8150
## 1 1 3 1 1 1 1 2 1 1 1 1 1 6 1
## 8160 8200 8208 8500 8620 8650 8740 8760 9000 9180 9288 9500 9700 9750 10000
## 1 1 1 2 1 1 1 1 3 1 1 1 1 1 11
## 10600 10640 10920 11030 11657 11905 11968 12000 12350 12550 12630 12680 12900 13500 13680
## 1 1 1 1 1 1 1 6 1 1 1 1 1 1 1
## 13704 13720 14300 14552 14776 14900 15000 15520 16000 16082 16300 16800 17250 17984 18000
## 1 1 1 1 1 1 4 1 2 1 1 1 1 1 3
## 18800 18950 19000 19200 19300 19800 19940 20000 20225 21000 21400 21600 22000 22200 22350
## 1 1 3 1 1 2 1 8 1 4 1 1 1 1 1
## 22500 22660 22890 23000 23475 23700 24000 24500 25000 25500 26100 26400 27184 28500 28840
## 2 1 1 1 1 1 1 1 3 1 1 1 1 1 1
## 29000 29124 29800 30000 31200 31280 31500 32000 32200 32730 33000 33600 34000 35000 35360
## 1 1 2 7 1 1 1 1 1 1 1 1 1 1 1
## 35900 36008 36069 37400 39304 40000 40400 40500 44352 48130 55000 55800 59610 59620 60000
## 1 1 1 1 1 4 1 1 1 1 1 1 1 1 3
## 63000 68000 76500 76568 85640 96000 105000 108000 148000 190000 359100 448280 <NA>
## 1 1 1 1 1 1 1 1 1 1 1 1 1800
## [1] "Frequency table after encoding"
## s6q35. What are your household's total profits from farming in the last 12 months? Ma
## 0 100 140 150 200 270 300
## 146 1 1 3 2 1 1
## 350 360 400 417 475 480 500
## 1 1 1 1 1 1 2
## 585 600 636 640 650 700 710
## 1 1 1 1 1 1 1
## 750 800 840 890 945 1000 1111
## 1 1 1 1 1 9 1
## 1475 1500 1530 1600 1700 1720 1750
## 1 4 1 1 1 1 1
## 1760 1800 1960 2000 2100 2200 2250
## 1 5 1 8 1 1 1
## 2340 2400 2415 2500 2528 2560 2590
## 1 2 1 2 1 1 1
## 2640 2784 2900 2965 2990 3000 3100
## 1 1 2 1 2 6 1
## 3104 3120 3150 3350 3395 3400 3500
## 1 2 1 1 1 1 2
## 3680 3700 3750 4000 4080 4186 4300
## 1 1 1 8 1 1 1
## 4305 4500 4700 4750 4760 5000 5103
## 1 1 1 1 1 17 1
## 5500 5600 5626 5680 6000 6100 6464
## 1 1 1 1 10 1 1
## 6500 6550 6590 6600 6760 6800 6930
## 1 1 1 1 1 1 1
## 6978 7000 7050 7060 7185 7200 7500
## 1 3 1 1 1 1 2
## 7560 7570 7650 7866 7971 8000 8150
## 1 1 1 1 1 6 1
## 8160 8200 8208 8500 8620 8650 8740
## 1 1 1 2 1 1 1
## 8760 9000 9180 9288 9500 9700 9750
## 1 3 1 1 1 1 1
## 10000 10600 10640 10920 11030 11657 11905
## 11 1 1 1 1 1 1
## 11968 12000 12350 12550 12630 12680 12900
## 1 6 1 1 1 1 1
## 13500 13680 13704 13720 14300 14552 14776
## 1 1 1 1 1 1 1
## 14900 15000 15520 16000 16082 16300 16800
## 1 4 1 2 1 1 1
## 17250 17984 18000 18800 18950 19000 19200
## 1 1 3 1 1 3 1
## 19300 19800 19940 20000 20225 21000 21400
## 1 2 1 8 1 4 1
## 21600 22000 22200 22350 22500 22660 22890
## 1 1 1 1 2 1 1
## 23000 23475 23700 24000 24500 25000 25500
## 1 1 1 1 1 3 1
## 26100 26400 27184 28500 28840 29000 29124
## 1 1 1 1 1 1 1
## 29800 30000 31200 31280 31500 32000 32200
## 2 7 1 1 1 1 1
## 32730 33000 33600 34000 35000 35360 35900
## 1 1 1 1 1 1 1
## 36008 36069 37400 39304 40000 40400 40500
## 1 1 1 1 4 1 1
## 44352 48130 55000 55800 59610 59620 60000
## 1 1 1 1 1 1 3
## 63000 68000 76500 76568 85640 96000 105000
## 1 1 1 1 1 1 1
## 108000 148000 170049 or more <NA>
## 1 1 3 1800
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("s6q1",
