DOL-ILAB SDC - Section_4
Pablo Diego-Rosell, PhD
2021-10-18
- 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_4" # !!!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
# !!!Include any Direct PII variables
dropvars <- c("eh_s4q3")
mydata <- mydata[!names(mydata) %in% dropvars]Direct PII-team: Encode field team names
# !!!No Direct PII - teamSmall locations: Encode locations with pop <100,000 using random large numbers
# !!!No Small locationsIndirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
# Focus on variables with a "Lowest Freq" in dictionary of 30 or less.
# Recode education attainment of adults to reduce risk of re-identification
haven_table("eh_s4q30")## eh_s4q30. Q180: What was the highest level of education 's mother completed?
## -998 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
## 73 98 133 180 258 281 1375 275 379 291 35 5 4 1820 24 46 49 96 84 57 8 134 2
## 24 25 96 <NA>
## 1 43 96 3haven_table("eh_s4q41")## eh_s4q41. Q191: What was the highest level of education 's father completed?
## -998 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 24
## 165 105 177 317 390 284 1510 198 366 271 23 4 5 1397 55 64 72 51 85 28 3 120 7
## 25 96 <NA>
## 57 93 3break_edu <- c(-998, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 13, 15, 16, 17, 18, 19, 21, 25, 96)
labels_edu <- c("-998"=1,
"1"=2,
"2"=3,
"3"=4,
"4"=5,
"5"=6,
"6"=7,
"7"=8,
"8"=9,
"9"=10,
"10 or 11 or 12"=11,
"13 or 14"=12,
"15"=13,
"16"=14,
"17"=15,
"18"=16,
"19 or 20"=17,
"21 or 22 or 24"=18,
"25"=19,
"96"=20)
mydata <- ordinal_recode (variable="eh_s4q30", break_points=break_edu, missing=999999, value_labels=labels_edu)
## [1] "Frequency table before encoding"
## eh_s4q30. Q180: What was the highest level of education 's mother completed?
## -998 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
## 73 98 133 180 258 281 1375 275 379 291 35 5 4 1820 24 46 49 96 84 57 8 134 2
## 24 25 96 <NA>
## 1 43 96 3
## recoded
## [-998,1) [1,2) [2,3) [3,4) [4,5) [5,6) [6,7) [7,8) [8,9) [9,10) [10,13) [13,15) [15,16) [16,17) [17,18)
## -998 73 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 1 0 98 0 0 0 0 0 0 0 0 0 0 0 0 0
## 2 0 0 133 0 0 0 0 0 0 0 0 0 0 0 0
## 3 0 0 0 180 0 0 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 258 0 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 281 0 0 0 0 0 0 0 0 0
## 6 0 0 0 0 0 0 1375 0 0 0 0 0 0 0 0
## 7 0 0 0 0 0 0 0 275 0 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 0 379 0 0 0 0 0 0
## 9 0 0 0 0 0 0 0 0 0 291 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0 0 35 0 0 0 0
## 11 0 0 0 0 0 0 0 0 0 0 5 0 0 0 0
## 12 0 0 0 0 0 0 0 0 0 0 4 0 0 0 0
## 13 0 0 0 0 0 0 0 0 0 0 0 1820 0 0 0
## 14 0 0 0 0 0 0 0 0 0 0 0 24 0 0 0
## 15 0 0 0 0 0 0 0 0 0 0 0 0 46 0 0
## 16 0 0 0 0 0 0 0 0 0 0 0 0 0 49 0
## 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0 96
## 18 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 19 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 20 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 21 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 22 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 24 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 25 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 96 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## recoded
