DOL-ILAB SDC - Section_7
Pablo Diego-Rosell, PhD
2021-10-25
- 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_7" # !!!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
mydata$household_id <- zap_labels(mydata$household_id)Direct PII-team: Encode field team names
# !!!No Direct PII - teamSmall locations: Encode locations with pop <100,000 using random large numbers
# !!!Small locationsIndirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
# Top code high income/expenses to the 99.5 percentile
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s6q3)[na.exclude(mydata$m_s6q3)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s6q3", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s6q3. sFq4: How much did you spend in total purchasing land in the last 12 months? M
## -998 600 4500 8000 15000 24000 25000 30000 33000 40000 250000 <NA>
## 1 1 1 2 1 1 1 3 1 1 1 2271
## [1] "Frequency table after encoding"
## m_s6q3. sFq4: How much did you spend in total purchasing land in the last 12 months? M
## -998 600 4500 8000 15000 24000 25000 30000 33000 40000 236350 or more <NA>
## 1 1 1 2 1 1 1 3 1 1 1 2271
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s6q7)[na.exclude(mydata$m_s6q7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s6q7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s6q7. sFq10: If you were to purchase this land you received on the open market, how mu
## -998 25000 30000 50000 1e+05 150000 250000 4e+05 <NA>
## 6 1 1 2 2 2 1 1 2269
## [1] "Frequency table after encoding"
## m_s6q7. sFq10: If you were to purchase this land you received on the open market, how mu
## -998 25000 30000 50000 1e+05 150000 250000 388750 or more <NA>
## 6 1 1 2 2 2 1 1 2269
mydata$m_farm_expenses <- as.numeric(mydata$m_farm_expenses)
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_farm_expenses)[na.exclude(mydata$m_farm_expenses)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_farm_expenses", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_farm_expenses.
## 0 20 40 80 90 93 100 120 180 200 220 250 271 300 400 432 450 500 525 550 565 574 600 800 1000 1008 1025
## 1847 1 2 1 1 1 1 1 1 2 1 1 1 4 3 1 1 4 1 1 1 1 2 3 4 1 1
## 1050 1085 1100 1150 1200 1310 1350 1400 1500 1520 1570 1600 1628 1730 1825 1900 1950 2000 2005 2050 2150 2400 2412 2450 2500 2600 2736
## 1 1 2 1 3 1 2 1 2 1 1 3 1 1 1 1 1 9 1 2 1 1 1 1 1 1 1
## 2840 3000 3040 3050 3200 3208 3300 3390 3420 3460 3500 3570 3600 3610 3700 3750 3760 3800 3900 3950 4000 4016 4050 4060 4200 4206 4300
## 1 7 1 1 1 1 3 1 1 1 2 1 2 1 1 2 1 2 2 1 4 1 2 2 3 1 3
## 4400 4480 4500 4600 4800 4810 4870 5000 5080 5100 5200 5390 5400 5450 5600 5876 5900 5990 6000 6100 6200 6264 6300 6600 6720 6736 6800
## 1 1 1 1 2 1 1 3 1 1 1 1 1 1 2 1 1 1 4 1 1 1 2 2 1 1 2
## 6850 7000 7115 7200 7316 7440 7500 7580 7600 7650 7828 7840 7900 8000 8020 8025 8080 8380 8400 8460 8730 8750 8850 8970 9000 9030 9150
## 1 2 1 1 1 1 1 1 1 1 1 1 1 3 1 1 1 1 2 1 1 1 1 1 2 1 1
## 9360 9500 9600 10000 10200 10250 10267 10300 10390 10700 10900 11000 11150 11500 11600 11840 12000 12100 12158 12200 12400 12500 12600 12608 12800 12900 12990
## 1 1 1 2 1 1 1 2 1 2 1 4 1 1 2 1 6 1 1 1 1 1 1 1 1 1 1
## 13013 13165 13280 13500 13600 13800 14000 14400 14800 15000 15115 15400 15690 15800 16000 16100 16300 16801 17000 17300 17316 17500 17700 17780 17800 18000 18100
## 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2
## 18400 18720 18860 19000 19100 19300 19400 19550 20000 20600 20695 20710 21000 21200 21500 21550 21600 21800 21990 22000 22300 22400 23000 23988 24000 24200 24400
## 1 1 1 1 1 1 1 1 2 1 1 1 2 1 1 1 1 1 1 1 1 1 2 1 1 1 1
## 24500 24600 25000 25250 25360 25400 25436 25500 26000 26200 26250 26600 27000 27400 27500 27600 28302 28400 28680 28800 28950 29158 29350 29600 29800 30000 30500
## 1 1 3 1 1 1 1 1 2 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## 31900 32000 33000 33800 34100 34500 35000 36000 37300 38800 40000 40200 41316 41600 43200 44350 44400 45200 46400 46718 48400 49000 51000 51800 56900 57000 61800
## 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1
## 63000 64400 65150 65800 68000 68675 77000 81725 87460 87700 88600 91000 102000 132160 138000 158200 163600 282600 <NA>
## 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 58
## [1] "Frequency table after encoding"
## m_farm_expenses. 