"s6q2unit",
"s6q2a",
"s6q3",
"s6q4",
"s6q5",
"s6q6",
"s6q8",
"s6q10",
"s6qn16",
"s6q12",
"s6q13_1",
"s6q15_1",
"s6q16_1",
"s6q18_1",
"s6q13_2",
"s6q15_2",
"s6q16_2",
"s6q18_2",
"s6q13_3",
"s6q15_3",
"s6q16_3",
"s6q18_3",
"s6q13_4",
"s6q15_4",
"s6q16_4",
"s6q18_4",
"s6q13_5",
"s6q15_5",
"s6q16_5",
"s6q18_5",
"s6q13_6",
"s6q15_6",
"s6q16_6",
"s6q18_6",
"s6q13_7",
"s6q15_7",
"s6q18_7",
"s6q13_8",
"s6q15_8",
"s6q16_8",
"s6q18_8",
"s6q13_9",
"s6q15_9",
"s6q16_9",
"s6q18_9",
"s6q13_10",
"s6q15_10",
"s6q16_10",
"s6q18_10",
"s6q13_11",
"s6q15_11",
"s6q18_11",
"s6q15_12",
"s6q18_12",
"s6q13_13",
"s6q15_13",
"s6q16_13",
"s6q18_13",
"s6q13_14",
"s6q15_14",
"s6q16_14",
"s6q18_14",
"s6q13_15",
"s6q15_15",
"s6q16_15",
"s6q18_15",
"s6q13_16",
"s6q15_16",
"s6q16_16",
"s6q18_16",
"s6q13_17",
"s6q15_17",
"s6q16_17",
"s6q18_17",
"s6q15_18",
"s6q18_18",
"s6q15_19",
"s6q16_19",
"s6q18_19",
"s6q15_20",
"s6q16_20",
"s6q18_20",
"s6q15_21",
"s6q16_21",
"s6q18_21",
"s6q13_22",
"s6q15_22",
"s6q18_22",
"s6q15_23",
"s6q16_23",
"s6q18_23")
capture_tables (indirect_PII)
# Recode those with very specific values.
break_units <- c(-999,1,2,3)
labels_units <- c("No Response"=1,
"Hectares" = 2,
"Square Meters" = 3,
"Other"=4)
mydata <- ordinal_recode (variable="s6q2unit", break_points=break_units, missing=999999, value_labels=labels_units)
## [1] "Frequency table before encoding"
## s6q2unit. What unit is the land measured in? Anong yunit sinukat ang lupa?
## Hectares Square Meters Tupong <NA>
## 54 332 2 1908
## recoded
## [-999,1) [1,2) [2,3) [3,1e+06)
## 1 0 54 0 0
## 2 0 0 332 0
## 3 0 0 0 2
## [1] "Frequency table after encoding"
## s6q2unit. What unit is the land measured in? Anong yunit sinukat ang lupa?
## Hectares Square Meters Other <NA>
## 54 332 2 1908
## [1] "Inspect value labels and relabel as necessary"
## No Response Hectares Square Meters Other
## 1 2 3 4mydata <- ordinal_recode (variable="s6q4", break_points=break_units, missing=999999, value_labels=labels_units)
## [1] "Frequency table before encoding"
## s6q4. What unit is the land measured in? Anong yunit sinukat ang lupa?
## Hectares Square Meters Tupong <NA>
## 91 90 7 2108
## recoded
## [-999,1) [1,2) [2,3) [3,1e+06)
## 1 0 91 0 0
## 2 0 0 90 0
## 3 0 0 0 7
## [1] "Frequency table after encoding"
## s6q4. What unit is the land measured in? Anong yunit sinukat ang lupa?
## Hectares Square Meters Other <NA>
## 91 90 7 2108
## [1] "Inspect value labels and relabel as necessary"
## No Response Hectares Square Meters Other
## 1 2 3 4break_owner <- c(-999,-888,1,2,3)
labels_owner <- c("No Response"=1,
"Other (specify)" = 2,
"Husband or husband's family" = 3,
"Wife or wife's family"=4,
"Other"=5)
mydata <- ordinal_recode (variable="s6q5", break_points=break_owner, missing=999999, value_labels=labels_owner)
