DOL-ILAB SDC - Section_8
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_8" # !!!Update filename
functions_vers <- "functions_1.8.R" # !!!Update helper functions fileSetup data, functions and create dictionary for dataset review
source (functions_vers)Visually inspect variables in "dictionary.csv" and flag for risk, using the following flags:
# Direct PII: Respondent Names, Addresses, Identification Numbers, Phone Numbers
# Direct PII-team: Interviewer Names, other field team names
# Indirect PII-ordinal: Date of birth, Age, income, education, household composition.
# Indirect PII-categorical: Gender, education, ethnicity, nationality,
# occupation, employer, head of household, marital status
# GPS: Longitude, Latitude
# Small Location: Location (<100,000)
# Large Location (>100,000)
# Weight: weightVar
# Household ID: hhId,
# Open-ends: Review responses for any sensitive information, redact as necessary Direct PII: variables to be removed
# !!!No Direct PIIDirect PII-team: Encode field team names
# !!!No Direct PII-teamSmall locations: Encode locations with pop <100,000 using random large numbers
# !!!No small locationsIndirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
# Focus on variables with a "Lowest Freq" in dictionary of 30 or less.
# Top code high income to the 99.5 percentile
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q8_1)[na.exclude(mydata$s8q8_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q8_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q8_1. How much was this start-up capital? Magkano ang pangunang kapital na ito?
## 0 10 20 35 50 60 75 90 100 125 130 150 178 200 250
## 3 1 1 1 3 1 1 1 6 1 1 5 1 8 3
## 271 300 350 400 450 500 600 700 750 800 900 1000 1500 1600 1675
## 1 7 1 2 2 36 3 4 1 2 1 45 16 2 1
## 2000 2100 2500 2700 3000 3500 3700 4000 4500 4900 5000 5500 6000 6500 7000
## 33 1 5 1 36 2 1 9 1 1 56 1 3 2 7
## 7500 8000 8400 10000 11000 11760 12000 14000 15000 16000 20000 21000 21600 22000 25000
## 1 1 1 27 1 1 1 4 10 1 7 2 1 1 2
## 30000 39000 45408 47000 50000 53096 75000 76000 80000 85000 1e+05 150000 <NA>
## 1 1 1 1 1 1 1 1 1 1 1 1 1903
## [1] "Frequency table after encoding"
## s8q8_1. How much was this start-up capital? Magkano ang pangunang kapital na ito?
## 0 10 20 35 50 60 75
## 3 1 1 1 3 1 1
## 90 100 125 130 150 178 200
## 1 6 1 1 5 1 8
## 250 271 300 350 400 450 500
## 3 1 7 1 2 2 36
## 600 700 750 800 900 1000 1500
## 3 4 1 2 1 45 16
## 1600 1675 2000 2100 2500 2700 3000
## 2 1 33 1 5 1 36
## 3500 3700 4000 4500 4900 5000 5500
## 2 1 9 1 1 56 1
## 6000 6500 7000 7500 8000 8400 10000
## 3 2 7 1 1 1 27
## 11000 11760 12000 14000 15000 16000 20000
## 1 1 1 4 10 1 7
## 21000 21600 22000 25000 30000 39000 45408
## 2 1 1 2 1 1 1
## 47000 50000 53096 75000 76000 80000 85000
## 1 1 1 1 1 1 1
## 85600 or more <NA>
## 2 1903
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q9_1)[na.exclude(mydata$s8q9_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q9_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q9_1. In the last 12 months what was spent on machinery or durable goods (e.g., tools,
## 0 50 60 65 66 85 100 105 120 130 150 195 200
## 333 2 1 1 1 1 3 1 1 1 4 1 4
## 250 255 260 292 300 360 370 380 420 450 500 510 560
## 2 1 1 1 5 1 1 1 1 2 14 1 1
## 600 620 708 750 800 840 850 900 960 1000 1111 1160 1350
## 6 1 1 2 2 2 1 1 1 9 1 1 1
## 1400 1500 1600 1850 2000 2400 2500 2640 3000 3060 3500 3900 3984
## 1 5 1 1 9 1 3 1 9 2 3 1 1
## 4000 4032 4045 4200 4320 4500 4900 5000 5070 5200 6720 7000 10000
## 2 1 1 1 1 1 1 10 1 1 1 3 4
## 12400 13500 13600 14000 14400 15000 16000 20000 21000 22000 40000 41900 48000
## 1 1 1 1 1 2 1 2 1 1 1 1 1
## 50000 50250 85000 1.2e+07 <NA>
## 1 1 1 1 1796
## [1] "Frequency table after encoding"
## s8q9_1. In the last 12 months what was spent on machinery or durable goods (e.g., tools,
## 0 50 60 65 66 85 100
## 333 2 1 1 1 1 3
## 105 120 130 150 195 200 250
## 1 1 1 4 1 4 2
## 255 260 292 300 360 370 380
## 1 1 1 5 1 1 1
## 420 450 500 510 560 600 620
## 1 2 14 1 1 6 1
## 708 750 800 840 850 900 960
## 1 2 2 2 1 1 1
## 1000 1111 1160 1350 1400 1500 1600
## 9 1 1 1 1 5 1
## 1850 2000 2400 2500 2640 3000 3060
## 1 9 1 3 1 9 2
## 3500 3900 3984 4000 4032 4045 4200
## 3 1 1 2 1 1 1
## 4320 4500 4900 5000 5070 5200 6720
## 1 1 1 10 1 1 1
## 7000 10000 12400 13500 13600 14000 14400
## 3 4 1 1 1 1 1
## 15000 16000 20000 21000 22000 40000 41900
## 2 1 2 1 1 1 1
## 48000 50000 50126 or more <NA>
## 1 1 3 1796
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q12_1)[na.exclude(mydata$s8q12_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q12_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q12_1. Electricity Kuryente
## 0 1 2 11 18 20 30 40 50 100 119 125 200 240 250
## 431 1 1 1 1 3 4 1 3 1 1 1 1 2 1
## 300 400 500 600 755 756 800 900 1000 1100 1200 1500 1800 2000 2400
## 3 1 3 6 1 1 2 1 1 1 2 1 1 1 3
## 2500 3000 3600 4000 6000 6800 7200 8400 15000 33600 34800 36000 37200 840000 <NA>
## 1 1 3 1 4 1 2 1 1 1 1 1 1 1 1795
## [1] "Frequency table after encoding"
## s8q12_1. Electricity Kuryente
## 0 1 2 11 18 20 30
## 431 1 1 1 1 3 4
## 40 50 100 119 125 200 240
## 1 3 1 1 1 1 2
## 250 300 400 500 600 755 756
## 1 3 1 3 6 1 1
## 800 900 1000 1100 1200 1500 1800
## 2 1 1 1 2 1 1
## 2000 2400 2500 3000 3600 4000 6000
## 1 3 1 1 3 1 4
## 6800 7200 8400 15000 33600 34800 35400 or more
## 1 2 1 1 1 1 3
## <NA>
## 1795
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q13_1)[na.exclude(mydata$s8q13_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q13_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q13_1. Salaries/Wages Pasahod/Suweldo
## 0 1 3 100 200 1500 4320 4800 10000 14400 20000 72000 76800 87600 360000
## 486 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## 528000 <NA>
## 1 1795
## [1] "Frequency table after encoding"
## s8q13_1. Salaries/Wages Pasahod/Suweldo
## 0 1 3 100 200 1500 4320
## 486 1 1 1 1 1 1
## 4800 10000 14400 20000 72000 76800 82200 or more
## 1 1 1 1 1 1 3
## <NA>
## 1795
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q14_1)[na.exclude(mydata$s8q14_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q14_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q14_1. Water Tubig