75917
## 0 20 40 80 90 93 100 120 180 200 220 250 271
## 1847 1 2 1 1 1 1 1 1 2 1 1 1
## 300 400 432 450 500 525 550 565 574 600 800 1000 1008
## 4 3 1 1 4 1 1 1 1 2 3 4 1
## 1025 1050 1085 1100 1150 1200 1310 1350 1400 1500 1520 1570 1600
## 1 1 1 2 1 3 1 2 1 2 1 1 3
## 1628 1730 1825 1900 1950 2000 2005 2050 2150 2400 2412 2450 2500
## 1 1 1 1 1 9 1 2 1 1 1 1 1
## 2600 2736 2840 3000 3040 3050 3200 3208 3300 3390 3420 3460 3500
## 1 1 1 7 1 1 1 1 3 1 1 1 2
## 3570 3600 3610 3700 3750 3760 3800 3900 3950 4000 4016 4050 4060
## 1 2 1 1 2 1 2 2 1 4 1 2 2
## 4200 4206 4300 4400 4480 4500 4600 4800 4810 4870 5000 5080 5100
## 3 1 3 1 1 1 1 2 1 1 3 1 1
## 5200 5390 5400 5450 5600 5876 5900 5990 6000 6100 6200 6264 6300
## 1 1 1 1 2 1 1 1 4 1 1 1 2
## 6600 6720 6736 6800 6850 7000 7115 7200 7316 7440 7500 7580 7600
## 2 1 1 2 1 2 1 1 1 1 1 1 1
## 7650 7828 7840 7900 8000 8020 8025 8080 8380 8400 8460 8730 8750
## 1 1 1 1 3 1 1 1 1 2 1 1 1
## 8850 8970 9000 9030 9150 9360 9500 9600 10000 10200 10250 10267 10300
## 1 1 2 1 1 1 1 1 2 1 1 1 2
## 10390 10700 10900 11000 11150 11500 11600 11840 12000 12100 12158 12200 12400
## 1 2 1 4 1 1 2 1 6 1 1 1 1
## 12500 12600 12608 12800 12900 12990 13013 13165 13280 13500 13600 13800 14000
## 1 1 1 1 1 1 1 1 1 1 1 1 2
## 14400 14800 15000 15115 15400 15690 15800 16000 16100 16300 16801 17000 17300
## 1 1 1 1 1 1 1 1 1 1 1 1 1
## 17316 17500 17700 17780 17800 18000 18100 18400 18720 18860 19000 19100 19300
## 1 1 1 1 1 2 2 1 1 1 1 1 1
## 19400 19550 20000 20600 20695 20710 21000 21200 21500 21550 21600 21800 21990
## 1 1 2 1 1 1 2 1 1 1 1 1 1
## 22000 22300 22400 23000 23988 24000 24200 24400 24500 24600 25000 25250 25360
## 1 1 1 2 1 1 1 1 1 1 3 1 1
## 25400 25436 25500 26000 26200 26250 26600 27000 27400 27500 27600 28302 28400
## 1 1 1 2 1 1 2 1 1 1 1 1 1
## 28680 28800 28950 29158 29350 29600 29800 30000 30500 31900 32000 33000 33800
## 1 1 1 1 1 1 1 1 1 1 1 1 1
## 34100 34500 35000 36000 37300 38800 40000 40200 41316 41600 43200 44350 44400
## 1 1 1 2 1 1 1 1 1 1 1 1 1
## 45200 46400 46718 48400 49000 51000 51800 56900 57000 61800 63000 64400 65150
## 2 1 1 1 1 1 1 1 1 1 1 1 1
## 65800 68000 68675 75917 or more <NA>
## 1 1 1 12 58
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s6q12)[na.exclude(mydata$m_s6q12)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s6q12", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s6q12. sFq16: How much in total would it have cost you to purchase those inputs with yo
## -998 0 2 5 10 15 20 25 30 35 40 45 50 55 60 70 75 80 90 100 120 150 180 200 220 250 260 290 300 400 450 458
## 31 13 2 1 31 1 43 5 15 4 19 4 96 2 12 7 4 5 2 105 3 13 2 28 1 7 1 1 19 4 2 1
## 500 600 650 700 750 800 850 900 998 1000 1100 1200 1250 1300 1400 1500 1600 1800 2000 2200 2250 2500 2652 3000 3600 3800 4000 4500 5000 5600 6000 6101
## 29 4 1 6 2 3 1 2 1 14 1 11 2 1 1 3 1 2 7 1 1 3 1 6 1 1 1 3 7 1 3 1
## 10000 13740 <NA>
## 2 1 1676
## [1] "Frequency table after encoding"
## m_s6q12. sFq16: How much in total would it have cost you to purchase those inputs with yo
## -998 0 2 5 10 15 20 25 30 35 40 45 50 55
## 31 13 2 1 31 1 43 5 15 4 19 4 96 2
## 60 70 75 80 90 100 120 150 180 200 220 250 260 290
## 12 7 4 5 2 105 3 13 2 28 1 7 1 1
## 300 400 450 458 500 600 650 700 750 800 850 900 998 1000
## 19 4 2 1 29 4 1 6 2 3 1 2 1 14
## 1100 1200 1250 1300 1400 1500 1600 1800 2000 2200 2250 2500 2652 3000
## 1 11 2 1 1 3 1 2 7 1 1 3 1 6
## 3600 3800 4000 4500 5000 5600 6000 6096 or more <NA>
## 1 1 1 3 7 1 3 4 1676
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s7q4)[na.exclude(mydata$m_s7q4)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s7q4", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s7q4. sGq7: How much did you spend? Magkano po ang inyong nagastos?