## [1] "Frequency table before encoding"
## s6q5. Who owns this land? Sino ang may-ari ng lupang ito?
## Husband or husband's family Wife or wife's family Shared ownership between 1 and 2
## 111 40 29
## <NA>
## 2116
## recoded
## [-999,-888) [-888,1) [1,2) [2,3) [3,1e+06)
## 1 0 0 111 0 0
## 2 0 0 0 40 0
## 3 0 0 0 0 29
## [1] "Frequency table after encoding"
## s6q5. Who owns this land? Sino ang may-ari ng lupang ito?
## Husband or husband's family Wife or wife's family Other
## 111 40 29
## <NA>
## 2116
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Husband or husband's family
## 1 2 3
## Wife or wife's family Other
## 4 5break_crop <- c(-999,-888,1,2,3,4)
labels_crop <- c("No Response"=1,
"Other (specify)" = 2,
"Rice" = 3,
"Corn"=4,
"Coconut"=5,
"Other"=6)
mydata <- ordinal_recode (variable="s6q13_1", break_points=break_crop, missing=999999, value_labels=labels_crop)
## [1] "Frequency table before encoding"
## s6q13_1. What crop did your household cultivate in the last 12 months? Anong panahim an
## Rice Corn Coconut Abaca Baguio beans Sweet potato
## 203 113 44 10 3 12
## Cassava Water spinach Coffee Jackfruit Ginger Mango (Carabao)
## 35 1 1 2 3 2
## Mango (Indian) Peanut Okra Watermelon Pepper Papaya
## 1 2 1 1 1 1
## Pineapple Rambutan Banana Onion Chili String beans
## 3 1 31 1 1 7
## Tobacco Eggplant Sugarcane <NA>
## 2 5 14 1795
## recoded
## [-999,-888) [-888,1) [1,2) [2,3) [3,4) [4,1e+06)
## 1 0 0 203 0 0 0
## 2 0 0 0 113 0 0
## 3 0 0 0 0 44 0
## 4 0 0 0 0 0 10
## 5 0 0 0 0 0 3
## 11 0 0 0 0 0 12
## 12 0 0 0 0 0 35
## 13 0 0 0 0 0 1
## 14 0 0 0 0 0 1
## 15 0 0 0 0 0 2
## 17 0 0 0 0 0 3
## 18 0 0 0 0 0 2
## 19 0 0 0 0 0 1
## 21 0 0 0 0 0 2
## 22 0 0 0 0 0 1
## 23 0 0 0 0 0 1
## 24 0 0 0 0 0 1
## 25 0 0 0 0 0 1
## 26 0 0 0 0 0 3
## 28 0 0 0 0 0 1
## 30 0 0 0 0 0 31
## 31 0 0 0 0 0 1
## 32 0 0 0 0 0 1
## 34 0 0 0 0 0 7
## 35 0 0 0 0 0 2
## 36 0 0 0 0 0 5
## 37 0 0 0 0 0 14
## [1] "Frequency table after encoding"
## s6q13_1. What crop did your household cultivate in the last 12 months? Anong panahim an
## Rice Corn Coconut Other <NA>
## 203 113 44 141 1795
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Rice Corn Coconut Other
## 1 2 3 4 5 6break_crop <- c(-999,-888,1,2,3)
labels_crop <- c("No Response"=1,
"Other (specify)" = 2,
"Rice" = 3,
"Corn"=4,
"Other"=5)
mydata <- ordinal_recode (variable="s6q13_2", break_points=break_crop, missing=999999, value_labels=labels_crop)
## [1] "Frequency table before encoding"
## s6q13_2. What crop did your household cultivate in the last 12 months? Anong panahim an
## Rice Corn Coconut Abaca Baguio beans Calamansi
## 24 38 16 10 2 1
## Cacao Tomato Sweet potato Cassava Lanzones Ginger
## 1 1 22 26 1 3
## Mango (Carabao) Mango (Indian) Peanut Watermelon Pepper Papaya
## 2 1 5 3 1 1
## Pineapple Banana Chili String beans Eggplant Sugarcane
## 2 20 2 7 5 1
## Squash <NA>
## 3 2098
## recoded
## [-999,-888) [-888,1) [1,2) [2,3) [3,1e+06)
## 1 0 0 24 0 0
## 2 0 0 0 38 0
## 3 0 0 0 0 16
## 4 0 0 0 0 10
## 5 0 0 0 0 2
## 7 0 0 0 0 1
## 8 0 0 0 0 1
## 10 0 0 0 0 1
## 11 0 0 0 0 22
## 12 0 0 0 0 26
## 16 0 0 0 0 1
## 17 0 0 0 0 3
## 18 0 0 0 0 2
## 19 0 0 0 0 1
## 21 0 0 0 0 5
## 23 0 0 0 0 3
## 24 0 0 0 0 1
## 25 0 0 0 0 1
## 26 0 0 0 0 2
## 30 0 0 0 0 20
## 32 0 0 0 0 2
## 34 0 0 0 0 7
## 36 0 0 0 0 5
## 37 0 0 0 0 1
## 38 0 0 0 0 3
## [1] "Frequency table after encoding"
## s6q13_2. What crop did your household cultivate in the last 12 months? Anong panahim an
## Rice Corn Other <NA>
## 24 38 136 2098
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Rice Corn Other
## 1 2 3 4 5break_source <- c(-999,-888,1,2,4,5)
labels_source <- c("No Response"=1,
"Other (specify)" = 2,
"Loan from family and friends" = 3,
"Other"=4,
"Personal savings"=5,
"Other"=6)
mydata <- ordinal_recode (variable="s6q16_1", break_points=break_source, missing=999999, value_labels=labels_source)