## 0 1 2 8 20 30 50 60 80 90 120 200 226 240 300
## 471 1 1 1 2 1 1 1 1 2 1 3 1 1 2
## 350 360 480 720 1250 1680 1728 1825 2400 3600 144000 <NA>
## 1 1 1 1 1 1 1 1 1 2 1 1794
## [1] "Frequency table after encoding"
## s8q14_1. Water Tubig
## 0 1 2 8 20 30 50 60
## 471 1 1 1 2 1 1 1
## 80 90 120 200 226 240 300 350
## 1 2 1 3 1 1 2 1
## 360 480 720 1250 1680 1728 1825 2400
## 1 1 1 1 1 1 1 1
## 2994 or more <NA>
## 3 1794
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q15_1)[na.exclude(mydata$s8q15_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q15_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q15_1. Transport Transportasyon
## 0 1 14 16 20 35 40 42 50 56 80 90 95 100 110
## 265 1 1 1 4 1 3 1 5 1 3 1 1 13 1
## 140 144 150 180 200 219 238 240 250 280 286 300 320 340 400
## 1 1 3 2 5 1 1 4 1 2 1 3 3 1 3
## 450 464 480 500 504 510 576 600 640 648 720 750 768 800 834
## 1 1 4 5 1 1 1 4 1 1 3 1 1 4 1
## 840 900 960 1000 1120 1152 1200 1240 1350 1440 1600 1728 1800 1920 2000
## 1 1 3 4 1 2 2 1 1 2 3 1 1 4 3
## 2160 2250 2280 2304 2400 2496 2500 2520 2800 2880 3000 3360 3600 3648 3650
## 1 1 1 1 7 2 2 1 1 6 1 1 1 1 1
## 3840 4200 4500 4704 4752 4800 5040 5200 5280 5600 5760 5780 5880 6000 6120
## 1 2 1 2 1 7 1 1 1 2 3 1 1 1 1
## 6240 6720 7200 7920 8000 8640 9125 9600 10800 11520 12000 13440 14400 15000 15840
## 1 3 6 1 1 1 1 5 3 1 1 2 4 1 1
## 16800 18000 19200 21000 25200 25923 28800 30240 32400 33600 36000 38400 63600 76800 192003
## 1 4 1 1 1 1 2 1 1 1 3 1 1 1 1
## <NA>
## 1795
## [1] "Frequency table after encoding"
## s8q15_1. Transport Transportasyon
## 0 1 14 16 20 35 40
## 265 1 1 1 4 1 3
## 42 50 56 80 90 95 100
## 1 5 1 3 1 1 13
## 110 140 144 150 180 200 219
## 1 1 1 3 2 5 1
## 238 240 250 280 286 300 320
## 1 4 1 2 1 3 3
## 340 400 450 464 480 500 504
## 1 3 1 1 4 5 1
## 510 576 600 640 648 720 750
## 1 1 4 1 1 3 1
## 768 800 834 840 900 960 1000
## 1 4 1 1 1 3 4
## 1120 1152 1200 1240 1350 1440 1600
## 1 2 2 1 1 2 3
## 1728 1800 1920 2000 2160 2250 2280
## 1 1 4 3 1 1 1
## 2304 2400 2496 2500 2520 2800 2880
## 1 7 2 2 1 1 6
## 3000 3360 3600 3648 3650 3840 4200
## 1 1 1 1 1 1 2
## 4500 4704 4752 4800 5040 5200 5280
## 1 2 1 7 1 1 1
## 5600 5760 5780 5880 6000 6120 6240
## 2 3 1 1 1 1 1
## 6720 7200 7920 8000 8640 9125 9600
## 3 6 1 1 1 1 5
## 10800 11520 12000 13440 14400 15000 15840
## 3 1 1 2 4 1 1
## 16800 18000 19200 21000 25200 25923 28800
## 1 4 1 1 1 1 2
## 30240 32400 33600 36000 38400 51000 or more <NA>
## 1 1 1 3 1 3 1795
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q16_1)[na.exclude(mydata$s8q16_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q16_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q16_1. Purchase of inputs, inventory, and products Pagbili ng mga inilalagay, imbentar
## 0 1 7 42 50 60 70 80 100 144 150 200 240
## 244 1 1 1 1 1 1 1 4 1 1 1 1
## 300 331 350 360 400 440 444 450 500 528 600 680 700
## 5 1 1 1 2 1 1 1 11 1 4 1 3
## 720 750 800 838 920 1000 1200 1500 1600 1700 1920 2000 2400
## 1 1 1 1 1 12 3 7 1 1 1 12 1
## 2880 3000 3375 3840 4000 4800 5000 5760 6000 7000 7200 8000 9000
## 1 12 1 1 5 2 6 1 4 3 3 5 2
## 9600 10000 10800 12000 15000 16000 18000 19200 19800 20000 21000 21600 24000
## 2 10 1 8 2 2 5 1 1 1 1 1 3
## 30000 32160 33600 36000 38400 38880 39200 44000 45408 48000 50000 51600 54000
## 2 1 2 3 1 1 1 1 1 7 1 1 1
## 56000 57600 60000 64000 67200 70000 72000 75600 76800 80000 90000 93504 96000
## 1 1 1 1 2 1 6 1 2 1 2 1 2
## 100800 108000 112000 120000 134400 144000 180000 192000 235200 240000 288000 324000 336000
## 1 1 1 3 1 6 1 1 1 1 2 1 1
## 492750 504000 540000 576000 672000 690000 720000 9e+05 1080000 <NA>
## 1 1 1 2 2 1 1 1 1 1800
## [1] "Frequency table after encoding"
## s8q16_1. Purchase of inputs, inventory, and products Pagbili ng mga inilalagay, imbentar
## 0 1 7 42 50 60 70
## 244 1 1 1 1 1 1
## 80 100 144 150 200 240 300
## 1 4 1 1 1 1 5
## 331 350 360 400 440 444 450
## 1 1 1 2 1 1 1
## 500 528 600 680 700 720 750
## 11 1 4 1 3 1 1
## 800 838 920 1000 1200 1500 1600
## 1 1 1 12 3 7 1
## 1700 1920 2000 2400 2880 3000 3375
## 1 1 12 1 1 12 1
## 3840 4000 4800 5000 5760 6000 7000
## 1 5 2 6 1 4 3
## 7200 8000 9000 9600 10000 10800 12000
## 3 5 2 2 10 1 8
## 15000 16000 18000 19200 19800 20000 21000
## 2 2 5 1 1 1 1
## 21600 24000 30000 32160 33600 36000 38400
## 1 3 2 1 2 3 1
## 38880 39200 44000 45408 48000 50000 51600
## 1 1 1 1 7 1 1
## 54000 56000 57600 60000 64000 67200 70000
## 1 1 1 1 1 2 1
## 72000 75600 76800 80000 90000 93504 96000
## 6 1 2 1 2 1 2
## 100800 108000 112000 120000 134400 144000 180000
## 1 1 1 3 1 6 1
## 192000 235200 240000 288000 324000 336000 492750
## 1 1 1 2 1 1 1
## 504000 540000 576000 672000 690000 705749 or more <NA>
## 1 1 2 2 1 3 1800
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q17_1)[na.exclude(mydata$s8q17_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q17_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q17_1. Other costs (exclude machinery, tools, durables already mentioned) Iba pang gas
## 0 1 20 25 120 150 170 195 200 300 370 500 840 880 1000
## 452 1 1 1 2 1 1 1 4 1 1 4 1 1 2
## 1200 1500 1600 1800 2000 2400 2800 3240 5000 6048 7200 7300 10500 11132 12000
## 1 1 1 5 1 1 1 1 1 1 2 1 1 1 1
## 18000 21600 36000 45000 85000 108000 <NA>
## 2 1 1 1 1 1 1795
## [1] "Frequency table after encoding"
## s8q17_1. Other costs (exclude machinery, tools, durables already mentioned) Iba pang gas
## 0 1 20 25 120 150 170
## 452 1 1 1 2 1 1
## 195 200 300 370 500 840 880
## 1 4 1 1 4 1 1
## 1000 1200 1500 1600 1800 2000 2400
## 2 1 1 1 5 1 1
## 2800 3240 5000 6048 7200 7300 10500
## 1 1 1 1 2 1 1
## 11132 12000 18000 21600 36000 40500 or more <NA>
## 1 1 2 1 1 3 1795
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q20_1)[na.exclude(mydata$s8q20_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q20_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q20_1. What was the total revenue received from this enterprise in the last 12 months?