## [18,19) [19,21) [21,25) [25,96) [96,1e+06)
## -998 0 0 0 0 0
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## 7 0 0 0 0 0
## 8 0 0 0 0 0
## 9 0 0 0 0 0
## 10 0 0 0 0 0
## 11 0 0 0 0 0
## 12 0 0 0 0 0
## 13 0 0 0 0 0
## 14 0 0 0 0 0
## 15 0 0 0 0 0
## 16 0 0 0 0 0
## 17 0 0 0 0 0
## 18 84 0 0 0 0
## 19 0 57 0 0 0
## 20 0 8 0 0 0
## 21 0 0 134 0 0
## 22 0 0 2 0 0
## 24 0 0 1 0 0
## 25 0 0 0 43 0
## 96 0 0 0 0 96
## [1] "Frequency table after encoding"
## eh_s4q30. Q180: What was the highest level of education 's mother completed?
## -998 1 2 3 4 5 6
## 73 98 133 180 258 281 1375
## 7 8 9 10 or 11 or 12 13 or 14 15 16
## 275 379 291 44 1844 46 49
## 17 18 19 or 20 21 or 22 or 24 25 96 <NA>
## 96 84 65 137 43 96 3
## [1] "Inspect value labels and relabel as necessary"
## -998 1 2 3 4 5 6
## 1 2 3 4 5 6 7
## 7 8 9 10 or 11 or 12 13 or 14 15 16
## 8 9 10 11 12 13 14
## 17 18 19 or 20 21 or 22 or 24 25 96
## 15 16 17 18 19 20break_edu <- c(-998, 1, 2, 3, 4, 5, 6, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19, 21, 25, 96)
labels_edu <- c("-998"=1,
"1"=2,
"2"=3,
"3"=4,
"4"=5,
"5"=6,
"6"=7,
"7"=8,
"8"=9,
"9 or 10 or 11 or 12"=10,
"13"=11,
"14"=12,
"15"=13,
"16"=14,
"17"=15,
"18"=16,
"19 or 20"=17,
"21 or 24"=18,
"25"=19,
"96"=20)
mydata <- ordinal_recode (variable="eh_s4q41", break_points=break_edu, missing=999999, value_labels=labels_edu)
## [1] "Frequency table before encoding"
## eh_s4q41. Q191: What was the highest level of education 's father completed?
## -998 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 24
## 165 105 177 317 390 284 1510 198 366 271 23 4 5 1397 55 64 72 51 85 28 3 120 7
## 25 96 <NA>
## 57 93 3
## recoded
## [-998,1) [1,2) [2,3) [3,4) [4,5) [5,6) [6,7) [7,8) [8,9) [9,13) [13,14) [14,15) [15,16) [16,17) [17,18)
## -998 165 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 1 0 105 0 0 0 0 0 0 0 0 0 0 0 0 0
## 2 0 0 177 0 0 0 0 0 0 0 0 0 0 0 0
## 3 0 0 0 317 0 0 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 390 0 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 284 0 0 0 0 0 0 0 0 0
## 6 0 0 0 0 0 0 1510 0 0 0 0 0 0 0 0
## 7 0 0 0 0 0 0 0 198 0 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 0 366 0 0 0 0 0 0
## 9 0 0 0 0 0 0 0 0 0 271 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0 23 0 0 0 0 0
## 11 0 0 0 0 0 0 0 0 0 4 0 0 0 0 0
## 12 0 0 0 0 0 0 0 0 0 5 0 0 0 0 0
## 13 0 0 0 0 0 0 0 0 0 0 1397 0 0 0 0
## 14 0 0 0 0 0 0 0 0 0 0 0 55 0 0 0
## 15 0 0 0 0 0 0 0 0 0 0 0 0 64 0 0
## 16 0 0 0 0 0 0 0 0 0 0 0 0 0 72 0
## 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0 51
## 18 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 19 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 20 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 21 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 24 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 25 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 96 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## recoded
