DOL-ILAB SDC - bhsection4
Pablo Diego-Rosell, PhD
2021-04-23
- Setup filenames, 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, data, functions and create dictionary for dataset review
filename <- "bhsection4" # !!!Update filename
functions_vers <- "functions_1.7.R" # !!!Update helper functions file
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
!!!Include relevant variables, but check their population size first to confirm they are <100,000
dropvars <- c("dise")
mydata <- mydata[!names(mydata) %in% dropvars]
locvars <- c("q006_block_id", "q007_vlg_id")
mydata <- encode_location (variables= locvars, missing=999999)## [1] "Frequency table before encoding"
## q006_block_id. 6 Block Code
## 1 2 3 4 5 6 7 8 9 <NA>
## 201 157 199 419 101 197 146 432 539 36
## [1] "Frequency table after encoding"
## q006_block_id. 6 Block Code
## 279 280 281 282 283 284 285 286 287 <NA>
## 432 157 201 197 199 539 146 101 419 36
## [1] "Frequency table before encoding"
## q007_vlg_id. 7 Village Code
## 1 2 3 4 5 6 7 9 10 11 12 13 15 16 17 18 19 20
## 17 16 17 16 20 31 29 17 15 20 26 24 15 18 21 19 18 20
## 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38
## 30 23 18 18 32 27 28 18 14 15 24 24 23 16 29 18 17 23
## 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
## 27 17 16 18 17 28 21 25 21 20 18 17 17 18 27 25 27 19
## 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74
## 17 22 13 24 23 18 19 18 30 16 19 22 28 14 16 21 16 24
## 75 76 77 78 80 81 82 83 84 85 87 88 89 90 91 92 93 94
## 23 18 23 30 31 17 22 17 18 13 18 22 16 19 20 19 21 14
## 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
## 21 23 28 22 26 19 25 21 16 19 17 31 16 28 22 17 21 26
## 113 114 115 116 117 118 119 <NA>
## 15 24 19 16 24 23 17 36
## [1] "Frequency table after encoding"
## q007_vlg_id. 7 Village Code
## 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
## 20 19 18 17 18 21 15 24 16 15 23 18 23 18 23 25 21 16
## 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
## 17 16 26 21 25 21 17 21 17 16 18 31 18 16 21 24 26 27
## 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
## 27 22 28 20 18 29 19 30 24 28 27 20 16 22 18 24 24 14
## 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336
## 15 30 16 13 13 19 20 22 15 16 14 17 23 18 18 23 18 25
## 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354
## 16 17 18 16 28 19 23 17 29 28 17 30 17 31 18 19 20 17
## 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
## 21 28 32 24 19 17 19 22 22 17 19 24 26 18 31 21 22 14
## 373 374 375 376 377 378 379 <NA>
## 17 27 16 19 23 17 23 36Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
# Focus on variables with a "Lowest Freq" in dictionary of 30 or less.
break_age <- c(0,5,10,15,20)
labels_age <- c("0-4" =1,
"5-9" =2,
"10-14" =3,
"15-19"=4,
"20 or older"=5)
mydata <- ordinal_recode (variable="q404_ch_age", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## q404_ch_age. 404 How old was the girl when she died?