## 0 1 150 300 350 360 450 500 600 700 900 1000 1050
## 8 1 1 5 1 1 1 6 1 1 3 2 1
## 1200 1250 1440 1460 1500 1800 1900 2000 2100 2160 2244 2400 2450
## 1 1 1 1 1 3 1 3 2 1 1 5 1
## 2500 2800 3000 3100 3200 3360 3456 3500 3600 3840 4000 4200 4320
## 1 2 9 1 1 1 1 1 5 1 4 1 1
## 4500 4800 5000 5280 5400 5625 6000 6300 6500 7200 7500 7560 7680
## 2 10 5 1 2 1 9 1 1 5 3 1 1
## 7800 8000 8400 9000 9300 9600 10000 10080 10800 12000 12400 12600 12700
## 1 1 3 3 1 2 3 2 1 14 1 3 2
## 12960 14200 14400 14900 15000 15050 16000 16800 17280 18000 18480 19200 20000
## 1 2 9 1 6 1 2 3 1 12 1 1 4
## 20160 21600 22000 22400 22560 23040 23100 24000 24080 25000 25200 26400 26880
## 1 1 1 2 1 1 1 15 1 1 3 1 2
## 27000 28000 28800 29400 30000 31200 33600 34200 36000 36400 36500 38400 40000
## 2 3 6 1 8 1 4 1 18 2 2 3 5
## 42000 43200 44880 45000 45360 45600 48000 49000 49440 50000 50400 52500 53250
## 4 4 1 2 1 1 4 1 1 1 2 1 1
## 54000 54750 55200 57600 60000 61600 63700 67200 70000 72000 73200 74400 75600
## 3 1 1 7 6 1 1 5 1 25 1 1 1
## 76800 81150 84000 86700 89600 90000 91250 93600 95040 96000 97200 99000 1e+05
## 2 1 3 1 1 2 1 1 1 3 1 1 1
## 100800 104400 105000 108000 109500 115200 120000 130000 144000 145600 150000 153600 168000
## 3 1 3 14 1 1 1 1 8 1 1 1 5
## 180000 182500 196000 198000 210000 216000 218400 240000 252000 259200 268800 270000 288000
## 6 1 1 1 1 4 2 1 2 1 1 1 4
## 3e+05 326400 336000 346080 360000 369600 432000 450000 480000 504000 528000 720000 828000
## 1 1 1 1 3 1 2 1 1 2 1 2 1
## 840000 1152000 1440000 2340001 <NA>
## 1 1 1 1 1817
## [1] "Frequency table after encoding"
## s8q20_1. What was the total revenue received from this enterprise in the last 12 months?
## 0 1 150 300 350 360
## 8 1 1 5 1 1
## 450 500 600 700 900 1000
## 1 6 1 1 3 2
## 1050 1200 1250 1440 1460 1500
## 1 1 1 1 1 1
## 1800 1900 2000 2100 2160 2244
## 3 1 3 2 1 1
## 2400 2450 2500 2800 3000 3100
## 5 1 1 2 9 1
## 3200 3360 3456 3500 3600 3840
## 1 1 1 1 5 1
## 4000 4200 4320 4500 4800 5000
## 4 1 1 2 10 5
## 5280 5400 5625 6000 6300 6500
## 1 2 1 9 1 1
## 7200 7500 7560 7680 7800 8000
## 5 3 1 1 1 1
## 8400 9000 9300 9600 10000 10080
## 3 3 1 2 3 2
## 10800 12000 12400 12600 12700 12960
## 1 14 1 3 2 1
## 14200 14400 14900 15000 15050 16000
## 2 9 1 6 1 2
## 16800 17280 18000 18480 19200 20000
## 3 1 12 1 1 4
## 20160 21600 22000 22400 22560 23040
## 1 1 1 2 1 1
## 23100 24000 24080 25000 25200 26400
## 1 15 1 1 3 1
## 26880 27000 28000 28800 29400 30000
## 2 2 3 6 1 8
## 31200 33600 34200 36000 36400 36500
## 1 4 1 18 2 2
## 38400 40000 42000 43200 44880 45000
## 3 5 4 4 1 2
## 45360 45600 48000 49000 49440 50000
## 1 1 4 1 1 1
## 50400 52500 53250 54000 54750 55200
## 2 1 1 3 1 1
## 57600 60000 61600 63700 67200 70000
## 7 6 1 1 5 1
## 72000 73200 74400 75600 76800 81150
## 25 1 1 1 2 1
## 84000 86700 89600 90000 91250 93600
## 3 1 1 2 1 1
## 95040 96000 97200 99000 1e+05 100800
## 1 3 1 1 1 3
## 104400 105000 108000 109500 115200 120000
## 1 3 14 1 1 1
## 130000 144000 145600 150000 153600 168000
## 1 8 1 1 1 5
## 180000 182500 196000 198000 210000 216000
## 6 1 1 1 1 4
## 218400 240000 252000 259200 268800 270000
## 2 1 2 1 1 1
## 288000 3e+05 326400 336000 346080 360000
## 4 1 1 1 1 3
## 369600 432000 450000 480000 504000 528000
## 1 2 1 1 2 1
## 720000 828000 840000 1030320 or more <NA>
## 2 1 1 3 1817
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q21_1)[na.exclude(mydata$s8q21_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q21_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q21_1. What are the sales of this enterprise in an average month? Magkano ang benta ng
## 0 30 50 80 100 120 150 180 187 200 250 288 300 320 350
## 10 1 1 1 2 2 5 1 1 4 1 1 9 1 2
## 360 400 420 450 500 600 630 640 700 750 800 840 900 1000 1080
## 2 6 1 3 7 6 1 1 3 1 4 1 1 10 1
## 1200 1225 1250 1400 1500 1600 1680 1700 1750 1800 1880 1900 1920 1960 2000
## 18 1 1 2 10 3 1 1 2 3 1 1 2 1 21
## 2100 2200 2240 2400 2500 2800 3000 3080 3200 3300 3500 3600 3780 3800 3900
## 1 2 1 6 6 6 24 1 5 1 1 6 1 1 1
## 4000 4200 4400 4500 4600 4800 4850 5000 5250 5320 5600 6000 6100 6300 6400
## 7 2 1 6 1 9 1 8 2 1 4 37 1 1 2
## 6600 7000 7500 7583 7800 8000 8100 8250 8400 8760 9000 9100 9600 9800 10000
## 1 1 9 1 1 4 1 1 6 1 26 1 1 1 5
## 10143 11200 11400 12000 12500 12600 13440 13500 14000 14400 14440 15000 16500 16800 18000
## 1 1 1 5 1 1 1 1 7 3 1 14 1 2 6
## 18200 18333 19600 20000 21000 21300 21600 22400 22500 24000 25000 25200 27000 27200 28000
## 1 1 1 4 3 1 1 3 2 3 1 1 1 1 1
## 30000 30030 31800 33000 33600 36000 36400 37500 38000 39000 40000 42000 44352 45000 48000
## 8 1 1 1 1 5 1 1 1 1 2 3 1 1 1
## 54000 57600 60000 63000 66000 69000 76800 79500 120000 144000 150000 220800 285000 360000 <NA>
## 1 1 2 1 1 1 1 1 3 1 1 1 1 1 1815
## [1] "Frequency table after encoding"
## s8q21_1. What are the sales of this enterprise in an average month? Magkano ang benta ng
## 0 30 50 80 100 120 150
## 10 1 1 1 2 2 5
## 180 187 200 250 288 300 320
## 1 1 4 1 1 9 1
## 350 360 400 420 450 500 600
## 2 2 6 1 3 7 6
## 630 640 700 750 800 840 900
## 1 1 3 1 4 1 1
## 1000 1080 1200 1225 1250 1400 1500
## 10 1 18 1 1 2 10
## 1600 1680 1700 1750 1800 1880 1900
## 3 1 1 2 3 1 1
## 1920 1960 2000 2100 2200 2240 2400
## 2 1 21 1 2 1 6
## 2500 2800 3000 3080 3200 3300 3500
## 6 6 24 1 