## -998 0 2000 3500 5000 6000 7000 7500 8000 10000 13000 14000 15000 16000 17500 18000 19000 20000 20400 21000 22000 24000 25000 27000 29000 30000 31000 35000 37000 44500 50000 70000
## 2 1 1 1 4 1 2 1 2 4 2 1 5 2 1 2 2 4 1 2 3 1 3 1 1 4 1 1 1 1 1 1
## <NA>
## 2225
## [1] "Frequency table after encoding"
## m_s7q4. sGq7: How much did you spend? Magkano po ang inyong nagastos?
## -998 0 2000 3500 5000 6000 7000 7500 8000 10000 13000 14000 15000
## 2 1 1 1 4 1 2 1 2 4 2 1 5
## 16000 17500 18000 19000 20000 20400 21000 22000 24000 25000 27000 29000 30000
## 2 1 2 2 4 1 2 3 1 3 1 1 4
## 31000 35000 37000 44500 50000 64099 or more <NA>
## 1 1 1 1 1 1 2225
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s7q7)[na.exclude(mydata$m_s7q7)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s7q7", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s7q7. sGq12: If you were to buy these livestock with your own resources, how much woul
## -998 14 300 1200 2000 3000 5000 6000 7000 8000 9000 10000 12000 13000 15000 16000 17000 17500 18000 20000 21000 22000 23000 25000 27000 28000 29000
## 4 1 1 1 1 1 7 2 3 7 1 21 3 3 30 4 2 1 8 37 1 1 1 8 1 1 1
## 30000 33000 35000 37000 40000 45000 48000 50000 69500 71000 80000 90000 115000 <NA>
## 11 1 10 1 8 2 1 9 1 1 2 1 1 2084
## [1] "Frequency table after encoding"
## m_s7q7. sGq12: If you were to buy these livestock with your own resources, how much woul
## -998 14 300 1200 2000 3000 5000 6000 7000 8000 9000 10000 12000
## 4 1 1 1 1 1 7 2 3 7 1 21 3
## 13000 15000 16000 17000 17500 18000 20000 21000 22000 23000 25000 27000 28000
## 3 30 4 2 1 8 37 1 1 1 8 1 1
## 29000 30000 33000 35000 37000 40000 45000 48000 50000 69500 71000 80000 90000 or more
## 1 11 1 10 1 8 2 1 9 1 1 2 2
## <NA>
## 2084
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s7q11)[na.exclude(mydata$m_s7q11)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s7q11", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s7q11. sGq18: How much did you spend? Magkano po ang inyong nagastos?
## -998 0 500 900 1000 1200 1300 1400 1500 1600 1700 1800 1900 2000 2200 2300 2350 2400 2500 2600 2700 2800 2900 3000 3400 3500 3600 3700 3850 3900 4000 4200
## 1 1 1 1 4 3 1 1 27 2 3 9 1 39 7 2 1 7 28 3 1 2 1 22 2 8 4 1 1 1 24 2
## 4400 4500 4600 4800 4900 5000 5200 5500 5610 5700 6000 6050 6100 6200 6300 6400 6500 6650 6800 7000 7200 7457 7500 8000 8400 9000 9200 10000 10200 10400 11000 11300
## 5 2 1 2 1 32 2 2 1 3 8 1 1 2 1 1 3 1 1 6 2 1 3 4 1 4 1 11 1 1 2 1
## 11500 11600 12000 12500 13000 13750 14000 14112 14600 15000 15400 16200 17000 20000 21900 22000 24000 28000 42500 53000 60000 70000 <NA>