## [18,19) [19,21) [21,25) [25,96) [96,1e+06)
## -998 0 0 0 0 0
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## 7 0 0 0 0 0
## 8 0 0 0 0 0
## 9 0 0 0 0 0
## 10 0 0 0 0 0
## 11 0 0 0 0 0
## 12 0 0 0 0 0
## 13 0 0 0 0 0
## 14 0 0 0 0 0
## 15 0 0 0 0 0
## 16 0 0 0 0 0
## 17 0 0 0 0 0
## 18 85 0 0 0 0
## 19 0 28 0 0 0
## 20 0 3 0 0 0
## 21 0 0 120 0 0
## 24 0 0 7 0 0
## 25 0 0 0 57 0
## 96 0 0 0 0 93
## [1] "Frequency table after encoding"
## eh_s4q41. Q191: What was the highest level of education 's father completed?
## -998 1 2 3 4
## 165 105 177 317 390
## 5 6 7 8 9 or 10 or 11 or 12
## 284 1510 198 366 303
## 13 14 15 16 17
## 1397 55 64 72 51
## 18 19 or 20 21 or 24 25 96
## 85 31 127 57 93
## <NA>
## 3
## [1] "Inspect value labels and relabel as necessary"
## -998 1 2 3 4
## 1 2 3 4 5
## 5 6 7 8 9 or 10 or 11 or 12
## 6 7 8 9 10
## 13 14 15 16 17
## 11 12 13 14 15
## 18 19 or 20 21 or 24 25 96
## 16 17 18 19 20Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
# !!!Include relevant variables in list below (Indirect PII - Categorical, and Ordinal if not processed yet)
indirect_PII <- c("eh_s4q4",
"eh_s4q32",
"eh_s4q33",
"eh_s4q43")
capture_tables (indirect_PII)
# Recode those with very specific values.
break_ocup <- c(-998, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 14, 22, 33, 34, 35, 39, 44, 62, 64, 65, 67, 68, 73, 75, 76, 77, 99)
labels_ocup <- c("Don't know"=1,
"Street and related sales and service workers"=2,
"Street and related sales and service workers"=3,
"Street and related sales and service workers"=4,
"Street and related sales and service workers"=5,
"Street and related sales and service workers"=6,
"Street and related sales and service workers"=7,
"Personal care workers"=8,
"Cleaners and helpers"=9,
"Cleaners and helpers"=10,
"Cleaners and helpers"=11,
"Food processing, wood working, garment and other craft and related trades workers"=12,
"Food processing, wood working, garment and other craft and related trades workers"=13,
"Agricultural, forestry and fishery labourers"=14,
"Agricultural, forestry and fishery labourers"=15,
"Agricultural, forestry and fishery labourers"=16,
"Agricultural, forestry and fishery labourers"=17,
"Agricultural, forestry and fishery labourers"=18,
"Food preparation assistants"=19,
"Refuse workers and other elementary workers"=20,
"Street and related sales and service workers"=21,
"Customer services clerks"=22,
"Personal service workers"=23,
"Electrical and electronic trades workers"=24,
"Food processing, wood working, garment and other craft and related trades workers"=25,
"Student"=26,
"Cleaners and helpers"=27,
"Street and related sales and service workers"=28,
"Other: Specify "=29)
mydata <- ordinal_recode (variable="eh_s4q33", break_points=break_ocup, missing=999999, value_labels=labels_ocup)
## [1] "Frequency table before encoding"
## eh_s4q33. Q183: What is 's Mother currently doing in that location? Ano an
## Don't know
## 84
## A sari-sari store
## 7
## Rice vending
## 1
## Fish vending
## 6
## Raw Food vending (not including rice or fish)
## 3
## Prepared/cooked food vending (carinderia)
## 6
## Other vending besides sari-sari store or food vending ( such as other street ven
## 6
## Hairdresser/Barber/Beautician
## 11
## Laundry services
## 4
## Cleaning Services, including domestic work
## 223
## Garbage collection
## 1
## Tailoring or dressmaking
## 9
## Bag making
## 2
## Fishing
## 1
## Rice Farming
## 2
## Other Farming
## 8
## Cultivating crops in a garden plot
## 3
## Other livestock related sources of income
## 2
## Food processing
## 1
## Guard
## 2
## Consumer store operator (not sari-sari store)
## 1
## Cashiers, Tellers And Related Clerks
## 3
## Hotel Housekeepers And Restaurant Services Workers
## 8
## Machinery Mechanics, Fitters And Related Trades Workers
## 2
## Textile, Garment And Related Trades Workers
## 2