5 1 1
## 3600 3780 3800 3900 4000 4200 4400
## 6 1 1 1 7 2 1
## 4500 4600 4800 4850 5000 5250 5320
## 6 1 9 1 8 2 1
## 5600 6000 6100 6300 6400 6600 7000
## 4 37 1 1 2 1 1
## 7500 7583 7800 8000 8100 8250 8400
## 9 1 1 4 1 1 6
## 8760 9000 9100 9600 9800 10000 10143
## 1 26 1 1 1 5 1
## 11200 11400 12000 12500 12600 13440 13500
## 1 1 5 1 1 1 1
## 14000 14400 14440 15000 16500 16800 18000
## 7 3 1 14 1 2 6
## 18200 18333 19600 20000 21000 21300 21600
## 1 1 1 4 3 1 1
## 22400 22500 24000 25000 25200 27000 27200
## 3 2 3 1 1 1 1
## 28000 30000 30030 31800 33000 33600 36000
## 1 8 1 1 1 1 5
## 36400 37500 38000 39000 40000 42000 44352
## 1 1 1 1 2 3 1
## 45000 48000 54000 57600 60000 63000 66000
## 1 1 1 1 2 1 1
## 69000 76800 79500 120000 144000 150000 192480 or more
## 1 1 1 3 1 1 3
## <NA>
## 1815
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q23_1)[na.exclude(mydata$s8q23_1)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q23_1", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q23_1. In the last twelve months, what was the amount your household earned as profit o
## -12960 -11000 -9600 -3000 0 1 30 40 50 80 100 150 190 200 250
## 1 1 1 1 66 1 1 1 1 1 4 1 2 1 2
## 300 344 350 360 380 400 450 480 500 550 600 700 720 800 900
## 1 1 1 1 1 1 2 1 7 1 8 1 1 2 3
## 920 960 1000 1200 1500 1550 1560 1650 1740 1800 1920 2000 2100 2244 2400
## 1 1 3 3 8 1 1 1 1 3 1 4 2 1 5
## 2500 2800 3000 3200 3450 3456 3600 3780 3800 3840 4000 4400 4500 4600 4800
## 1 2 13 1 1 1 4 1 1 1 2 1 4 2 4
## 5000 5550 6000 6300 6720 6930 6960 7000 7200 7500 7680 7700 7800 7920 8000
## 5 1 2 1 1 1 1 3 3 2 2 1 1 1 4
## 8080 8400 8650 8760 9000 9440 9600 10000 10080 10100 10400 10500 10560 10604 11496
## 1 1 1 1 3 1 4 10 2 1 1 1 1 1 1
## 12000 12400 12440 12540 12600 12960 13200 13860 14000 14130 14200 14250 14400 14700 14800
## 9 1 1 1 1 1 1 1 1 1 2 1 2 1 1
## 15000 15050 15680 16000 16060 16160 16320 16520 16600 16750 16800 18000 18480 19200 19800
## 7 1 1 1 1 1 1 1 1 1 3 8 1 1 1
## 20000 20400 20496 21000 21600 22080 22400 22560 22845 23000 23280 23316 23520 23950 24000
## 3 1 1 2 3 1 1 1 1 1 1 1 1 1 4
## 25200 26400 27000 27400 27450 28000 28800 28950 29568 30000 30800 30928 31200 31800 32400
## 1 2 1 1 1 1 3 1 1 6 1 1 1 1 1
## 33000 33420 33600 34000 35000 35040 35250 35600 36000 36400 36500 42000 43200 44352 45000
## 1 1 2 1 2 1 1 1 10 1 2 2 2 1 1
## 45600 48000 48864 48960 49000 49200 49428 49440 50000 50160 52500 53250 53880 54000 55000
## 1 2 1 1 1 1 1 1 1 1 1 1 1 5 1
## 55200 55866 57230 57600 57608 59600 60000 62755 63000 63600 67200 71600 71900 72000 74200
## 1 1 1 3 1 1 4 1 1 2 3 1 1 9 1
## 76800 79650 80000 86400 87200 90240 91000 93072 96000 97200 100800 102000 103000 106840 108000
## 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8
## 109500 120000 127880 129504 143424 144000 149280 168000 168600 180000 182500 192000 237000 254400 259200
## 1 1 1 1 1 2 1 1 1 2 1 1 1 1 1
## 288000 360000 450000 2e+06 <NA>
## 1 1 1 1 1821
## [1] "Frequency table after encoding"
## s8q23_1. In the last twelve months, what was the amount your household earned as profit o
## -12960 -11000 -9600 -3000 0 1 30
## 1 1 1 1 66 1 1
## 40 50 80 100 150 190 200
## 1 1 1 4 1 2 1
## 250 300 344 350 360 380 400
## 2 1 1 1 1 1 1
## 450 480 500 550 600 700 720
## 2 1 7 1 8 1 1
## 800 900 920 960 1000 1200 1500
## 2 3 1 1 3 3 8
## 1550 1560 1650 1740 1800 1920 2000
## 1 1 1 1 3 1 4
## 2100 2244 2400 2500 2800 3000 3200
## 2 1 5 1 2 13 1
## 3450 3456 3600 3780 3800 3840 4000
## 1 1 4 1 1 1 2
## 4400 4500 4600 4800 5000 5550 6000
## 1 4 2 4 5 1 2
## 6300 6720 6930 6960 7000 7200 7500
## 1 1 1 1 3 3 2
## 7680 7700 7800 7920 8000 8080 8400
## 2 1 1 1 4 1 1
## 8650 8760 9000 9440 9600 10000 10080
## 1 1 3 1 4 10 2
## 10100 10400 10500 10560 10604 11496 12000
## 1 1 1 1 1 1 9
## 12400 12440 12540 12600 12960 13200 13860
## 1 1 1 1 1 1 1
## 14000 14130 14200 14250 14400 14700 14800
## 1 1 2 1 2 1 1
## 15000 15050 15680 16000 16060 16160 16320
## 7 1 1 1 1 1 1
## 16520 16600 16750 16800 18000 18480 19200
## 1 1 1 3 8 1 1
## 19800 20000 20400 20496 21000 21600 22080
## 1 3 1 1 2 3 1
## 22400 22560 22845 23000 23280 23316 23520
## 1 1 1 1 1 1 1
## 23950 24000 25200 26400 27000 27400 27450
## 1 4 1 2 1 1 1
## 28000 28800 28950 29568 30000 30800 30928
## 1 3 1 1 6 1 1
## 31200 31800 32400 33000 33420 33600 34000
## 1 1 1 1 1 2 1
## 35000 35040 35250 35600 36000 36400 36500
## 2 1 1 1 10 1 2
## 42000 43200 44352 45000 45600 48000 48864
## 2 2 1 1 1 2 1
## 48960 49000 49200 49428 49440 50000 50160
## 1 1 1 1 1 1 1
## 52500 53250 53880 54000 55000 55200 55866
## 1 1 1 5 1 1 1
## 57230 57600 57608 59600 60000 62755 63000
## 1 3 1 1 4 1 1
## 63600 67200 71600 71900 72000 74200 76800
## 2 3 1 1 9 1 1
## 79650 80000 86400 87200 90240 91000 93072
## 1 1 1 1 1 1 1
## 96000 97200 100800 102000 103000 106840 108000
## 1 1 1 1 1 1 8
## 109500 120000 127880 129504 143424 144000 149280
## 1 1 1 1 1 2 1
## 168000 168600 180000 182500 192000 237000 254400
## 1 1 2 1 1 1 1
## 259200 288000 333359 or more <NA>
## 1 1 3 1821
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q8_2)[na.exclude(mydata$s8q8_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q8_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q8_2. How much was this start-up capital? Magkano ang pangunang kapital na ito?