## 1 1 2 2 1 1 1 1 1 3 1 1 1 2 1 1 2 1 1 1 1 1 1938
## [1] "Frequency table after encoding"
## m_s7q11. sGq18: How much did you spend? Magkano po ang inyong nagastos?
## -998 0 500 900 1000 1200 1300 1400 1500 1600 1700 1800 1900
## 1 1 1 1 4 3 1 1 27 2 3 9 1
## 2000 2200 2300 2350 2400 2500 2600 2700 2800 2900 3000 3400 3500
## 39 7 2 1 7 28 3 1 2 1 22 2 8
## 3600 3700 3850 3900 4000 4200 4400 4500 4600 4800 4900 5000 5200
## 4 1 1 1 24 2 5 2 1 2 1 32 2
## 5500 5610 5700 6000 6050 6100 6200 6300 6400 6500 6650 6800 7000
## 2 1 3 8 1 1 2 1 1 3 1 1 6
## 7200 7457 7500 8000 8400 9000 9200 10000 10200 10400 11000 11300 11500
## 2 1 3 4 1 4 1 11 1 1 2 1 1
## 11600 12000 12500 13000 13750 14000 14112 14600 15000 15400 16200 17000 20000
## 1 2 2 1 1 1 1 1 3 1 1 1 2
## 21900 22000 24000 28000 42500 53000 54889 or more <NA>
## 1 1 2 1 1 1 2 1938
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s7q14)[na.exclude(mydata$m_s7q14)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s7q14", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s7q14. sGq23: If you were to buy these livestock with your own resources, how much woul
## -998 600 800 1000 1200 1300 1500 1600 1800 2000 2200 2300 2400 2500 2600 2800 3000 3200 3500 3600 3900 4000 4400 4500 4800 5000 5100 5200 6000 6200 6400 6600
## 1 1 1 7 1 2 14 1 1 29 3 2 1 33 1 2 16 1 6 1 1 9 2 5 1 18 1 1 12 1 1 1
## 7000 7200 7500 8000 9000 9200 9500 10000 10800 11000 12000 13500 14000 14400 15000 16000 16800 17000 17500 20000 22500 23000 24000 27500 27600 45000 69500 75000 <NA>
## 2 1 6 6 3 1 1 13 2 2 3 1 1 1 1 3 1 1 2 6 1 1 1 1 1 1 1 1 2043
## [1] "Frequency table after encoding"
## m_s7q14. sGq23: If you were to buy these livestock with your own resources, how much woul
## -998 600 800 1000 1200 1300 1500 1600 1800 2000 2200 2300 2400
## 1 1 1 7 1 2 14 1 1 29 3 2 1
## 2500 2600 2800 3000 3200 3500 3600 3900 4000 4400 4500 4800 5000
## 33 1 2 16 1 6 1 1 9 2 5 1 18
## 5100 5200 6000 6200 6400 6600 7000 7200 7500 8000 9000 9200 9500
## 1 1 12 1 1 1 2 1 6 6 3 1 1
## 10000 10800 11000 12000 13500 14000 14400 15000 16000 16800 17000 17500 20000
## 13 2 2 3 1 1 1 1 3 1 1 2 6
## 22500 23000 24000 27500 27600 45000 64477 or more <NA>
## 1 1 1 1 1 1 2 2043
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s7q18)[na.exclude(mydata$m_s7q18)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s7q18", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s7q18. sGq29: How much did you spend? Magkano po ang inyong nagastos?
## -998 0 10 20 25 30 50 60 65 70 85 90 100 105 120 150 200 210 240 250 280 284 300 320 325 336 340 350 360 370 390 400
## 7 4 1 1 1 1 12 1 1 1 1 1 22 1 1 17 45 1 6 10 1 1 44 1 1 1 1 3 3 1 1 16
## 420 450 500 540 550 580 600 650 660 680 700 750 760 780 800 850 875 900 1000 1025 1180 1200 1500 1540 1584 1600 1790 1900 2000 2300 2500 2700