## 0 1 2 3 4 5 6 7 8 9 11 12 14 <NA>
## 1 4 2 2 2 6 2 2 4 3 2 2 1 2394
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 0 1 0 0 0 0
## 1 4 0 0 0 0
## 2 2 0 0 0 0
## 3 2 0 0 0 0
## 4 2 0 0 0 0
## 5 0 6 0 0 0
## 6 0 2 0 0 0
## 7 0 2 0 0 0
## 8 0 4 0 0 0
## 9 0 3 0 0 0
## 11 0 0 2 0 0
## 12 0 0 2 0 0
## 14 0 0 1 0 0
## [1] "Frequency table after encoding"
## q404_ch_age. 404 How old was the girl when she died?
## 0-4 5-9 10-14 <NA>
## 11 17 5 2394
## [1] "Inspect value labels and relabel as necessary"
## 0-4 5-9 10-14 15-19 20 or older
## 1 2 3 4 5mydata <- ordinal_recode (variable="q405_age", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## q405_age. 405 How old was the girl when her mother stopped living in the same residence as
## 0 1 2 3 4 5 6 7 8 9 10 11 12 14 <NA>
## 7 21 14 7 5 13 5 7 9 17 12 7 6 1 2296
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 0 7 0 0 0 0
## 1 21 0 0 0 0
## 2 14 0 0 0 0
## 3 7 0 0 0 0
## 4 5 0 0 0 0
## 5 0 13 0 0 0
## 6 0 5 0 0 0
## 7 0 7 0 0 0
## 8 0 9 0 0 0
## 9 0 17 0 0 0
## 10 0 0 12 0 0
## 11 0 0 7 0 0
## 12 0 0 6 0 0
## 14 0 0 1 0 0
## [1] "Frequency table after encoding"
## q405_age. 405 How old was the girl when her mother stopped living in the same residence as
## 0-4 5-9 10-14 <NA>
## 54 51 26 2296
## [1] "Inspect value labels and relabel as necessary"
## 0-4 5-9 10-14 15-19 20 or older
## 1 2 3 4 5mydata <- ordinal_recode (variable="q411_age_died", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## q411_age_died. 411 How old was the girl when he died?
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 38 <NA>
## 11 13 9 13 8 13 12 10 17 14 14 7 2 1 2 1 2280
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 0 11 0 0 0 0
## 1 13 0 0 0 0
## 2 9 0 0 0 0
## 3 13 0 0 0 0
## 4 8 0 0 0 0
## 5 0 13 0 0 0
## 6 0 12 0 0 0
## 7 0 10 0 0 0
## 8 0 17 0 0 0
## 9 0 14 0 0 0
## 10 0 0 14 0 0
## 11 0 0 7 0 0
## 12 0 0 2 0 0
## 13 0 0 1 0 0
## 14 0 0 2 0 0
## 38 0 0 0 0 1
## [1] "Frequency table after encoding"
## q411_age_died. 411 How old was the girl when he died?
## 0-4 5-9 10-14 20 or older <NA>
## 54 66 26 1 2280
## [1] "Inspect value labels and relabel as necessary"
## 0-4 5-9 10-14 15-19 20 or older
## 1 2 3 4 5mydata <- ordinal_recode (variable="q411_age_died", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## q411_age_died. 411 How old was the girl when he died?
## 0-4 5-9 10-14 20 or older <NA>
## 54 66 26 1 2280
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 1 54 0 0 0 0
## 2 66 0 0 0 0
## 3 26 0 0 0 0
## 5 0 1 0 0 0
## [1] "Frequency table after encoding"
## q411_age_died. 411 How old was the girl when he died?
## 0-4 5-9 <NA>
## 146 1 2280
## [1] "Inspect value labels and relabel as necessary"
## 0-4 5-9 10-14 15-19 20 or older
## 1 2 3 4 5mydata <- ordinal_recode (variable="q412_age", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## q412_age. 412 How old was the girl when her father stopped living in the same residence as
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 <NA>
## 40 46 13 5 9 19 17 12 21 28 28 23 14 3 4 2 2143
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 0 40 0 0 0 0
## 1 46 0 0 0 0
## 2 13 0 0 0 0
## 3 5 0 0 0 0
## 4 9 0 0 0 0
## 5 0 19 0 0 0
## 6 0 17 0 0 0
## 7 0 12 0 0 0
## 8 0 21 0 0 0
## 9 0 28 0 0 0
## 10 0 0 28 0 0
## 11 0 0 23 0 0
## 12 0 0 14 0 0
## 13 0 0 3 0 0
## 14 0 0 4 0 0
## 15 0 0 0 2 0
## [1] "Frequency table after encoding"
## q412_age. 412 How old was the girl when her father stopped living in the same residence as
## 0-4 5-9 10-14 15-19 <NA>
## 113 97 72 2 2143
## [1] "Inspect value labels and relabel as necessary"
## 0-4 5-9 10-14 15-19 20 or older
## 1 2 3 4 5Indirect 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("q407_emp_status",
"q414_emp_status",
"q415_rel",
"q418i_othr_allowed",
"q429_obstacles",
"q430g_sharecar_cur",
"q430j_other",
"q430j_other_specify",
"q430j_other_cur",
"q430j_other_fut",
"q431h_othr_nec")
capture_tables (indirect_PII)Matching and crosstabulations: Run automated PII check
# !!! No direct demographic variables available in datasetOpen-ends: review responses for any sensitive information, redact as necessary
open_ends <- c("q415_rel_othr",
"q422_change",
"q423_future_plans",
"q431h_othr_specify")
report_open (list_open_ends = open_ends)
mydata <- mydata[!names(mydata) %in% open_ends] # Drop as actually verbatim data in local languageGPS data: Displace
# !!! No GPS dataSave processed data in Stata and SPSS format
Adds "_PU" (Public Use) to the end of the name
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)