## 0 200 300 500 1000 1500 2000 2500 3000 3250 4500 5000 7000 8000 10000 15000 18000 20000
## 1 2 3 5 5 3 1 1 5 1 1 7 1 1 4 3 1 2
## 21500 28000 30000 40000 <NA>
## 1 1 1 1 2245
## [1] "Frequency table after encoding"
## s8q8_2. How much was this start-up capital? Magkano ang pangunang kapital na ito?
## 0 200 300 500 1000 1500 2000
## 1 2 3 5 5 3 1
## 2500 3000 3250 4500 5000 7000 8000
## 1 5 1 1 7 1 1
## 10000 15000 18000 20000 21500 28000 30000
## 4 3 1 2 1 1 1
## 37500 or more <NA>
## 1 2245
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q9_2)[na.exclude(mydata$s8q9_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q9_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q9_2. In the last 12 months what was spent on machinery or durable goods (e.g., tools,
## 0 100 300 400 570 900 1000 1100 1500 2000 2800 6200 18000 24000 31200 45000 <NA>
## 52 1 1 2 1 2 2 1 2 1 1 1 1 1 1 1 2225
## [1] "Frequency table after encoding"
## s8q9_2. In the last 12 months what was spent on machinery or durable goods (e.g., tools,
## 0 100 300 400 570 900 1000
## 52 1 1 2 1 2 2
## 1100 1500 2000 2800 6200 18000 24000
## 1 2 1 1 1 1 1
## 31200 40170 or more <NA>
## 1 1 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q12_2)[na.exclude(mydata$s8q12_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q12_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q12_2. Electricity Kuryente
## 0 20 500 600 1100 2400 31800 <NA>
## 65 1 1 1 1 1 1 2225
## [1] "Frequency table after encoding"
## s8q12_2. Electricity Kuryente
## 0 20 500 600 1100 2400 21510 or more
## 65 1 1 1 1 1 1
## <NA>
## 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q13_2)[na.exclude(mydata$s8q13_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q13_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q13_2. Salaries/Wages Pasahod/Suweldo
## 0 1800 <NA>
## 70 1 2225
## [1] "Frequency table after encoding"
## s8q13_2. Salaries/Wages Pasahod/Suweldo
## 0 1170 or more <NA>
## 70 1 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q14_2)[na.exclude(mydata$s8q14_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q14_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q14_2. Water Tubig
## 0 320 7200 <NA>
## 69 1 1 2225
## [1] "Frequency table after encoding"
## s8q14_2. Water Tubig
## 0 320 4792 or more <NA>
## 69 1 1 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q15_2)[na.exclude(mydata$s8q15_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q15_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q15_2. Transport Transportasyon
## 0 20 80 105 150 200 300 400 420 500 640 1152 1440 1500 2000 2400 2500 2880
## 43 1 1 1 1 2 1 2 1 1 1 1 1 2 1 3 1 1
## 4500 9000 9600 14400 19200 <NA>
## 1 1 2 1 1 2225
## [1] "Frequency table after encoding"
## s8q15_2. Transport Transportasyon
## 0 20 80 105 150 200 300
## 43 1 1 1 1 2 1
## 400 420 500 640 1152 1440 1500
## 2 1 1 1 1 1 2
## 2000 2400 2500 2880 4500 9000 9600
## 1 3 1 1 1 1 2
## 14400 17520 or more <NA>
## 1 1 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q16_2)[na.exclude(mydata$s8q16_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q16_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q16_2. Purchase of inputs, inventory, and products Pagbili ng mga inilalagay, imbentar
## 0 150 300 500 1000 1100 1200 3200 4500 5000 8400 15000 18000 42000 48000
## 47 1 1 3 1 1 1 1 1 2 1 1 1 1 1
## 72000 78000 96000 234960 <NA>
## 2 1 1 1 2227
## [1] "Frequency table after encoding"
## s8q16_2. Purchase of inputs, inventory, and products Pagbili ng mga inilalagay, imbentar
## 0 150 300 500 1000 1100 1200
## 47 1 1 3 1 1 1
## 3200 4500 5000 8400 15000 18000 42000
## 1 1 2 1 1 1 1
## 48000 72000 78000 96000 187713 or more <NA>
## 1 2 1 1 1 2227
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q17_2)[na.exclude(mydata$s8q17_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q17_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q17_2. Other costs (exclude machinery, tools, durables already mentioned) Iba pang gas
## 0 40 600 1500 5475 12800 72000 <NA>
## 65 1 1 1 1 1 1 2225
## [1] "Frequency table after encoding"
## s8q17_2. Other costs (exclude machinery, tools, durables already mentioned) Iba pang gas
## 0 40 600 1500 5475 12800 51280 or more
## 65 1 1 1 1 1 1
## <NA>
## 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q20_2)[na.exclude(mydata$s8q20_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q20_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q20_2. What was the total revenue received from this enterprise in the last 12 months?
## 0 300 350 500 1200 2700 3000 4000 4200 4800 5000 5200 6000
## 3 1 1 1 1 1 1 1 1 1 1 1 2
## 7000 8000 10000 12000 14400 15000 16800 18000 19200 20000 21000 21120 24000
## 1 2 2 1 7 1 1 2 1 1 1 1 4
## 28800 32360 36000 37500 38400 42000 43200 50400 54000 67200 72000 84000 108000
## 1 1 5 1 1 1 1 1 3 1 3 1 1
## 118286 144000 288000 360000 1080000 <NA>
## 1 1 1 1 1 2229
## [1] "Frequency table after encoding"
## s8q20_2. What was the total revenue received from this enterprise in the last 12 months?
## 0 300 350 500 1200 2700 3000
## 3 1 1 1 1 1 1
## 4000 4200 4800 5000 5200 6000 7000
## 1 1 1 1 1 2 1
## 8000 10000 12000 14400 15000 16800 18000
## 2 2 1 7 1 1 2
## 19200 20000 21000 21120 24000 28800 32360
## 1 1 1 1 4 1 1
## 36000 37500 38400 42000 43200 50400 54000
## 5 1 1 1 1 1 3
## 67200 72000 84000 108000 118286 144000 288000
## 1 3 1 1 1 1 1
## 360000 842400 or more <NA>
## 1 1 2229
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q21_2)[na.exclude(mydata$s8q21_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q21_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q21_2. What are the sales of this enterprise in an average month? Magkano ang benta ng
## 0 100 350 500 800 1000 1200 1250 1400 1500 1920 2000 2333 2600 2696
## 3 1 2 2 1 3 8 1 1 4 1 4 1 1 1
## 3000 3200 3280 3500 3600 4200 4500 5000 5400 5600 6000 8000 8400 12000 18000
## 6 1 1 1 1 2 1 1 1 1 4 1 1 2 1
## 19200 20000 24000 28800 30000 72000 90000 180000 <NA>
## 1 2 1 1 2 1 1 1 2227
## [1] "Frequency table after encoding"
## s8q21_2. What are the sales of this enterprise in an average month? Magkano ang benta ng
## 0 100 350 500 800 1000 1200
## 3 1 2 2 1 3 8
## 1250 1400 1500 1920 2000 2333 2600
## 1 1 4 1 4 1 1
## 2696 3000 3200 3280 3500 3600 4200
## 1 6 1 1 1 1 2
## 4500 5000 5400 5600 6000 8000 8400
## 1 1 1 1 4 1 1
## 12000 18000 19200 20000 24000 28800 30000
## 2 1 1 2 1 1 2
## 72000 90000 149399 or more <NA>
## 1 1 1 2227
percentile_99.5 <- floor(quantile(na.exclude(mydata$s8q23_2)[na.exclude(mydata$s8q23_2)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="s8q23_2", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## s8q23_2. In the last twelve months, what was the amount your household earned as profit o
## -36000 -3000 0 50 300 480 500 850 1000 1200 1500 2333 2700 3280 4000
## 1 1 7 1 1 1 2 1 1 2 1 1 1 1 3
## 4200 4380 4800 5000 6000 8000 8400 9600 9700 10000 14000 14100 14400 15000 16500
## 1 1 1 3 1 1 1 1 1 4 1 1 3 1 1
## 18000 19200 20000 21120 23200 24000 32360 36000 37000 38400 53100 54000 60000 66700 69600
## 1 1 1 1 1 2 1 3 1 1 1 1 1 1 1
## 71430 72000 160800 <NA>
## 1 1 1 2228
## [1] "Frequency table after encoding"
## s8q23_2. In the last twelve months, what was the amount your household earned as profit o
## -36000 -3000 0 50 300 480 500
## 1 1 7 1 1 1 2
## 850 1000 1200 1500 2333 2700 3280
## 1 1 2 1 1 1 1
## 4000 4200 4380 4800 5000 6000 8000
## 3 1 1 1 3 1 1
## 8400 9600 9700 10000 14000 14100 14400
## 1 1 1 4 1 1 3
## 15000 16500 18000 19200 20000 21120 23200
## 1 1 1 1 1 1 1
## 24000 32360 36000 37000 38400 53100 54000
## 2 1 3 1 1 1 1
## 60000 66700 69600 71430 72000 131052 or more <NA>
## 1 1 1 1 1 1 2228
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("s8q1",
"s8q2_1",
"s8q2_2")
capture_tables (indirect_PII)
# Recode those with very specific values.
break_ocup <- c(-999,-888,1,7,9,20,21,24,27,30,31,34,36,37,39,40,43,44)
labels_ocup <- c("No Response" = 1,
"Other: Specify" = 2,
"Other" = 3,
"Elementary occupations" = 4,
"Other" = 5,
"Service and sales workers" = 6,
"Service and sales workers" = 7,
"Elementary occupations "= 8,
"Craft and related trades workers "= 9,
"Craft and related trades workers"= 10,
"Elementary occupations"= 11,
"Elementary occupations"=12,
"Craft and related trades workers"=13,
"Service and sales workers"=14,
"Craft and related trades workers"=15,
"Elementary occupations"=16,
"Craft and related trades workers"=17,
"Craft and related trades workers"=18)
mydata <- ordinal_recode (variable="s8q2_1", break_points=break_ocup, missing=999999, value_labels=labels_ocup)
