DOL-ILAB SDC - ehsection4
Pablo Diego-Rosell, PhD
2021-06-15
- 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 <- "ehsection4" # !!!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("a006_a_block_id", "a007_a_vill_id")
mydata <- encode_location (variables= locvars, missing=999999)## [1] "Frequency table before encoding"
## a006_a_block_id. 006 Block ID
## 1 2 3 4 5 6 7 8 9
## 212 171 196 416 100 197 158 432 552
## [1] "Frequency table after encoding"
## a006_a_block_id. 006 Block ID
## 279 280 281 282 283 284 285 286 287
## 212 432 171 197 196 552 158 100 416
## [1] "Frequency table before encoding"
## a007_a_vill_id. 007 Village ID
## 1 2 3 4 5 6 7 8 9 10 11 12 13 15 16 17 18 19 20 21 22 23 24 25 26 27 28
## 17 16 17 16 20 30 29 16 15 15 17 26 24 15 18 21 18 18 20 30 23 18 18 32 27 28 18
## 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55
## 15 15 24 26 23 16 29 19 17 22 27 16 16 18 16 28 21 24 21 20 18 17 17 18 27 25 27
## 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 80 81 82 83
## 19 16 22 13 24 21 18 19 18 30 16 19 22 25 14 16 21 16 24 23 18 23 30 31 16 22 17
## 84 85 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
## 18 13 18 22 16 19 20 19 20 14 21 24 29 22 26 19 25 21 16 19 16 31 14 28 22 17 21
## 112 113 114 115 116 117 118 119 120 121 122
## 27 15 24 20 16 24 23 22 13 13 10
## [1] "Frequency table after encoding"
## a007_a_vill_id. 007 Village ID
## 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635
## 16 22 15 17 31 20 16 21 30 17 21 18 22 28 27 17 19 22 16 17 32 17 13 26 15 31 28
## 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662
## 15 14 27 16 27 18 16 16 30 20 26 18 24 23 18 24 15 16 15 16 20 18 18 18 18 30 17
## 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689
## 16 18 18 27 17 21 29 26 19 19 23 16 22 29 23 23 19 18 24 16 19 29 24 20 28 10 21
## 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
## 20 18 25 22 22 17 24 24 21 25 20 30 22 19 21 13 19 14 19 16 21 21 16 16 16 25 18
## 717 718 719 720 721 722 723 724 725 726 727
## 27 16 14 22 13 18 23 24 15 24 13Indirect 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="a404_old_girl_die_", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## a404_old_girl_die_. 404. How old was the girl when she died?
## 1 2 3 4 7 8 9 10 11 12 13 15 16 <NA>
## 5 3 1 5 5 1 4 5 1 8 1 1 1 2393
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 1 5 0 0 0 0
## 2 3 0 0 0 0
## 3 1 0 0 0 0
## 4 5 0 0 0 0
## 7 0 5 0 0 0
## 8 0 1 0 0 0
## 9 0 4 0 0 0
## 10 0 0 5 0 0
## 11 0 0 1 0 0
## 12 0 0 8 0 0
## 13 0 0 1 0 0
## 15 0 0 0 1 0
## 16 0 0 0 1 0
## [1] "Frequency table after encoding"
## a404_old_girl_die_. 404. How old was the girl when she died?
## 0-4 5-9 10-14 15-19 <NA>
## 14 10 15 2 2393
## [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="a405_stop_liv_resid_", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## a405_stop_liv_resid_. 405. How old was the girl when her mother stopped living in the same residence?
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 17 <NA>
## 26 16 10 14 8 1 3 6 4 12 9 5 2 3 1 1 2313
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 1 26 0 0 0 0
## 2 16 0 0 0 0
## 3 10 0 0 0 0
## 4 14 0 0 0 0
## 5 0 8 0 0 0
## 6 0 1 0 0 0
## 7 0 3 0 0 0
## 8 0 6 0 0 0
## 9 0 4 0 0 0
## 10 0 0 12 0 0
## 11 0 0 9 0 0
## 12 0 0 5 0 0
## 13 0 0 2 0 0
## 14 0 0 3 0 0
## 15 0 0 0 1 0
## 17 0 0 0 1 0
## [1] "Frequency table after encoding"
## a405_stop_liv_resid_. 405. How old was the girl when her mother stopped living in the same residence?
## 0-4 5-9 10-14 15-19 <NA>
## 66 22 31 2 2313
## [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="a411_old_girl_die_", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## a411_old_girl_die_. 411. How old was the girl when he died?
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 <NA>
## 21 12 13 10 13 10 13 22 8 21 14 22 7 9 6 3 2230
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 1 21 0 0 0 0
## 2 12 0 0 0 0
## 3 13 0 0 0 0
## 4 10 0 0 0 0
## 5 0 13 0 0 0
## 6 0 10 0 0 0
## 7 0 13 0 0 0
## 8 0 22 0 0 0
## 9 0 8 0 0 0
## 10 0 0 21 0 0
## 11 0 0 14 0 0
## 12 0 0 22 0 0
## 13 0 0 7 0 0
## 14 0 0 9 0 0
## 15 0 0 0 6 0
## 16 0 0 0 3 0
## [1] "Frequency table after encoding"
## a411_old_girl_die_. 411. How old was the girl when he died?
## 0-4 5-9 10-14 15-19 <NA>
## 56 66 73 9 2230
## [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="a412_stop_liv_resid_", break_points=break_age, missing=999999, value_labels=labels_age)
## [1] "Frequency table before encoding"
## a412_stop_liv_resid_. 412. How old was the girl when her father stopped living in the same residence?
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 17 <NA>
## 36 13 8 13 13 6 5 5 3 20 12 8 12 3 3 1 2273
## recoded
## [0,5) [5,10) [10,15) [15,20) [20,1e+06)
## 1 36 0 0 0 0
## 2 13 0 0 0 0
## 3 8 0 0 0 0
## 4 13 0 0 0 0
## 5 0 13 0 0 0
## 6 0 6 0 0 0
## 7 0 5 0 0 0
## 8 0 5 0 0 0
## 9 0 3 0 0 0
## 10 0 0 20 0 0
## 11 0 0 12 0 0
## 12 0 0 8 0 0
## 13 0 0 12 0 0
## 14 0 0 3 0 0
## 15 0 0 0 3 0
## 17 0 0 0 1 0
## [1] "Frequency table after encoding"
## a412_stop_liv_resid_. 412. How old was the girl when her father stopped living in the same residence?
## 0-4 5-9 10-14 15-19 <NA>
## 70 32 55 4 2273
## [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("a415a_guardn_child_",
"a430l_oth_",
"a430l_oth_entry_",
"a430la_current_")
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("a415a_guardn_child_",
"a418k_other_entry_",
"a422_life_change_",
"a423_plan_future_",
"a428_obstacle_girl_",
"a429_gto_school_",
"a429_gto_school_oth_",
"a435_situations_",
"a437_advantages_",
"a438_good_match_")
report_open (list_open_ends = open_ends)
dropvars <- c("a418k_other_entry_",
"a422_life_change_",
"a423_plan_future_",
"a429_gto_school_oth_")
mydata <- mydata[!names(mydata) %in% dropvars] # 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)