## [1] "Frequency table before encoding"
## s6q16_1. What was the main source of start-up capital (such as money or goods) for this c
## 1. Loan from family and friends 2. Gift from family and friends
## 91 4
## 3. Sale of assets 4. Personal savings
## 7 122
## 5. Regular or micro-loan from bank 6. Loan from money-lender
## 10 28
## 7. NGO or charitable organization 8. Reinvested profit from another enterprise
## 3 11
## 9. Rosca/Self-help group/merry-go-round 10. Government Transfer Program
## 1 1
## <NA>
## 2018
## recoded
## [-999,-888) [-888,1) [1,2) [2,4) [4,5) [5,1e+06)
## 1 0 0 91 0 0 0
## 2 0 0 0 4 0 0
## 3 0 0 0 7 0 0
## 4 0 0 0 0 122 0
## 5 0 0 0 0 0 10
## 6 0 0 0 0 0 28
## 7 0 0 0 0 0 3
## 8 0 0 0 0 0 11
## 9 0 0 0 0 0 1
## 10 0 0 0 0 0 1
## [1] "Frequency table after encoding"
## s6q16_1. What was the main source of start-up capital (such as money or goods) for this c
## Loan from family and friends Other Personal savings
## 91 65 122
## <NA>
## 2018
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Loan from family and friends
## 1 2 3
## Other Personal savings Other
## 4 5 6break_source <- c(-999,-888,1,2,4,5)
labels_source <- c("No Response"=1,
"Other (specify)" = 2,
"Other" = 3,
"Other"=4,
"Personal savings"=5,
"Other"=6)
mydata <- ordinal_recode (variable="s6q16_2", break_points=break_source, missing=999999, value_labels=labels_source)
## [1] "Frequency table before encoding"
## s6q16_2. What was the main source of start-up capital (such as money or goods) for this c
## 1. Loan from family and friends 2. Gift from family and friends
## 19 2
## 3. Sale of assets 4. Personal savings
## 2 50
## 6. Loan from money-lender 8. Reinvested profit from another enterprise
## 13 9
## <NA>
## 2201
## recoded
## [-999,-888) [-888,1) [1,2) [2,4) [4,5) [5,1e+06)
## 1 0 0 19 0 0 0
## 2 0 0 0 2 0 0
## 3 0 0 0 2 0 0
## 4 0 0 0 0 50 0
## 6 0 0 0 0 0 13
## 8 0 0 0 0 0 9
## [1] "Frequency table after encoding"
## s6q16_2. What was the main source of start-up capital (such as money or goods) for this c
## Other Personal savings <NA>
## 45 50 2201
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Other Other Personal savings Other
## 1 2 3 4 5 6break_measure <- c(-999,-888,1,2,3)
labels_measure <- c("No Response"=1,
"Other (specify)" = 2,
"Kilograms" = 3,
"Sacks"=4,
"Other"=5)
mydata <- ordinal_recode (variable="s6q18_1", break_points=break_measure, missing=999999, value_labels=labels_measure)
## [1] "Frequency table before encoding"
## s6q18_1. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Sacks Pieces Can Bundles Tons Bunches <NA>
## 143 295 40 6 24 4 7 1777
## recoded
## [-999,-888) [-888,1) [1,2) [2,3) [3,1e+06)
## 1 0 0 143 0 0
## 2 0 0 0 295 0
## 3 0 0 0 0 40
## 4 0 0 0 0 6
## 7 0 0 0 0 24
## 9 0 0 0 0 4
## 15 0 0 0 0 7
## [1] "Frequency table after encoding"
## s6q18_1. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Sacks Other <NA>
## 143 295 81 1777
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Kilograms Sacks Other
## 1 2 3 4 5mydata <- ordinal_recode (variable="s6q18_2", break_points=break_measure, missing=999999, value_labels=labels_measure)
## [1] "Frequency table before encoding"
## s6q18_2. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Sacks Pieces Can Bundles Tons Bunches Bags <NA>
## 88 76 29 10 7 1 6 1 2078
## recoded
## [-999,-888) [-888,1) [1,2) [2,3) [3,1e+06)
## 1 0 0 88 0 0
## 2 0 0 0 76 0
## 3 0 0 0 0 29
## 4 0 0 0 0 10
## 7 0 0 0 0 7
## 9 0 0 0 0 1
## 15 0 0 0 0 6
## 16 0 0 0 0 1
## [1] "Frequency table after encoding"
## s6q18_2. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Sacks Other <NA>
## 88 76 54 2078
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Kilograms Sacks Other
## 1 2 3 4 5break_measure <- c(-999,-888,1,2)
labels_measure <- c("No Response"=1,
"Other (specify)" = 2,
"Kilograms" = 3,
"Other"=4)
mydata <- ordinal_recode (variable="s6q18_3", break_points=break_measure, missing=999999, value_labels=labels_measure)
## [1] "Frequency table before encoding"
## s6q18_3. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Sacks Pieces Can Bundles Bunches Bags <NA>
## 52 6 14 7 10 6 1 2200
## recoded
## [-999,-888) [-888,1) [1,2) [2,1e+06)
## 1 0 0 52 0
## 2 0 0 0 6
## 3 0 0 0 14
## 4 0 0 0 7
## 7 0 0 0 10
## 15 0 0 0 6
## 16 0 0 0 1
## [1] "Frequency table after encoding"
## s6q18_3. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Other <NA>
## 52 44 2200
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Kilograms Other
## 1 2 3 4mydata <- ordinal_recode (variable="s6q18_4", break_points=break_measure, missing=999999, value_labels=labels_measure)