## 1 5 39 1 1 1 14 1 1 1 6 2 1 1 6 1 1 4 28 1 1 3 8 1 1 1 1 1 11 1 3 2
## 2940 3000 3300 4000 4500 5000 6000 6700 7000 10000 12000 25000 <NA>
## 1 6 1 1 2 3 1 1 2 1 1 1 1905
## [1] "Frequency table after encoding"
## m_s7q18. sGq29: How much did you spend? Magkano po ang inyong nagastos?
## -998 0 10 20 25 30 50 60 65 70 85 90 100
## 7 4 1 1 1 1 12 1 1 1 1 1 22
## 105 120 150 200 210 240 250 280 284 300 320 325 336
## 1 1 17 45 1 6 10 1 1 44 1 1 1
## 340 350 360 370 390 400 420 450 500 540 550 580 600
## 1 3 3 1 1 16 1 5 39 1 1 1 14
## 650 660 680 700 750 760 780 800 850 875 900 1000 1025
## 1 1 1 6 2 1 1 6 1 1 4 28 1
## 1180 1200 1500 1540 1584 1600 1790 1900 2000 2300 2500 2700 2940
## 1 3 8 1 1 1 1 1 11 1 3 2 1
## 3000 3300 4000 4500 5000 6000 6700 7000 10000 10210 or more <NA>
## 6 1 1 2 3 1 1 2 1 2 1905
percentile_99.5 <- floor(quantile(na.exclude(mydata$m_s7q21)[na.exclude(mydata$m_s7q21)!=999999], probs = c(0.995)))
mydata <- top_recode (variable="m_s7q21", break_point=percentile_99.5, missing=999999)## [1] "Frequency table before encoding"
## m_s7q21. sGq34: If you were to buy these birds with your own resources, how much would th
## -998 20 30 50 60 75 80 90 100 120 130 150 165 175 180 200 210 225 240 250 260 265 270 300 308 340 350 360 370 400 440 450
## 39 1 1 6 4 1 1 2 27 10 3 47 1 3 4 66 1 1 3 11 1 1 2 79 1 1 10 5 1 16 1 14
## 465 480 500 525 550 560 570 600 650 655 700 720 750 760 800 820 840 850 860 880 900 910 930 960 990 1000 1030 1050 1100 1120 1150 1200
## 1 2 67 1 2 1 1 35 4 1 13 1 13 1 18 1 1 1 1 1 9 1 1 1 1 68 1 2 4 1 1 16
## 1250 1260 1300 1350 1400 1500 1540 1550 1600 1650 1700 1800 1860 1900 2000 2100 2150 2200 2250 2400 2500 2510 2550 2700 2850 3000 3100 3380 3500 3600 3750 4000
## 3 1 5 3 1 30 1 1 2 1 1 6 1 1 26 2 1 3 1 2 11 1 1 1 2 16 1 2 4 2 1 5
## 4500 4800 5000 5100 5500 6000 6150 7000 7500 8000 9000 10000 10500 12000 15000 16000 22800 25000 30000 <NA>
## 2 1 14 1 1 7 1 1 2 1 1 3 2 2 1 1 1 1 1 1466
## [1] "Frequency table after encoding"
## m_s7q21. sGq34: If you were to buy these birds with your own resources, how much would th
## -998 20 30 50 60 75 80 90 100 120 130 150 165
## 39 1 1 6 4 1 1 2 27 10 3 47 1
## 175 180 200 210 225 240 250 260 265 270 300 308 340
## 3 4 66 1 1 3 11 1 1 2 79 1 1
## 350 360 370 400 440 450 465 480 500 525 550 560 570
## 10 5 1 16 1 14 1 2 67 1 2 1 1
## 600 650 655 700 720 750 760 800 820 840 850 860 880
## 35 4 1 13 1 13 1 18 1 1 1 1 1
## 900 910 930 960 990 1000 1030 1050 1100 1120 1150 1200 1250
## 9 1 1 1 1 68 1 2 4 1 1 16 3
## 1260 1300 1350 1400 1500 1540 1550 1600 1650 1700 1800 1860 1900
## 1 5 3 1 30 1 1 2 1 1 6 1 1
## 2000 2100 2150 2200 2250 2400 2500 2510 2550 2700 2850 3000 3100
## 26 2 1 3 1 2 11 1 1 1 2 16 1
## 3380 3500 3600 3750 4000 4500 4800 5000 5100 5500 6000 6150 7000
## 2 4 2 1 5 2 1 14 1 1 7 1 1
## 7500 8000 9000 10000 10500 12000 14729 or more <NA>
## 2 1 1 3 2 2 5 1466
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("m_s6q1",
"m_s6q2",
"m_s6q4",
"m_s6q5",
"m_s6q6",
"m_s6q8",
"m_s6q10",
"m_s6q11",
"m_s6q13",
"m_s7q1",
"m_s7q2",
"m_s7q3",
"m_s7q5",
"m_s7q6",
"m_s7q8",
"m_s7q9",
"m_s7q10",
"m_s7q12",
"m_s7q13",
"m_s7q15",
"m_s7q16",
"m_s7q17",
"m_s7q19",
"m_s7q20")
capture_tables (indirect_PII)