## [1] "Frequency table before encoding"
## s8q2_1. What is the nature of this enterprise ? Ano ang kalikasan ng negosyong ito?
## Earn a profit
## 7
## Make a loss
## 9
## Break even
## 2
## Street Work Including Scavenging And Begging
## 2
## Commercial Sexual Activity
## 1
## Hairdresser/Barber/Beautician
## 6
## Consumer store operator
## 71
## Charcoal Makers And Related Workers
## 8
## Food Processing and Related Trades Workers
## 23
## Handicraft Workers In Wood, Textile, Leather, Chemicals And Related Workers
## 49
## Hotel Housekeepers And Restaurant Services Workers
## 1
## Market Stall Vendors, Street Vendors And Related Workers
## 148
## Metal Molders, Welders, Sheet-Metal Workers, Structural-Metal Preparers And Related Trades Workers
## 3
## Motor Vehicle Drivers
## 7
## Printing Binding And Related Trades Workers
## 1
## Shoe Cleaning And Other Street Services Elementary Occupations
## 1
## Textile, Garment And Related Trades Workers
## 5
## Wood Treaters, Cabinet Makers And Related Trades Workers
## 1
## <NA>
## 1951
## recoded
## [-999,-888) [-888,1) [1,7) [7,9) [9,20) [20,21) [21,24) [24,27) [27,30) [30,31) [31,34) [34,36) [36,37)
## 1 0 0 7 0 0 0 0 0 0 0 0 0 0
## 2 0 0 9 0 0 0 0 0 0 0 0 0 0
## 3 0 0 2 0 0 0 0 0 0 0 0 0 0
## 7 0 0 0 2 0 0 0 0 0 0 0 0 0
## 9 0 0 0 0 1 0 0 0 0 0 0 0 0
## 20 0 0 0 0 0 6 0 0 0 0 0 0 0
## 21 0 0 0 0 0 0 71 0 0 0 0 0 0
## 24 0 0 0 0 0 0 0 8 0 0 0 0 0
## 27 0 0 0 0 0 0 0 0 23 0 0 0 0
## 30 0 0 0 0 0 0 0 0 0 49 0 0 0
## 31 0 0 0 0 0 0 0 0 0 0 1 0 0
## 34 0 0 0 0 0 0 0 0 0 0 0 148 0
## 36 0 0 0 0 0 0 0 0 0 0 0 0 3
## 37 0 0 0 0 0 0 0 0 0 0 0 0 0
## 39 0 0 0 0 0 0 0 0 0 0 0 0 0
## 40 0 0 0 0 0 0 0 0 0 0 0 0 0
## 43 0 0 0 0 0 0 0 0 0 0 0 0 0
## 44 0 0 0 0 0 0 0 0 0 0 0 0 0
## recoded
## [37,39) [39,40) [40,43) [43,44) [44,1e+06)
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 7 0 0 0 0 0
## 9 0 0 0 0 0
## 20 0 0 0 0 0
## 21 0 0 0 0 0
## 24 0 0 0 0 0
## 27 0 0 0 0 0
## 30 0 0 0 0 0
## 31 0 0 0 0 0
## 34 0 0 0 0 0
## 36 0 0 0 0 0
## 37 7 0 0 0 0
## 39 0 1 0 0 0
## 40 0 0 1 0 0
## 43 0 0 0 5 0
## 44 0 0 0 0 1
## [1] "Frequency table after encoding"
## s8q2_1. What is the nature of this enterprise ? Ano ang kalikasan ng negosyong ito?
## Other Elementary occupations Service and sales workers
## 19 152 84
## Elementary occupations Craft and related trades workers Craft and related trades workers
## 8 23 59
## <NA>
## 1951
## [1] "Inspect value labels and relabel as necessary"
## No Response Other: Specify Other
## 1 2 3
## Elementary occupations Other Service and sales workers
## 4 5 6
## Service and sales workers Elementary occupations Craft and related trades workers
## 7 8 9
## Craft and related trades workers Elementary occupations Elementary occupations
## 10 11 12
## Craft and related trades workers Service and sales workers Craft and related trades workers
## 13 14 15
## Elementary occupations Craft and related trades workers Craft and related trades workers
## 16 17 18mydata <- ordinal_recode (variable="s8q2_2", break_points=break_ocup, missing=999999, value_labels=labels_ocup)