## [1] "Frequency table before encoding"
## s6q18_4. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Sacks Pieces Can Bundles Bunches <NA>
## 33 5 8 2 5 3 2240
## recoded
## [-999,-888) [-888,1) [1,2) [2,1e+06)
## 1 0 0 33 0
## 2 0 0 0 5
## 3 0 0 0 8
## 4 0 0 0 2
## 7 0 0 0 5
## 15 0 0 0 3
## [1] "Frequency table after encoding"
## s6q18_4. How is crop quantity measured? Paano sinusukat ang bilang ng mga ani?
## Kilograms Other <NA>
## 33 23 2240
## [1] "Inspect value labels and relabel as necessary"
## No Response Other (specify) Kilograms Other
## 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("s6q1whynoresponse",
"s6q2unitwhynoresponse",
"s6q2whynoresponse",
"s6q2awhynoresponse",
"s6q3whynoresponse",
"s6q4whynoresponse",
"s6q4awhynoresponse",
"s6q5_other",
"s6q5whynoresponse",
"s6q6whynoresponse",
"s6q7whynoresponse",
"s6q8whynoresponse",
"s6q9whynoresponse",
"s6q9awhynoresponse",
"s6q10whynoresponse",
"s6q11whynoresponse",
"s6qn16whynoresponse",
"s6q12whynoresponse",
"s6q12countwhynoresponse",
"s6q14_1",
"s6q15awhynoresponse_1",
"s6q15whynoresponse_1",
"s6q16other_1",
"s6q16whynoresponse_1",
"s6q17whynoresponse_1",
"s6q19whynoresponse_1",
"s6q18other_1",
"s6q18whynoresponse_1",
"s6q19awhynoresponse_1",
"s6q20whynoresponse_1",
"s6q21whynoresponse_1",
"s6q14_2",
"s6q15awhynoresponse_2",
"s6q15whynoresponse_2",
"s6q16other_2",
"s6q16whynoresponse_2",
"s6q17whynoresponse_2",
"s6q19whynoresponse_2",
"s6q18other_2",
"s6q18whynoresponse_2",
"s6q19awhynoresponse_2",
"s6q20whynoresponse_2",
"s6q21whynoresponse_2",
"s6q14_3",
"s6q15awhynoresponse_3",
"s6q15whynoresponse_3",
"s6q16other_3",
"s6q16whynoresponse_3",
"s6q17whynoresponse_3",
"s6q19whynoresponse_3",
"s6q18other_3",
"s6q18whynoresponse_3",
"s6q19awhynoresponse_3",
"s6q20whynoresponse_3",
"s6q21whynoresponse_3",
"s6q14_4",
"s6q15awhynoresponse_4",
"s6q15whynoresponse_4",
"s6q16other_4",
"s6q16whynoresponse_4",
"s6q17whynoresponse_4",
"s6q19whynoresponse_4",
"s6q18other_4",
"s6q18whynoresponse_4",
"s6q19awhynoresponse_4",
"s6q20whynoresponse_4",
"s6q21whynoresponse_4",
"s6q14_5",
"s6q15awhynoresponse_5",
"s6q15whynoresponse_5",
"s6q16other_5",
"s6q16whynoresponse_5",
"s6q17whynoresponse_5",
"s6q19whynoresponse_5",
"s6q18other_5",
"s6q18whynoresponse_5",
"s6q19awhynoresponse_5",
"s6q20whynoresponse_5",
"s6q21whynoresponse_5",
"s6q14_6",
"s6q15awhynoresponse_6",
"s6q15whynoresponse_6",
"s6q16other_6",
"s6q16whynoresponse_6",
"s6q17whynoresponse_6",
"s6q19whynoresponse_6",
"s6q18other_6",
"s6q18whynoresponse_6",
"s6q19awhynoresponse_6",
"s6q20whynoresponse_6",
"s6q21whynoresponse_6",
"s6q14_7",
"s6q15awhynoresponse_7",
"s6q15whynoresponse_7",
"s6q16other_7",
"s6q16whynoresponse_7",
"s6q17whynoresponse_7",
"s6q19whynoresponse_7",
"s6q18other_7",
"s6q18whynoresponse_7",
"s6q19awhynoresponse_7",
"s6q20whynoresponse_7",
"s6q21whynoresponse_7",
"s6q14_8",
"s6q15awhynoresponse_8",
"s6q15whynoresponse_8",
"s6q16other_8",
"s6q16whynoresponse_8",
"s6q17whynoresponse_8",
"s6q19whynoresponse_8",
"s6q18other_8",
"s6q18whynoresponse_8",
"s6q19awhynoresponse_8",
"s6q20whynoresponse_8",
"s6q21whynoresponse_8",
"s6q14_9",
"s6q15awhynoresponse_9",
"s6q15whynoresponse_9",
"s6q16other_9",
"s6q16whynoresponse_9",
"s6q17whynoresponse_9",
"s6q19whynoresponse_9",
"s6q18other_9",
"s6q18whynoresponse_9",
"s6q19awhynoresponse_9",
"s6q20whynoresponse_9",
"s6q21whynoresponse_9",
"s6q14_10",
"s6q15awhynoresponse_10",
"s6q15whynoresponse_10",
"s6q16other_10",
"s6q16whynoresponse_10",
"s6q17whynoresponse_10",
"s6q19whynoresponse_10",
"s6q18other_10",
"s6q18whynoresponse_10",
"s6q19awhynoresponse_10",
"s6q20whynoresponse_10",
"s6q21whynoresponse_10",
"s6q14_11",
"s6q15awhynoresponse_11",
"s6q15whynoresponse_11",
"s6q16other_11",
"s6q16whynoresponse_11",
"s6q17whynoresponse_11",
"s6q19whynoresponse_11",