# Recode those with very specific values.
# !!!No very specific valuesMatching and crosstabulations: Run automated PII check
# !!!Insufficient demographic dataOpen-ends: review responses for any sensitive information, redact as necessary
# !!! Identify open-end variables here:
open_ends <- c("m_s6q4_other",
"m_s6q6_other",
"m_s6q8_warning",
"m_s6q13_other",
"m_endnote6",
"m_s7q3_other",
"m_s7q6_other",
"m_s7q10_other",
"m_s7q13_other",
"m_s7q17_other",
"m_s7q20_other",
"m_endnote7")
indirect_PII <- c("m_s6q4_other",
"m_s6q6_other",
"m_s6q8_warning",
"m_s6q13_other",
"m_endnote6",
"m_s7q3_other",
"m_s7q6_other",
"m_s7q10_other",
"m_s7q13_other",
"m_s7q17_other",
"m_s7q20_other",
"m_endnote7")
capture_tables(indirect_PII)
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
mydata$m_s6q4_other[1003] <- "[Tagalog]"
mydata$m_s6q4_other[1294] <- "[Tagalog]"
mydata$m_s6q13_other[260] <- "[Tagalog]"
mydata$m_s6q13_other[346] <- "[Tagalog]"
mydata$m_s6q13_other[352] <- "4 kls. Of Certified Seeds from Local Government of [municipality],(4500)"
mydata$m_s6q13_other[1468] <- "Department of Agriculture and UP [municipality]"
mydata$m_s7q6_other[423] <- "[Tagalog]"
mydata$m_s7q6_other[643] <- "[Tagalog]"
mydata$m_s7q6_other[1046] <- "[municipality] municipal government"
mydata$m_s7q6_other[1469] <- "[Tagalog]"
mydata$m_s7q10_other[281] <- "[Tagalog]"
mydata$m_s7q10_other[536] <- "Fond of [Tagalog]"
mydata$m_s7q13_other[546] <- "[Tagalog]"
mydata$m_s7q13_other[1029] <- "[Tagalog]"
mydata$m_s7q13_other[1938] <- "[Tagalog]"
mydata$m_s7q20_other[268] <- "[Tagalog]"
mydata$m_s7q20_other[897] <- "[Tagalog]"
mydata$m_s7q20_other[1030] <- "[Tagalog]"
mydata$m_s7q20_other[268] <- "[language], [name]"
mydata$m_endnote6[16] <- "Respondent said that even in baseline survey, they already spending [amount redacted] in cultivating crops. He can't recall that he's been asked regarding the matter."
mydata$m_endnote6[27] <- "They plant last [date] spend [amount redacted] but they have not plant yet becausr they're waiting for the rain before they can plant"
mydata$m_endnote6[28] <- "They plant last [date] and harvested [date], they havent plant yet so thry have no idea yet how much will cost them, so they cant compare if the expensed decrease or increase"
mydata$m_endnote6[53] <- "They plant once a year, every July, last [date] they spend [amount redacted] and they know yet if their expense is increased because they have' nt plant yet for this year."
mydata$m_endnote6[62] <- "They did'nt cultivate crops last 2016 because 2 of the household member got sick, they cultivate crops this year but corn only and spend [amount redacted] for seeds and fertilizer, they are waiting for the rain so that they can cultivate crops (rice grain)"
mydata$m_endnote6[70] <- "Bought seed at [amount redacted] only for their owned consumption"
mydata$m_endnote6[92] <- "He told that during baseline survey their expenses in their crops is only [amount redacted], he include their not on crops in the [amount redacted] expenses last baseline."
mydata$m_endnote6[110] <- "On the baseline survey their expenses is [amount redacted] while for Last 12 months their expenses estimated [amount redacted]"
mydata$m_endnote6[156] <- "The farm they cultivitang is owned by 4 household (4siblings), so every year, different household is cultivating the farm. Their turn to cultivate was last [date]."
mydata$m_endnote6[173] <- "[name] planted vegetables at their backyard for their consumption, she is not using any fertilizer, no expenses, as well as the seeds were given by friends and neighbors"
mydata$m_endnote6[190] <- "Bought the seed for croping, spend [amount redacted]"
mydata$m_endnote6[215] <- "He recieved half sack of fertilizer from DA He spent [amount redacted] for 2 corn farm, and he spent [amount redacted] for the rice field last [date] which is not included in the baseline."
mydata$m_endnote6[218] <- "Last 12 months they spend [amount redacted] in land cultivation , the expenses increased on labor from [amount redacted] to [amount redacted] plus free meal. The money they spend half of it came from loan to a friend and half of it from their savings"
mydata$m_endnote6[219] <- "Respondent only spend [amount redacted] pesos for the seeds since they were not yet started cultivating the farm. She said, that they will just be starting on Suday."
mydata$m_endnote6[223] <- "Respondent planted eggplant which she spent [amount redacted]."
mydata$m_endnote6[236] <- "They planted 'camote' last April and spent [amount redacted] for it."
mydata$m_endnote6[240] <- "Respondent said that fro, [amount redacted], they already spend [amount redacted] pesos for cultivating crops."