## Student
## 1
## Principally performs chores and other unpaid household services for own househol
## 90
## Street food vending
## 5
## Other: Specify
## 123
## <NA>
## 5233
## recoded
## [-998,1) [1,2) [2,3) [3,4) [4,5) [5,6) [6,7) [7,8) [8,9) [9,10) [10,12) [12,14) [14,22) [22,33) [33,34)
## -998 84 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 1 0 7 0 0 0 0 0 0 0 0 0 0 0 0 0
## 2 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 3 0 0 0 6 0 0 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 3 0 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 6 0 0 0 0 0 0 0 0 0
## 6 0 0 0 0 0 0 6 0 0 0 0 0 0 0 0
## 7 0 0 0 0 0 0 0 11 0 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 0 4 0 0 0 0 0 0
## 9 0 0 0 0 0 0 0 0 0 223 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
## 12 0 0 0 0 0 0 0 0 0 0 0 9 0 0 0
## 14 0 0 0 0 0 0 0 0 0 0 0 0 2 0 0
## 22 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## 33 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2
## 34 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 35 0 0 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 0 0
## 44 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 62 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 64 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 65 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 67 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 68 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 73 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 75 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 76 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 77 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 99 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## recoded
## [34,35) [35,39) [39,44) [44,62) [62,64) [64,65) [65,67) [67,68) [68,73) [73,75) [75,76) [76,77) [77,99)
## -998 0 0 0 0 0 0 0 0 0 0 0 0 0
## 1 0 0 0 0 0 0 0 0 0 0 0 0 0
## 2 0 0 0 0 0 0 0 0 0 0 0 0 0
## 3 0 0 0 0 0 0 0 0 0 0 0 0 0
## 4 0 0 0 0 0 0 0 0 0 0 0 0 0
## 5 0 0 0 0 0 0 0 0 0 0 0 0 0
## 6 0 0 0 0 0 0 0 0 0 0 0 0 0
## 7 0 0 0 0 0 0 0 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 0 0 0 0 0 0
## 9 0 0 0 0 0 0 0 0 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0 0 0 0 0
## 12 0 0 0 0 0 0 0 0 0 0 0 0 0
## 14 0 0 0 0 0 0 0 0 0 0 0 0 0
## 22 0 0 0 0 0 0 0 0 0 0 0 0 0
## 33 0 0 0 0 0 0 0 0 0 0 0 0 0
## 34 8 0 0 0 0 0 0 0 0 0 0 0 0
## 35 0 3 0 0 0 0 0 0 0 0 0 0 0
## 39 0 0 2 0 0 0 0 0 0 0 0 0 0
## 44 0 0 0 1 0 0 0 0 0 0 0 0 0
## 62 0 0 0 0 2 0 0 0 0 0 0 0 0
## 64 0 0 0 0 0 1 0 0 0 0 0 0 0
## 65 0 0 0 0 0 0 3 0 0 0 0 0 0
## 67 0 0 0 0 0 0 0 8 0 0 0 0 0
## 68 0 0 0 0 0 0 0 0 2 0 0 0 0
## 73 0 0 0 0 0 0 0 0 0 2 0 0 0
## 75 0 0 0 0 0 0 0 0 0 0 1 0 0
## 76 0 0 0 0 0 0 0 0 0 0 0 90 0
## 77 0 0 0 0 0 0 0 0 0 0 0 0 5
## 99 0 0 0 0 0 0 0 0 0 0 0 0 0
## recoded
## [99,1e+06)
## -998 0
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## 7 0
## 8 0
## 9 0
## 10 0
## 12 0
## 14 0
## 22 0
## 33 0
## 34 0
## 35 0
## 39 0
## 44 0
## 62 0
## 64 0
## 65 0
## 67 0
## 68 0
## 73 0
## 75 0
## 76 0
## 77 0
## 99 123
## [1] "Frequency table after encoding"
## eh_s4q33. Q183: What is 's Mother currently doing in that location? Ano an
## Don't know
## 84
## Street and related sales and service workers
## 35
## Personal care workers
## 11
## Cleaners and helpers
## 318
## Food processing, wood working, garment and other craft and related trades workers
## 13
## Agricultural, forestry and fishery labourers
## 16
## Food preparation assistants
## 1
## Refuse workers and other elementary workers
## 2
## Customer services clerks
## 3
## Personal service workers
## 8
## Electrical and electronic trades workers
## 2
## Student
## 1
## Other: Specify
## 123
## <NA>
## 5233
## [1] "Inspect value labels and relabel as necessary"
## Don't know
## 1
## Street and related sales and service workers