## [1] "Frequency table before encoding"
## s8q2_2. What is the nature of this enterprise ? Ano ang kalikasan ng negosyong ito?
## Earn a profit
## 1
## Consumer store operator
## 4
## Food Processing and Related Trades Workers
## 1
## Handicraft Workers In Wood, Textile, Leather, Chemicals And Related Workers
## 7
## Market Stall Vendors, Street Vendors And Related Workers
## 20
## Metal Molders, Welders, Sheet-Metal Workers, Structural-Metal Preparers And Related Trades Workers
## 1
## Motor Vehicle Drivers
## 5
## <NA>
## 2257
## recoded
## [-999,-888) [-888,1) [1,7) [7,9) [9,20) [20,21) [21,24) [24,27) [27,30) [30,31) [31,34) [34,36) [36,37)
## 1 0 0 1 0 0 0 0 0 0 0 0 0 0
## 21 0 0 0 0 0 0 4 0 0 0 0 0 0
## 27 0 0 0 0 0 0 0 0 1 0 0 0 0
## 30 0 0 0 0 0 0 0 0 0 7 0 0 0
## 34 0 0 0 0 0 0 0 0 0 0 0 20 0
## 36 0 0 0 0 0 0 0 0 0 0 0 0 1
## 37 0 0 0 0 0 0 0 0 0 0 0 0 0
## recoded
## [37,39) [39,40) [40,43) [43,44) [44,1e+06)
## 1 0 0 0 0 0
## 21 0 0 0 0 0
## 27 0 0 0 0 0
## 30 0 0 0 0 0
## 34 0 0 0 0 0
## 36 0 0 0 0 0
## 37 5 0 0 0 0
## [1] "Frequency table after encoding"
## s8q2_2. What is the nature of this enterprise ? Ano ang kalikasan ng negosyong ito?
## Other Elementary occupations Service and sales workers
## 1 20 9
## Craft and related trades workers Craft and related trades workers <NA>
## 1 8 2257
## [1] "Inspect value labels and relabel as necessary"
## No Response Other: Specify Other
## 1 2 3
## Elementary occupations Other Service and sales workers
## 4 5 6
## Service and sales workers Elementary occupations Craft and related trades workers
## 7 8 9
## Craft and related trades workers Elementary occupations Elementary occupations
## 10 11 12
## Craft and related trades workers Service and sales workers Craft and related trades workers
## 13 14 15
## Elementary occupations Craft and related trades workers Craft and related trades workers
## 16 17 18Matching 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("s8q1whynoresponse",
"s8q2_other_1",
"s8q2whynoresponse_1",
"s8q3whynoresponse_1",
"s8q4whynoresponse_1",
"s8q5whynoresponse_1",
"s8q5awhynoresponse_1",
"s8q6whynoresponse_1",
"s8q7_other_1",
"s8q7whynoresponse_1",
"s8q8whynoresponse_1",
"s8q9whynoresponse_1",
"s8q10_other_1",
"s8q10whynoresponse_1",
"s8q11whynoresponse_1",
"s8q12whynoresponse_1",
"s8q13whynoresponse_1",
"s8q14whynoresponse_1",
"s8q15whynoresponse_1",
"s8q16whynoresponse_1",
"s8q17whynoresponse_1",
"s8q18_1",
"s8q19_other_1",
"s8q19whynoresponse_1",
"s8q20whynoresponse_1",
"s8q21whynoresponse_1",
"s8q22whynoresponse_1",
"s8q23whynoresponse_1",
"s8q2_other_2",
"s8q2whynoresponse_2",
"s8q3whynoresponse_2",
"s8q4whynoresponse_2",
"s8q5whynoresponse_2",
"s8q5awhynoresponse_2",
"s8q6whynoresponse_2",
"s8q7_other_2",
"s8q7whynoresponse_2",
"s8q8whynoresponse_2",
"s8q9whynoresponse_2",
"s8q10_other_2",
"s8q10whynoresponse_2",
"s8q11whynoresponse_2",
"s8q12whynoresponse_2",
"s8q13whynoresponse_2",
"s8q14whynoresponse_2",
"s8q15whynoresponse_2",
"s8q16whynoresponse_2",
"s8q17whynoresponse_2",
"s8q18_2",
"s8q19_other_2",
"s8q19whynoresponse_2",
"s8q20whynoresponse_2",
"s8q21whynoresponse_2",
"s8q22whynoresponse_2",
"s8q23whynoresponse_2",
"s8q2_other_3",
"s8q2whynoresponse_3",
"s8q3whynoresponse_3",
"s8q4whynoresponse_3",
"s8q5whynoresponse_3",
"s8q5awhynoresponse_3",
"s8q6whynoresponse_3",
"s8q7_other_3",
"s8q7whynoresponse_3",
"s8q8whynoresponse_3",
"s8q9whynoresponse_3",
"s8q10_other_3",
"s8q10whynoresponse_3",
"s8q11whynoresponse_3",
"s8q12whynoresponse_3",
"s8q13whynoresponse_3",
"s8q14whynoresponse_3",
"s8q15whynoresponse_3",
"s8q16whynoresponse_3",
"s8q17whynoresponse_3",
"s8q18_3",
"s8q19_other_3",
"s8q19whynoresponse_3",
"s8q20whynoresponse_3",
"s8q21whynoresponse_3",
"s8q22whynoresponse_3",
"s8q23whynoresponse_3")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
mydata$s8q2_other_1[215] <- "Managers"
mydata$s8q2_other_1[281] <- "Managers"
mydata$s8q2_other_1[322] <- "Managers"
mydata$s8q2_other_1[460] <- "Managers"
mydata$s8q2_other_1[480] <- "Managers"
mydata$s8q2_other_1[492] <- "Managers"
mydata$s8q2_other_1[497] <- "Managers"
mydata$s8q2_other_1[520] <- "Managers"
mydata$s8q2_other_1[541] <- "Managers"
mydata$s8q2_other_1[546] <- "Managers"
mydata$s8q2_other_1[553] <- "Managers"
mydata$s8q2_other_1[557] <- "Managers"
mydata$s8q2_other_1[573] <- "Managers"
mydata$s8q2_other_1[593] <- "Managers"
mydata$s8q2_other_1[627] <- "Managers"
mydata$s8q2_other_1[704] <- "Managers"
mydata$s8q2_other_1[735] <- "Managers"
mydata$s8q2_other_1[859] <- "Managers"
mydata$s8q2_other_1[869] <- "Managers"
mydata$s8q2_other_1[937] <- "Managers"
mydata$s8q2_other_1[944] <- "Managers"
mydata$s8q2_other_1[966] <- "Managers"
mydata$s8q2_other_1[1013] <- "Managers"
mydata$s8q2_other_1[1019] <- "Managers"
mydata$s8q2_other_1[1021] <- "Managers"
mydata$s8q2_other_1[1022] <- "Managers"
mydata$s8q2_other_1[1152] <- "Managers"
mydata$s8q2_other_1[1171] <- "Managers"
mydata$s8q2_other_1[1228] <- "Managers"
mydata$s8q2_other_1[1408] <- "Managers"
mydata$s8q2_other_1[1414] <- "Managers"
mydata$s8q2_other_1[1553] <- "Managers"
mydata$s8q2_other_1[1638] <- "Managers"
mydata$s8q2_other_1[1649] <- "Managers"
mydata$s8q2_other_1[1888] <- "Managers"
mydata$s8q2_other_1[1890] <- "Managers"
mydata$s8q2_other_1[1926] <- "Managers"
mydata$s8q2_other_1[1928] <- "Managers"
mydata$s8q2_other_1[1935] <- "Managers"
mydata$s8q2_other_1[1958] <- "Managers"
mydata$s8q2_other_1[2015] <- "Managers"
mydata$s8q2_other_1[2028] <- "Managers"
mydata$s8q2_other_1[2066] <- "Managers"
mydata$s8q2_other_1[2145] <- "Managers"
mydata$s8q2_other_1[2171] <- "Managers"
mydata$s8q2_other_1[2177] <- "Managers"
mydata$s8q2_other_1[2226] <- "Managers"
mydata$s8q2_other_1[2265] <- "Managers"
mydata$s8q2_other_1[2279] <- "Managers"
mydata$s8q2_other_1[2281] <- "Managers"
mydata$s8q2_other_1[577] <- "Managers"
mydata$s8q2_other_1[623] <- "Managers"
mydata$s8q2_other_1[1696] <- "Managers"
mydata$s8q2_other_1[2031] <- "Managers"
mydata$s8q2_other_1[2278] <- "Managers"
mydata$s8q2_other_1[800] <- "Craft and related trades workers"
mydata$s8q2_other_1[1150] <- "Craft and related trades workers"
mydata$s8q2_other_1[1293] <- "Craft and related trades workers"
mydata$s8q2_other_1[1296] <- "Craft and related trades workers"
mydata$s8q2_other_1[1302] <- "Craft and related trades workers"
mydata$s8q2_other_1[1543] <- "Craft and related trades workers"
mydata$s8q2_other_1[1565] <- "Craft and related trades workers"
mydata$s8q2_other_1[1599] <- "Craft and related trades workers"
mydata$s8q2_other_1[1604] <- "Craft and related trades workers"
mydata$s8q2_other_1[1606] <- "Craft and related trades workers"
mydata$s8q2_other_1[1610] <- "Craft and related trades workers"
mydata$s8q2_other_1[1697] <- "Craft and related trades workers"
mydata$s8q2_other_1[1699] <- "Craft and related trades workers"
mydata$s8q2_other_1[1707] <- "Craft and related trades workers"
mydata$s8q2_other_1[1711] <- "Craft and related trades workers"
mydata$s8q2_other_1[1770] <- "Craft and related trades workers"
mydata$s8q2_other_1[1783] <- "Craft and related trades workers"
mydata$s8q2_other_1[1785] <- "Craft and related trades workers"
mydata$s8q2_other_1[1789] <- "Craft and related trades workers"
mydata$s8q2_other_1[1819] <- "Craft and related trades workers"
mydata$s8q2_other_1[1166] <- "Craft and related trades workers"
mydata$s8q2_other_1[1862] <- "Craft and related trades workers"
mydata$s8q2_other_1[2201] <- "Craft and related trades workers"
mydata$s8q2_other_1[176] <- "Service and sales workers"
mydata$s8q2_other_1[192] <- "Service and sales workers"
mydata$s8q2_other_1[519] <- "Service and sales workers"
mydata$s8q2_other_1[526] <- "Service and sales workers"
mydata$s8q2_other_1[604] <- "Service and sales workers"
mydata$s8q2_other_1[645] <- "Service and sales workers"
mydata$s8q2_other_1[751] <- "Service and sales workers"
mydata$s8q2_other_1[752] <- "Service and sales workers"
mydata$s8q2_other_1[925] <- "Service and sales workers"