mydata$m_endnote6[257] <- "Seed- [amount redacted], fertilizers- [amount redacted], pesticides-[amount redacted], insecticides- [amount redacted]. Total [amount redacted]"
mydata$m_endnote6[259] <- "[amount redacted] seed of eggplant and sili"
mydata$m_endnote6[261] <- "[Language]"
mydata$m_endnote6[262] <- " During te baseline survey she remembered that shemention to the enumerator that thay have spent [amount redacted] in cultivating their crops, and for the last 12 months they have spent the same amount"
mydata$m_endnote6[280] <- "They planted rice even before the baseline interview but was not stated the amount they spent even though he said it to the interviewer based from him. They bought the land last 2002. For tbe last 12 mos they have spent [amount redacted]"
mydata$m_endnote6[306] <- "Fertilizer-[amount redacted], Rutubator-[amount redacted], Pagpapatanim- [amount redacted], Tagapag bunot-[amount redacted], Tagasuyod- [amount redacted], Pamatay nang damu- [amount redacted], Snail-[amount redacted], Crude- [amount redacted] Total of [amount redacted] pesos."
mydata$m_endnote6[317] <- "FERTILIZER- [amount redacted], SEEDS- [amount redacted], PESTICIDES-[amount redacted], LABOR [amount redacted] INSECTICIDES-[amount redacted] total=[amount redacted]"
mydata$m_endnote6[327] <- "She said that they spwnt [amount redacted] during the last year before basekine interview for cultivating plants. Last October they have spent [amount redacted] for the cultivation of their corn crop."
mydata$m_endnote6[337] <- "Fertilizers=[amount redacted], Seed=[amount redacted], Pesticides=[amount redacted], Nag Araro=[amount redacted], Nagtanim=[amount redacted]. Total of [amount redacted]."
mydata$m_endnote6[343] <- "Seed [amount redacted], abono [amount redacted], pamatay nang damo [amount redacted], =[amount redacted]"
mydata$m_endnote6[377] <- "Abono=[amount redacted], patubig=[amount redacted], Pesticides= [amount redacted], Seeds= [amount redacted] TOTAL OF [amount redacted]. the seeds must be gave to them by Department of Agriculture."
mydata$m_endnote6[378] <- "Abono=[amount redacted], fertilizer - [amount redacted], pesticides= [amount redacted], laborer [amount redacted], expenses in the sides of the farm (seeds given by the neigborhood) [amount redacted] Total =[amount redacted]."
mydata$m_endnote6[403] <- "The seeds or plant they gather in the other farm is the what they used in planting, the amount of [amount redacted] in the sFq13 was the amount of the fertilizer."
mydata$m_endnote6[420] <- "Last year the respondent cultivated [amount redacted] sq.m for his cassava plants. And now his lot rented for 3 years with [amount redacted]. He owns only backyard gardening."
mydata$m_endnote6[468] <- "[Language]"
mydata$m_endnote6[571] <- "The household loaned the [amount redacted] and the saving of [amount redacted] in using to plant"
mydata$m_endnote6[599] <- " The DOLE gave them amounted [amount redacted] pesos that they sell, and the [amount redacted] pesos which comes from their savings, with the total of [amount redacted] pesos"
mydata$m_endnote6[617] <- "[Language]"
mydata$m_endnote6[646] <- "Last year the household cultivated 2 ha. and spent [amount redacted] and now spent [amount redacted] for 1 ha"
mydata$m_endnote6[651] <- "Respondent said that they received a pack of seeds from Brgy. [barangay name] for them to plant."
mydata$m_endnote6[678] <- "[amount redacted] from DSWD AAthat they reinvested in planting im the farm and [amount redacted] from micro credit loan and the rest is [amount redacted] from teir savings"
mydata$m_endnote6[679] <- "They gather wild plant and transfered from the farm to their backyard. [language]"
mydata$m_endnote6[715] <- "July 2016 start to plant on rented land"
mydata$m_endnote6[937] <- "She only purchased land with the amount [amount redacted], installment of [amount redacted] every month. She already done for installment in 10 months."
mydata$m_endnote6[949] <- "[Language]"
mydata$m_endnote6[1062] <- "[amount redacted] ung fertilizer, [amount redacted] seeds"
mydata$m_endnote6[1064] <- "Since last survey the household already has a [amount redacted] pesos expenses for 12 months."
mydata$m_endnote6[1126] <- "The farm they used were owned by [name] and his siblings. So they shared in expenses and same with the crops they harvest."
mydata$m_endnote6[1140] <- "Last year they spend [amount redacted] pesosi order to cultivate crops. They spend the same in this year"
mydata$m_endnote6[1283] <- "Contradicting the data collected last year, the respondent said that they were spending [amount redacted] every year for all the inputs needed to cultivate crops."