## 2
## Street and related sales and service workers
## 3
## Street and related sales and service workers
## 4
## Street and related sales and service workers
## 5
## Street and related sales and service workers
## 6
## Street and related sales and service workers
## 7
## Personal care workers
## 8
## Cleaners and helpers
## 9
## Cleaners and helpers
## 10
## Cleaners and helpers
## 11
## Food processing, wood working, garment and other craft and related trades workers
## 12
## Food processing, wood working, garment and other craft and related trades workers
## 13
## Agricultural, forestry and fishery labourers
## 14
## Agricultural, forestry and fishery labourers
## 15
## Agricultural, forestry and fishery labourers
## 16
## Agricultural, forestry and fishery labourers
## 17
## Agricultural, forestry and fishery labourers
## 18
## Food preparation assistants
## 19
## Refuse workers and other elementary workers
## 20
## Street and related sales and service workers
## 21
## Customer services clerks
## 22
## Personal service workers
## 23
## Electrical and electronic trades workers
## 24
## Food processing, wood working, garment and other craft and related trades workers
## 25
## Student
## 26
## Cleaners and helpers
## 27
## Street and related sales and service workers
## 28
## Other: Specify
## 29Matching 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("eh_s4q6",
"eh_s4q10",
"eh_s4q12",
"eh_s4q14",
"eh_s4q22",
"eh_s4q24",
"eh_s4q31",
"eh_s4q34",
"eh_s4q37",
"eh_s4q42",
"eh_s4q45")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number
mydata$eh_s4q34[35] <- "Cleaners and helpers"
mydata$eh_s4q34[72] <- "Cleaners and helpers"
mydata$eh_s4q34[114] <- "Personal care workers"
mydata$eh_s4q34[115] <- "Personal care workers"
mydata$eh_s4q34[133] <- "Personal service workers"
mydata$eh_s4q34[134] <- "Personal service workers"
mydata$eh_s4q34[135] <- "Personal service workers"
mydata$eh_s4q34[136] <- "Personal service workers"
mydata$eh_s4q34[157] <- "Protective services workers"
mydata$eh_s4q34[158] <- "Protective services workers"
mydata$eh_s4q34[361] <- "Street and related sales and service workers"
mydata$eh_s4q34[553] <- "Street and related sales and service workers"
mydata$eh_s4q34[601] <- "Business and administration associate professionals"
mydata$eh_s4q34[833] <- "Cleaners and helpers"
mydata$eh_s4q34[834] <- "Cleaners and helpers"
mydata$eh_s4q34[883] <- "Other"
mydata$eh_s4q34[884] <- "Other"
mydata$eh_s4q34[1047] <- "Food processing, wood working, garment and other craft and related trades workers"
mydata$eh_s4q34[1049] <- "Food processing, wood working, garment and other craft and related trades workers"
mydata$eh_s4q34[1203] <- "Personal care workers"
mydata$eh_s4q34[1204] <- "Personal care workers"
mydata$eh_s4q34[1252] <- "Personal care workers"
mydata$eh_s4q34[1264] <- "Personal care workers"
mydata$eh_s4q34[1265] <- "Personal care workers"
mydata$eh_s4q34[1266] <- "Personal care workers"
mydata$eh_s4q34[1361] <- "Other"
mydata$eh_s4q34[1392] <- "Cleaners and helpers"
mydata$eh_s4q34[1416] <- "Personal care workers"
mydata$eh_s4q34[1417] <- "Personal care workers"
mydata$eh_s4q34[1422] <- "Cleaners and helpers"
mydata$eh_s4q34[1487] <- "Cleaners and helpers"
mydata$eh_s4q34[1488] <- "Cleaners and helpers"
mydata$eh_s4q34[1527] <- "Personal care workers"
mydata$eh_s4q34[1528] <- "Personal care workers"
mydata$eh_s4q34[1677] <- "Cleaners and helpers"
mydata$eh_s4q34[1702] <- "Sales workers"
mydata$eh_s4q34[1713] <- "Cleaners and helpers"
mydata$eh_s4q34[1716] <- "Cleaners and helpers"
mydata$eh_s4q34[1804] <- "Other"
mydata$eh_s4q34[1805] <- "Other"
mydata$eh_s4q34[1839] <- "Other"
mydata$eh_s4q34[1840] <- "Other"
mydata$eh_s4q34[1841] <- "Other"
mydata$eh_s4q34[1842] <- "Other"
mydata$eh_s4q34[1867] <- "Teaching professionals"
mydata$eh_s4q34[1909] <- "[language]"
mydata$eh_s4q34[1951] <- "other"