mydata$s8q2_other_1[928] <- "Service and sales workers"
mydata$s8q2_other_1[929] <- "Service and sales workers"
mydata$s8q2_other_1[1125] <- "Service and sales workers"
mydata$s8q2_other_1[1127] <- "Service and sales workers"
mydata$s8q2_other_1[1157] <- "Service and sales workers"
mydata$s8q2_other_1[1199] <- "Service and sales workers"
mydata$s8q2_other_1[1200] <- "Service and sales workers"
mydata$s8q2_other_1[1206] <- "Service and sales workers"
mydata$s8q2_other_1[1278] <- "Service and sales workers"
mydata$s8q2_other_1[1309] <- "Service and sales workers"
mydata$s8q2_other_1[1315] <- "Service and sales workers"
mydata$s8q2_other_1[1347] <- "Service and sales workers"
mydata$s8q2_other_1[1356] <- "Service and sales workers"
mydata$s8q2_other_1[1455] <- "Service and sales workers"
mydata$s8q2_other_1[1541] <- "Service and sales workers"
mydata$s8q2_other_1[1551] <- "Service and sales workers"
mydata$s8q2_other_1[1571] <- "Service and sales workers"
mydata$s8q2_other_1[1583] <- "Service and sales workers"
mydata$s8q2_other_1[1655] <- "Service and sales workers"
mydata$s8q2_other_1[1661] <- "Service and sales workers"
mydata$s8q2_other_1[1708] <- "Service and sales workers"
mydata$s8q2_other_1[1722] <- "Service and sales workers"
mydata$s8q2_other_1[1733] <- "Service and sales workers"
mydata$s8q2_other_1[1804] <- "Service and sales workers"
mydata$s8q2_other_1[1807] <- "Service and sales workers"
mydata$s8q2_other_1[1875] <- "Service and sales workers"
mydata$s8q2_other_1[1880] <- "Service and sales workers"
mydata$s8q2_other_1[1920] <- "Service and sales workers"
mydata$s8q2_other_1[1925] <- "Service and sales workers"
mydata$s8q2_other_1[1931] <- "Service and sales workers"
mydata$s8q2_other_1[2022] <- "Service and sales workers"
mydata$s8q2_other_1[2024] <- "Service and sales workers"
mydata$s8q2_other_1[2058] <- "Service and sales workers"
mydata$s8q2_other_1[2062] <- "Service and sales workers"
mydata$s8q2_other_1[2143] <- "Service and sales workers"
mydata$s8q2_other_1[2167] <- "Service and sales workers"
mydata$s8q2_other_1[2190] <- "Service and sales workers"
mydata$s8q2_other_1[2229] <- "Service and sales workers"
mydata$s8q2_other_1[2238] <- "Service and sales workers"
mydata$s8q2_other_1[2244] <- "Service and sales workers"
mydata$s8q2_other_1[2270] <- "Service and sales workers"
mydata$s8q2_other_1[1527] <- "Service and sales workers"
mydata$s8q2_other_1[1530] <- "Service and sales workers"
mydata$s8q2_other_1[1539] <- "Service and sales workers"
mydata$s8q2_other_1[1540] <- "Service and sales workers"
mydata$s8q2_other_1[1551] <- "Service and sales workers"
mydata$s8q2_other_1[1566] <- "Service and sales workers"
mydata$s8q2_other_1[1587] <- "Service and sales workers"
mydata$s8q2_other_1[1588] <- "Service and sales workers"
mydata$s8q2_other_1[1595] <- "Service and sales workers"
mydata$s8q2_other_1[1626] <- "Service and sales workers"
mydata$s8q2_other_1[1629] <- "Service and sales workers"
mydata$s8q2_other_1[1631] <- "Service and sales workers"
mydata$s8q2_other_1[1846] <- "Service and sales workers"
mydata$s8q2_other_1[1885] <- "Service and sales workers"
mydata$s8q2_other_1[1917] <- "Service and sales workers"
mydata$s8q2_other_1[2063] <- "Service and sales workers"
mydata$s8q2_other_1[2072] <- "Service and sales workers"
mydata$s8q2_other_1[2105] <- "Service and sales workers"
mydata$s8q2_other_1[2166] <- "Service and sales workers"
mydata$s8q2_other_1[2182] <- "Service and sales workers"
mydata$s8q2_other_1[1765] <- "Plant and machine operators and assemblers"
mydata$s8q2_other_1[1780] <- "Plant and machine operators and assemblers"
mydata$s8q2_other_1[1946] <- "Plant and machine operators and assemblers"
mydata$s8q2_other_1[2006] <- "Plant and machine operators and assemblers"
mydata$s8q2_other_1[1188] <- "Skilled agricultural, forestry and fishery workers"
mydata$s8q2_other_1[1704] <- "Skilled agricultural, forestry and fishery workers"
mydata$s8q2_other_1[1188] <- "Elementary occupations"
mydata$s8q2_other_1[1704] <- "Elementary occupations"
mydata$s8q2whynoresponse_1[1536] <- "Service and sales workers"
mydata$s8q2whynoresponse_1[1544] <- "Service and sales workers"
mydata$s8q2_other_2[101] <- "Service and sales workers"
mydata$s8q2_other_2[520] <- "Service and sales workers"
mydata$s8q2_other_2[1166] <- "Service and sales workers"
mydata$s8q2_other_2[1471] <- "Service and sales workers"
mydata$s8q2_other_2[1543] <- "Service and sales workers"
mydata$s8q2_other_2[1560] <- "Service and sales workers"
mydata$s8q2_other_2[1567] <- "Service and sales workers"
mydata$s8q2_other_2[1592] <- "Service and sales workers"
mydata$s8q2_other_2[1617] <- "Service and sales workers"
mydata$s8q2_other_2[1637] <- "Service and sales workers"
mydata$s8q2_other_2[1638] <- "Service and sales workers"
mydata$s8q2_other_2[1921] <- "Service and sales workers"
mydata$s8q2_other_2[2012] <- "Service and sales workers"
mydata$s8q2_other_2[2145] <- "Service and sales workers"
mydata$s8q2_other_2[2161] <- "Service and sales workers"
mydata$s8q2_other_2[2167] <- "Service and sales workers"
mydata$s8q2_other_2[2174] <- "Service and sales workers"
mydata$s8q2_other_2[2165] <- "Service and sales workers"
mydata$s8q2_other_2[2087] <- "Service and sales workers"
mydata$s8q2_other_2[577] <- "Managers"
mydata$s8q2_other_2[1158] <- "Managers"
mydata$s8q2_other_2[1324] <- "Managers"
mydata$s8q2_other_2[2171] <- "Managers"
mydata$s8q2_other_2[1231] <- "Craft and related trades workers"
mydata$s8q2_other_2[1295] <- "Craft and related trades workers"
mydata$s8q2_other_2[1336] <- "Craft and related trades workers"
mydata$s8q2_other_2[1391] <- "Elementary occupations"
mydata$s8q2_other_2[1866] <- "Elementary occupations"
mydata$s8q2_other_2[1931] <- "Skilled agricultural, forestry and fishery workers"
mydata$s8q2_other_2[1722] <- "Plant and machine operators and assemblers"
mydata$s8q7_other_1[541] <- "[Wholesale and retail trade]"
mydata$s8q7_other_1[798] <- "Income of spouse from [Wholesale and retail trade]"
mydata$s8q7_other_1[929] <- "Earnings from [Wholesale and retail trade]"
mydata$s8q7_other_1[1048] <- "Earnings from [Wholesale and retail trade]"
mydata$s8q7_other_1[1195] <- "From own child [name redacted]"
mydata$s8q7_other_1[1233] <- "[Service and sales workers]"
mydata$s8q7_other_1[1586] <- "[Technicians and associate professionals]"
mydata$s8q7_other_1[1862] <- "[language]"
mydata$s8q7_other_1[2036] <- "[repair of motor vehicles and motorcycles]"
mydata$s8q10_other_1[541] <- "Income from [Agriculture, forestry and fishing]"
mydata$s8q10_other_1[929] <- "Sales from the [Transportation and storage]"
mydata$s8q10_other_1[1195] <- "[Wholesale and retail trade]"
mydata$s8q10_other_1[1233] <- "Loans from [Service and sales workers]"
mydata$s8q18_1[541] <- "Charcoal [amount redacted] per month"
mydata$s8q18_1[929] <- "[amount redacted]"
mydata$s8q18_1[1195] <- "[amount redacted]"
mydata$s8q19_other_1[432] <- "Everyday sales from [Wholesale and retail trade]"
mydata$s8q19_other_1[541] <- "Sales from the [Wholesale and retail trade]"
mydata$s8q19_other_1[627] <- "Loan from friend, personal and [Wholesale and retail trade]"
mydata$s8q19_other_1[859] <- "[Wholesale and retail trade] sales"
mydata$s8q19_other_1[926] <- "Daily sales from [Wholesale and retail trade]."
mydata$s8q19whynoresponse_1[1372] <- "[language]"
mydata$s8q21whynoresponse_1[257] <- "Operating for [number redacted] days only, [amount redacted]"
mydata$s8q21whynoresponse_1[1389] <- "[amount redacted]"
mydata$s8q22whynoresponse_1[322] <- "The store started for 1 week only"
mydata$s8q23whynoresponse_1[865] <- "Breakeven only, but sometimes she can save [amount redacted] but not always"
mydata$s8q2whynoresponse_2[859] <- "[Manager]"
mydata$s8q2whynoresponse_2[1541] <- "[Transportation and storage]"
mydata$s8q7_other_2[1560] <- "[language]"
mydata$s8q10_other_2[1543] <- "Workmate - [Service and sales worker]"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)