"s6q18other_11",
"s6q18whynoresponse_11",
"s6q19awhynoresponse_11",
"s6q20whynoresponse_11",
"s6q21whynoresponse_11",
"s6q14_12",
"s6q15awhynoresponse_12",
"s6q15whynoresponse_12",
"s6q16other_12",
"s6q16whynoresponse_12",
"s6q17whynoresponse_12",
"s6q19whynoresponse_12",
"s6q18other_12",
"s6q18whynoresponse_12",
"s6q19awhynoresponse_12",
"s6q20whynoresponse_12",
"s6q21whynoresponse_12",
"s6q14_13",
"s6q15awhynoresponse_13",
"s6q15whynoresponse_13",
"s6q16other_13",
"s6q16whynoresponse_13",
"s6q17whynoresponse_13",
"s6q19whynoresponse_13",
"s6q18other_13",
"s6q18whynoresponse_13",
"s6q19awhynoresponse_13",
"s6q20whynoresponse_13",
"s6q21whynoresponse_13",
"s6q14_14",
"s6q15awhynoresponse_14",
"s6q15whynoresponse_14",
"s6q16other_14",
"s6q16whynoresponse_14",
"s6q17whynoresponse_14",
"s6q19whynoresponse_14",
"s6q18other_14",
"s6q18whynoresponse_14",
"s6q19awhynoresponse_14",
"s6q20whynoresponse_14",
"s6q21whynoresponse_14",
"s6q14_15",
"s6q15awhynoresponse_15",
"s6q15whynoresponse_15",
"s6q16other_15",
"s6q16whynoresponse_15",
"s6q17whynoresponse_15",
"s6q19whynoresponse_15",
"s6q18other_15",
"s6q18whynoresponse_15",
"s6q19awhynoresponse_15",
"s6q20whynoresponse_15",
"s6q21whynoresponse_15",
"s6q14_16",
"s6q15awhynoresponse_16",
"s6q15whynoresponse_16",
"s6q16other_16",
"s6q16whynoresponse_16",
"s6q17whynoresponse_16",
"s6q19whynoresponse_16",
"s6q18other_16",
"s6q18whynoresponse_16",
"s6q19awhynoresponse_16",
"s6q20whynoresponse_16",
"s6q21whynoresponse_16",
"s6q14_17",
"s6q15awhynoresponse_17",
"s6q15whynoresponse_17",
"s6q16other_17",
"s6q16whynoresponse_17",
"s6q17whynoresponse_17",
"s6q19whynoresponse_17",
"s6q18other_17",
"s6q18whynoresponse_17",
"s6q19awhynoresponse_17",
"s6q20whynoresponse_17",
"s6q21whynoresponse_17",
"s6q14_18",
"s6q15awhynoresponse_18",
"s6q15whynoresponse_18",
"s6q16other_18",
"s6q16whynoresponse_18",
"s6q17whynoresponse_18",
"s6q19whynoresponse_18",
"s6q18other_18",
"s6q18whynoresponse_18",
"s6q19awhynoresponse_18",
"s6q20whynoresponse_18",
"s6q21whynoresponse_18",
"s6q14_19",
"s6q15awhynoresponse_19",
"s6q15whynoresponse_19",
"s6q16other_19",
"s6q16whynoresponse_19",
"s6q17whynoresponse_19",
"s6q19whynoresponse_19",
"s6q18other_19",
"s6q18whynoresponse_19",
"s6q19awhynoresponse_19",
"s6q20whynoresponse_19",
"s6q21whynoresponse_19",
"s6q14_20",
"s6q15awhynoresponse_20",
"s6q15whynoresponse_20",
"s6q16other_20",
"s6q16whynoresponse_20",
"s6q17whynoresponse_20",
"s6q19whynoresponse_20",
"s6q18other_20",
"s6q18whynoresponse_20",
"s6q19awhynoresponse_20",
"s6q20whynoresponse_20",
"s6q21whynoresponse_20",
"s6q14_21",
"s6q15awhynoresponse_21",
"s6q15whynoresponse_21",
"s6q16other_21",
"s6q16whynoresponse_21",
"s6q17whynoresponse_21",
"s6q19whynoresponse_21",
"s6q18other_21",
"s6q18whynoresponse_21",
"s6q19awhynoresponse_21",
"s6q20whynoresponse_21",
"s6q21whynoresponse_21",
"s6q14_22",
"s6q15awhynoresponse_22",
"s6q15whynoresponse_22",
"s6q16other_22",
"s6q16whynoresponse_22",
"s6q17whynoresponse_22",
"s6q19whynoresponse_22",
"s6q18other_22",
"s6q18whynoresponse_22",
"s6q19awhynoresponse_22",
"s6q20whynoresponse_22",
"s6q21whynoresponse_22",
"s6q14_23",
"s6q15awhynoresponse_23",
"s6q15whynoresponse_23",
"s6q16other_23",
"s6q16whynoresponse_23",
"s6q17whynoresponse_23",
"s6q19whynoresponse_23",
"s6q18other_23",
"s6q18whynoresponse_23",
"s6q19awhynoresponse_23",
"s6q20whynoresponse_23",
"s6q21whynoresponse_23",
"s6q22whynoresponse",
"s6q23whynoresponse",
"s6q24whynoresponse",
"s6q25whynoresponse",
"s6q26whynoresponse",
"s6q27whynoresponse",
"s6q28whynoresponse",
"s6q29whynoresponse",
"s6q30whynoresponse",
"s6q31whynoresponse",
"s6q33",
"s6q32whynoresponse",
"s6q34whynoresponse",
"s6q35whynoresponse")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
mydata$s6q1whynoresponse[227] <- "The land was granted by the [LGU]."