mydata$eh_s4q34[1952] <- "other"
mydata$eh_s4q34[1953] <- "[language]"
mydata$eh_s4q34[2019] <- "Other"
mydata$eh_s4q34[2072] <- "Personal care workers"
mydata$eh_s4q34[2073] <- "Personal care workers"
mydata$eh_s4q34[2074] <- "Personal care workers"
mydata$eh_s4q34[2075] <- "Personal care workers"
mydata$eh_s4q34[2102] <- "Other"
mydata$eh_s4q34[2103] <- "Other"
mydata$eh_s4q34[2112] <- "Other"
mydata$eh_s4q34[2174] <- "[language]"
mydata$eh_s4q34[2239] <- "Labourers in mining, construction, manufacturing and transport"
mydata$eh_s4q34[2380] <- "Electrical and electronic trades workers"
mydata$eh_s4q34[2581] <- "Other"
mydata$eh_s4q34[2592] <- "Business and administration associate professionals"
mydata$eh_s4q34[2637] <- "Cleaners and helpers"
mydata$eh_s4q34[2644] <- "Cleaners and helpers"
mydata$eh_s4q34[2697] <- "Cleaners and helpers"
mydata$eh_s4q34[2724] <- "Cleaners and helpers"
mydata$eh_s4q34[2725] <- "Cleaners and helpers"
mydata$eh_s4q34[2834] <- "Cleaners and helpers"
mydata$eh_s4q34[2835] <- "Cleaners and helpers"
mydata$eh_s4q34[2836] <- "Cleaners and helpers"
mydata$eh_s4q34[2878] <- "Labourers in mining, construction, manufacturing and transport"
mydata$eh_s4q34[2889] <- "other"
mydata$eh_s4q34[2907] <- "Customer services clerks"
mydata$eh_s4q34[2910] <- "Cleaners and helpers"
mydata$eh_s4q34[2911] <- "Cleaners and helpers"
mydata$eh_s4q34[2912] <- "Cleaners and helpers"
mydata$eh_s4q34[2913] <- "Cleaners and helpers"
mydata$eh_s4q34[2914] <- "Cleaners and helpers"
mydata$eh_s4q34[2915] <- "Cleaners and helpers"
mydata$eh_s4q34[2916] <- "Cleaners and helpers"
mydata$eh_s4q34[2957] <- "Other"
mydata$eh_s4q34[2994] <- "Labourers in mining, construction, manufacturing and transport"
mydata$eh_s4q34[3050] <- "Labourers in mining, construction, manufacturing and transport"
mydata$eh_s4q34[3085] <- "other"
mydata$eh_s4q34[3086] <- "other"
mydata$eh_s4q34[3098] <- "Personal care workers"
mydata$eh_s4q34[3151] <- "Cleaners and helpers"
mydata$eh_s4q34[3152] <- "Cleaners and helpers"
mydata$eh_s4q34[3164] <- "Cleaners and helpers"
mydata$eh_s4q34[3165] <- "Cleaners and helpers"
mydata$eh_s4q34[3195] <- "Other"
mydata$eh_s4q34[3220] <- "Electrical and electronic trades workers"
mydata$eh_s4q34[3221] <- "Electrical and electronic trades workers"
mydata$eh_s4q34[3222] <- "Electrical and electronic trades workers"
mydata$eh_s4q34[3228] <- "Other"
mydata$eh_s4q34[3578] <- "Other"
mydata$eh_s4q34[3582] <- "Street and related sales and service workers"
mydata$eh_s4q34[3766] <- "other"
mydata$eh_s4q34[3767] <- "other"
mydata$eh_s4q34[3769] <- "other"
mydata$eh_s4q34[4137] <- "Personal care workers"
mydata$eh_s4q34[4139] <- "Other"
mydata$eh_s4q34[4141] <- "Other"
mydata$eh_s4q34[4595] <- "Labourers in mining, construction, manufacturing and transport"
mydata$eh_s4q34[4786] <- "Personal care workers"
mydata$eh_s4q34[4916] <- "Other"
mydata$eh_s4q34[5050] <- "Cleaners and helpers"
mydata$eh_s4q34[5051] <- "Cleaners and helpers"
mydata$eh_s4q34[5060] <- "Other"
mydata$eh_s4q34[5070] <- "Cleaners and helpers"
mydata$eh_s4q34[5071] <- "Cleaners and helpers"
mydata$eh_s4q34[5072] <- "Cleaners and helpers"
mydata$eh_s4q34[5135] <- "Labourers in mining, construction, manufacturing and transport"
mydata$eh_s4q34[5162] <- "Personal service workers"
mydata$eh_s4q34[5163] <- "Personal service workers"
mydata$eh_s4q34[5179] <- "Personal care workers"
mydata$eh_s4q34[5180] <- "Personal care workers"
mydata$eh_s4q34[5181] <- "Personal care workers"
mydata$eh_s4q34[5244] <- "other"
mydata$eh_s4q34[5250] <- "Food processing, wood working, garment and other craft and related trades workers"
mydata$eh_s4q34[5278] <- "Teaching professionals"
mydata$eh_s4q34[5723] <- "Personal care workers"
mydata$eh_s4q34[5743] <- "Electrical and electronic trades workers"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)