mydata$m_endnote6[1303] <- "The respondant told me the they spent roughly [amount redacted] pesos every year to cultivate crops and they spend stayed same in the last 12 months but in sFq12 stated that the household spent [amount redacted] in the previous year"
mydata$m_endnote6[1307] <- "The respondent spent roughly [amount redacted] in the last 12 months in cultivating crops ([amount redacted] in fertilizer and [amount redacted] in labor)and almost a half of it [amount redacted] pesos they spent before the baseline survey but in SFQ12 in baseline survey they spent [amount redacted] pesos"
mydata$m_endnote6[1379] <- "[amount redacted] was just her share to the expenses, because her children who already have their own family or household were also sharing to the expenses,"
mydata$m_endnote6[1468] <- "Their crops is organic, by the help of UP [UP name] they are planting vegetables. They gets free 4 bags of seeds in the department of Agriculture."
mydata$m_endnote6[2067] <- "The cost was decreased because he has only [amount redacted]tupongs of land from the [amount redacted]hectares [language]"
mydata$m_endnote6[2073] <- "[amount redacted] for the 1year expenses"
mydata$m_endnote7[16] <- "The [amount redacted] chicks were purchased by the twins, [name], using their salary from the hardware."
mydata$m_endnote7[18] <- "The household's goat gave birth to [amount redacted] new goats. And they also had a new chicks but respondent don't have an idea of the amount of the chicks."
mydata$m_endnote7[36] <- "Respondent said the rooster will cost [amount redacted] if they will bought it but when she asked her husband, she changed her response in favor of her husband's response. Even though, I still took the respondent's 1st response."
mydata$m_endnote7[80] <- "They had purchased [amount redacted] pigs but it was last June 2016."
mydata$m_endnote7[86] <- "They have [amount redacted] goats"
mydata$m_endnote7[110] <- "They have [amount redacted] chicken, but the goat they are care is not their ownd"
mydata$m_endnote7[112] <- "The household bought [amount redacted] piglets last November 2016 but they killed the [amount redacted] pigs last March 2017 and sold the meat."
mydata$m_endnote7[219] <- "Respondent has no idea of the amount of the new [amount redacted] native chicks."
mydata$m_endnote7[240] <- "Respondent can't tell the amount of the [amount redacted] native chicks because according to her, those were not been sold."
mydata$m_endnote7[287] <- "Baseline respondent said that the sales from the in kind of KASAMA (DOLE) was the main source, they purchase the pig worth [amount redacted]"
mydata$m_endnote7[306] <- "[amount redacted] is for 12 person she's the one who've got those piggery. It is an association so [amount redacted] piggery for 12 person belongs the sow and the piglet. For ducks-[amount redacted], chickens-[amount redacted]."
mydata$m_endnote7[332] <- "They dont acquired any new animals. The cow that they have was have an arrangement, the owner give them [amount redacted] cow after giving birth as paid for them."
mydata$m_endnote7[349] <- "In livestock they have also additional [amount redacted] goat (kid) worth [amount redacted]"
mydata$m_endnote7[364] <- "[language]"
mydata$m_endnote7[376] <- "Respondent said that they bought 2 pig worth 5000 pesos, from the sales of the in kind transfer of Dole Integrated Livelihood and Emergency Program in which they are now tending."
mydata$m_endnote7[454] <- "3 is for [amount redacted], she buys [amount redacted] but the 2 of them died."
mydata$m_endnote7[475] <- "The large livestock is the carabao and the amount is [amount redacted], the price is low because the household head or [name] bought it to his sibling"
mydata$m_endnote7[500] <- "[language]"
mydata$m_endnote7[872] <- "The worth of 2 chikens is [amount redacted]"
mydata$m_endnote7[1029] <- "[language]"
mydata$m_endnote7[1045] <- "Government transfer came mayor [name]"
mydata$m_endnote7[1050] <- "As per the respondent ,on his computation its only costing [amount redacted] pesos only the value of the pigs that they received from DOLE's livelihood program"
mydata$m_endnote7[1127] <- "Recently he bought [amount redacted] pcs. Of 45 days chicks."
mydata$m_endnote7[1213] <- "Even before the DOLE gives [amount redacted] piglets to them, the household already tending pigs."
mydata$m_endnote7[1245] <- "[language]"
mydata$m_endnote7[1253] <- "Their relatives gave the pig, they made it as patener(mother pig), then during the interview they have [amount redacted] piglets."
mydata$m_endnote7[1285] <- "[name] traded his quail to the mother Duck of his cousin, then the mother duck produces a (male) duck. But mostly of its eggs were stolen."
mydata$m_endnote7[1317] <- "[language]"
mydata$m_endnote7[1351] <- "[amount redacted] inakay, ducklings"
mydata$m_endnote7[1357] <- "They bought [amount redacted]pcs. Of 45days chicken last March 5, then cooked it last May for the fiesta."
mydata$m_endnote7[1362] <- "They have [amount redacted] ducks and [amount redacted] chicker. Her elder son takee care of them"
mydata$m_endnote7[1472] <- "The [amount redacted] goats were fro another household, they only have an agreement that when it gave birth, it will be parted to each household."
mydata$m_endnote7[1486] <- "4Ps gave them [amount redacted] 'baby goat'"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)