mydata$s6q5_other[407] <- "Other"
mydata$s6q5_other[513] <- "Other"
mydata$s6q5_other[577] <- "Other"
mydata$s6q5_other[624] <- "Other"
mydata$s6q5_other[936] <- "Other"
mydata$s6q5_other[953] <- "Other"
mydata$s6q5_other[1010] <- "Other"
mydata$s6q5_other[1093] <- "Other"
mydata$s6q5_other[2000] <- "Other"
mydata$s6q5_other[2219] <- "Other"
mydata$s6q5whynoresponse[1073] <- "Other"
mydata$s6q9whynoresponse[30] <- "Out of [amount redacted] respondent only recieve [amount redacted]"
mydata$s6q9whynoresponse[1068] <- "Not definite. Depends on what owner of land asks for after assessment of harvest. Usually just a [percentage redacted]"
mydata$s6q12whynoresponse[16] <- "Other"
mydata$s6q12whynoresponse[333] <- "Other"
mydata$s6q14_1[531] <- "Other"
mydata$s6q14_1[696] <- "Other"
mydata$s6q14_1[709] <- "Other"
mydata$s6q14_1[865] <- "Other"
mydata$s6q14_1[904] <- "Other"
mydata$s6q14_1[992] <- "Other"
mydata$s6q14_1[1073] <- "Other"
mydata$s6q14_1[1235] <- "Other"
mydata$s6q14_1[1316] <- "Other"
mydata$s6q14_1[1331] <- "Other"
mydata$s6q14_1[1358] <- "Other"
mydata$s6q14_1[1421] <- "Other"
mydata$s6q14_1[1486] <- "Other"
mydata$s6q14_1[1520] <- "Other"
mydata$s6q14_1[1571] <- "Other"
mydata$s6q14_1[1641] <- "Other"
mydata$s6q14_1[1695] <- "Other"
mydata$s6q14_1[1699] <- "Other"
mydata$s6q14_1[1704] <- "Other"
mydata$s6q14_1[1715] <- "Other"
mydata$s6q14_1[1810] <- "Other"
mydata$s6q14_1[1814] <- "Other"
mydata$s6q14_1[1818] <- "Other"
mydata$s6q14_1[1901] <- "Other"
mydata$s6q14_1[1976] <- "Other"
mydata$s6q14_1[2132] <- "Other"
mydata$s6q14_1[2135] <- "Other"
mydata$s6q14_1[2228] <- "Other"
mydata$s6q16other_1[662] <- "Loan from family and friends"
mydata$s6q16other_1[671] <- "Loan from family and friends"
mydata$s6q16other_1[1514] <- "Loan from family and friends"
mydata$s6q16other_1[26] <- "Other"
mydata$s6q16other_1[55] <- "Other"
mydata$s6q16other_1[130] <- "Other"
mydata$s6q16other_1[131] <- "Other"
mydata$s6q16other_1[132] <- "Other"
mydata$s6q16other_1[262] <- "Other"
mydata$s6q16other_1[286] <- "Other"
mydata$s6q16other_1[290] <- "Other"
mydata$s6q16other_1[317] <- "Other"
mydata$s6q16other_1[320] <- "Other"
mydata$s6q16other_1[327] <- "Other"
mydata$s6q16other_1[332] <- "Other"
mydata$s6q16other_1[379] <- "Other"
mydata$s6q16other_1[422] <- "Other"
mydata$s6q16other_1[455] <- "Other"
mydata$s6q16other_1[459] <- "Other"
mydata$s6q16other_1[460] <- "Other"
mydata$s6q16other_1[475] <- "Other"
mydata$s6q16other_1[513] <- "Other"
mydata$s6q16other_1[564] <- "Other"
mydata$s6q16other_1[584] <- "Other"
mydata$s6q16other_1[587] <- "Other"
mydata$s6q16other_1[595] <- "Other"
mydata$s6q16other_1[596] <- "Other"
mydata$s6q16other_1[612] <- "Other"
mydata$s6q16other_1[614] <- "Other"
mydata$s6q16other_1[631] <- "Other"
mydata$s6q16other_1[638] <- "Other"
mydata$s6q16other_1[649] <- "Other"
mydata$s6q16other_1[650] <- "Other"
mydata$s6q16other_1[678] <- "Other"
mydata$s6q16other_1[686] <- "Other"
mydata$s6q16other_1[1367] <- "Other"
mydata$s6q16other_1[1389] <- "Other"
mydata$s6q16other_1[1395] <- "Other"
mydata$s6q16other_1[1542] <- "Other"
