DOL-ILAB SDC - ecsection5_relabelled
Pablo Diego-Rosell, PhD
2021-06-22
- 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
- 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 <- "ecsection5_relabelled" # !!!Update filename
functions_vers <- "functions_1.7.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-team
Small locations: Encode locations with pop <100,000 using random large numbers
dropvars <- c("dise")
mydata <- mydata[!names(mydata) %in% dropvars]
locvars <- c("q002_blckid", "q003_vill_id")
mydata <- encode_location (variables= locvars, missing=999999)## [1] "Frequency table before encoding"
## q002_blckid. 002 Unique block ID
## 1 2 3 4 5 6 7 8 9
## 206 167 188 412 96 192 158 424 544
## [1] "Frequency table after encoding"
## q002_blckid. 002 Unique block ID
## 279 280 281 282 283 284 285 286 287
## 206 544 167 424 96 188 412 158 192
## [1] "Frequency table before encoding"
## q003_vill_id. 003 Village ID
## 1 2 3 4 5 6 7 8 9 10 11 12 13 15 16 17 18 19 20
## 17 16 17 16 20 29 29 16 15 13 17 26 24 14 18 21 18 18 20
## 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
## 30 23 18 18 32 25 27 17 14 13 24 26 21 16 28 19 15 22 27
## 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
## 16 16 18 16 27 21 22 21 20 17 17 17 18 27 25 27 19 13 21
## 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
## 12 24 19 17 19 18 30 16 19 21 25 13 16 21 16 23 22 18 23
## 78 80 81 82 83 84 85 87 88 89 90 91 92 93 94 95 96 97 98
## 30 30 16 21 17 17 13 18 22 16 19 20 18 20 14 20 24 28 21
## 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
## 26 17 25 20 15 19 16 31 13 28 22 17 21 27 15 24 20 14 24
## 118 119 120 121 122 <NA>
## 22 21 13 13 10 1
## [1] "Frequency table after encoding"
## q003_vill_id. 003 Village ID
## 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627
## 18 16 24 20 21 16 27 13 20 18 19 17 23 17 10 21 19 18 24
## 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646
## 24 16 27 23 32 21 28 19 16 16 30 25 21 20 27 21 28 18 29
## 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665
## 25 25 16 17 20 24 17 31 15 21 17 13 26 26 22 30 12 14 18
## 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
## 27 14 15 17 23 21 24 22 22 20 21 21 27 17 16 30 13 24 19
## 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703
## 20 18 17 16 16 29 16 21 22 18 16 14 16 19 18 17 28 19 25
## 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
## 13 13 21 13 17 15 20 22 27 30 22 16 13 14 20 26 17 19 18
## 723 724 725 726 727 <NA>
## 18 15 18 17 13 1Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values
!!! No Indirect PII - Ordinal
Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values
indirect_PII <- c("q504_areu_currmarrd",
"q506o_others_entry",
"q506o_other_access")
capture_tables (indirect_PII)
# Recode those with very specific values. !!! No action, low risk
val_labels(mydata$q506o_others_entry)## Motor cycle/ Bike Water heater Fan/cooler Tape recorder Tractor
## 1 2 3 4 5
## Boxes Books Not applicable Not applicable
## 6 7 999 NAbreaks <- c(1:7)
labels <- c("Small motor vehicle" = 1,
"Water heater" = 2,
"Fan/cooler" = 3,
"Tape recorder" = 4,
"Large Motor Vehicle" = 5,
"Boxes" = 6,
"Books" = 7)
mydata2 <- ordinal_recode (variable="q506o_others_entry",
break_points=breaks,
missing=999999,
value_labels=labels)
## [1] "Frequency table before encoding"
## q506o_others_entry. 506o. Other item (specify)
## Motor cycle/ Bike Water heater Fan/cooler Tape recorder Tractor
## 3 1 4 1 4
## Boxes Books Not applicable
## 1 1 2372
## recoded
## [1,2) [2,3) [3,4) [4,5) [5,6) [6,7) [7,1e+06)
## 1 3 0 0 0 0 0 0
## 2 0 1 0 0 0 0 0
## 3 0 0 4 0 0 0 0
## 4 0 0 0 1 0 0 0
## 5 0 0 0 0 4 0 0
## 6 0 0 0 0 0 1 0
## 7 0 0 0 0 0 0 1
## 999 0 0 0 0 0 0 2372
## [1] "Frequency table after encoding"
## q506o_others_entry. 506o. Other item (specify)
## Small motor vehicle Water heater Fan/cooler Tape recorder
## 3 1 4 1
## Large Motor Vehicle Boxes Books
## 4 1 2373
## [1] "Inspect value labels and relabel as necessary"
## Small motor vehicle Water heater Fan/cooler Tape recorder
## 1 2 3 4
## Large Motor Vehicle Boxes Books
## 5 6 7Open-ends: review responses for any sensitive information, redact as necessary
# !!!Identify open-end variables here:
open_ends <- c("q509_watntobecome",
"q512d_steps_nxtyr1",
"q512d_steps_nxtyr2",
"q512d_steps_nxtyr3",
"q512g_knwtodo_1yr")
report_open (list_open_ends = open_ends)
# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number !!! Drop all, as actually verbatim data in Hindi
drop_vars <- c("q512d_steps_nxtyr1",
"q512d_steps_nxtyr2",
"q512d_steps_nxtyr3",
"q512g_knwtodo_1yr")
mydata <- mydata[!names(mydata) %in% drop_vars]GPS data: Displace
!!! No GPS data
Save 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)