mydata$s6q16other_1[1588] <- "Other"
mydata$s6q16other_1[1686] <- "Other"
mydata$s6q16other_1[1824] <- "Other"
mydata$s6q16other_1[1825] <- "Other"
mydata$s6q16other_1[1828] <- "Other"
mydata$s6q16other_1[1832] <- "Other"
mydata$s6q16other_1[1904] <- "Other"
mydata$s6q16other_1[2082] <- "Other"
mydata$s6q16other_1[2129] <- "Other"
mydata$s6q16other_1[2134] <- "Other"
mydata$s6q16other_1[2215] <- "Other"
mydata$s6q16other_1[2219] <- "Other"
mydata$s6q18other_1[799] <- "Other"
mydata$s6q18other_1[840] <- "Other"
mydata$s6q18other_1[904] <- "Other"
mydata$s6q18other_1[952] <- "Other"
mydata$s6q18other_1[1358] <- "Other"
mydata$s6q18other_1[1501] <- "Other"
mydata$s6q14_2[17] <- "Other"
mydata$s6q14_2[116] <- "Other"
mydata$s6q14_2[701] <- "Other"
mydata$s6q14_2[709] <- "Other"
mydata$s6q14_2[760] <- "Other"
mydata$s6q14_2[778] <- "Other"
mydata$s6q14_2[941] <- "Other"
mydata$s6q14_2[1057] <- "Other"
mydata$s6q14_2[1073] <- "Other"
mydata$s6q14_2[1205] <- "Other"
mydata$s6q14_2[1235] <- "Other"
mydata$s6q14_2[1299] <- "Other"
mydata$s6q14_2[1313] <- "Other"
mydata$s6q14_2[1316] <- "Other"
mydata$s6q14_2[1340] <- "Other"
mydata$s6q14_2[1347] <- "Other"
mydata$s6q14_2[1417] <- "Other"
mydata$s6q14_2[1421] <- "Other"
mydata$s6q14_2[1476] <- "Other"
mydata$s6q14_2[1520] <- "Other"
mydata$s6q14_2[1553] <- "Other"
mydata$s6q14_2[1698] <- "Other"
mydata$s6q14_2[1744] <- "Other"
mydata$s6q14_2[2000] <- "Other"
mydata$s6q14_2[2024] <- "Other"
mydata$s6q14_2[2136] <- "Other"
mydata$s6q14_2[2138] <- "Other"
mydata$s6q14_2[2139] <- "Other"
mydata$s6q14_2[2221] <- "Other"
mydata$s6q16other_2[132] <- "Other"
mydata$s6q16other_2[290] <- "Other"
mydata$s6q16other_2[327] <- "Other"
mydata$s6q16other_2[459] <- "Other"
mydata$s6q16other_2[466] <- "Other"
mydata$s6q16other_2[580] <- "Other"
mydata$s6q16other_2[593] <- "Other"
mydata$s6q16other_2[599] <- "Other"
mydata$s6q16other_2[627] <- "Other"
mydata$s6q16other_2[666] <- "Other"
mydata$s6q16other_2[1828] <- "Other"
mydata$s6q16other_2[2218] <- "Other"
mydata$s6q18other_2[638] <- "Other"
mydata$s6q18other_2[657] <- "Other"
mydata$s6q18other_2[675] <- "Other"
mydata$s6q18other_2[1068] <- "Other"
mydata$s6q18other_2[1113] <- "Other"
mydata$s6q18other_2[1905] <- "Other"
mydata$s6q18other_3[1367] <- "Other"
mydata$s6q18other_3[1831] <- "Other"
mydata$s6q18other_3[2268] <- "Other"
mydata$s6q18other_4[1345] <- "Other"
mydata$s6q18other_4[1367] <- "Other"
mydata$s6q18other_4[1831] <- "Other"
mydata$s6q19awhynoresponse_5[1235] <- "[Language]"
mydata$s6q14_12[1477] <- "[Language]"
mydata$s6q14_21[1477] <- "[Language]"
mydata$s6q14_23[1477] <- "[Language]"
mydata$s6q24whynoresponse[2046] <- "He only knows the total amount which is [amount redacted] for 12 months"
mydata$s6q26whynoresponse[2046] <- "He only knows the total amount which is [amount redacted] for 12 months"
mydata$s6q30whynoresponse[1085] <- "Only the hudband and wife are working in the farm and also there son [name]"
mydata$s6q30whynoresponse[2046] <- "He only knows the total amount which is [amount redacted] in 12 months"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)