rm(list=ls(all=t))

Setup filenames

filename <- "bcsection1" # !!!Update filename
functions_vers <-  "functions_1.7.R" # !!!Update helper functions file

Setup 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 PII

Direct PII-team: Encode field team names

# !!! No Direct PII-team

Small 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("q002_blckid", "q003_vill_id") 
mydata <- encode_location (variables= locvars, missing=999999)
## [1] "Frequency table before encoding"
## q002_blckid. 2. Tehsil/Block ID
##   1   2   3   4   5   6   7   8   9 
## 210 152 192 414 100 197 158 426 550 
## [1] "Frequency table after encoding"
## q002_blckid. 2. Tehsil/Block ID
## 279 280 281 282 283 284 285 286 287 
## 426 152 192 550 414 100 210 158 197 
## [1] "Frequency table before encoding"
## q003_vill_id. 3. Village ID
##   1   2   3   4   5   6   7   9  10  11  12  13  14  15  16  17  18  19  20  21  22  23  24  25 
##  17  12  16  16  19  31  27  17  15  20  26  23   2  13  19  21  17  18  20  30  22  17  16  27 
##  26  27  28  29  30  31  32  33  34  35  36  37  38  39  40  41  42  43  44  45  46  47  48  49 
##  27  28  18  15  15  24  27  21  13  30  17  17  21  28  16  16  18  16  26  21  24  21  17  17 
##  50  51  52  53  54  55  56  57  58  59  60  61  62  63  64  65  66  67  68  69  70  71  72  73 
##  17  13  18  28  25  27  19  14  21  12  22   9  17  19  18  28  15  19  22  26  14  16  21  16 
##  74  75  76  77  78  80  81  82  83  84  85  86  87  88  89  90  91  92  93  94  95  96  97  98 
##  25  23  17  23  31  30  17  22  17  16  13  14  17  18  16  19  19  20  21  14  20  24  29  29 
##  99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 
##  26  22  25  21  11  23  17  30  14  28  20  16  20  27  41  22  20  12  24  19  21  13  13  10 
## [1] "Frequency table after encoding"
## q003_vill_id. 3. 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 
##  29  16  12  21  23  18  16  23  10  25  18  15  31  19  28  17  20  17  17  17  21  20  19  19 
## 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 
##  25  22  15  31  17  22  28  22  24  17  14  24  26  30  21  20  26  13  29  11  19  27  28  15 
## 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 
##  14  24  21  19  14  20  21  13  15  27  16  13   2  18  17  20  17  21  17  13  20  30  23  25 
## 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 
##  18  27  18  22  27  12  16   9  18  17  26  27  17  17  17  21  21  41  17  21  28  20  12  14 
## 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 
##  16  21  24  13  30  30  19  16  17  27  22  14  19  16  19  16  13  22  16  23  26  28  16  16

Indirect PII - Ordinal: Global recode or Top/bottom coding for extreme values

# Top code household composition variables with large and unusual numbers 

mydata <- top_recode ("q101_sibli_share", break_point=5, missing=c(888, 999999)) # Topcode cases with 5 or more  
## [1] "Frequency table before encoding"
## q101_sibli_share. 101. How many siblings do you have that share at least a mother or father but do
##    0    1    2    3    4    5    6    7    8    9 
## 2289    4   16   24   25   22   10    7    1    1

## [1] "Frequency table after encoding"
## q101_sibli_share. 101. How many siblings do you have that share at least a mother or father but do
##         0         1         2         3         4 5 or more 
##      2289         4        16        24        25        41

mydata <- top_recode ("q102_age_non_resi", break_point=5, missing=c(888, 999999)) # Topcode cases with 5 or more
## [1] "Frequency table before encoding"
## q102_age_non_resi. 102. In order of age, what number are you considering all of your non-resident s
##    0    1    2    3    4    5    6    7    8 <NA> 
##    2   35   27   19   11   10    3    2    1 2289

## [1] "Frequency table after encoding"
## q102_age_non_resi. 102. In order of age, what number are you considering all of your non-resident s
##         0         1         2         3         4 5 or more      <NA> 
##         2        35        27        19        11        16      2289

mydata <- top_recode ("q103_age_non_resi_f", break_point=3, missing=c(888, 999999)) # Topcode cases with 3 or more
## [1] "Frequency table before encoding"
## q103_age_non_resi_f. 103. In order of age, what number are you considering all of your non-resident f
##    0    1    2    3    4    5    6    7 <NA> 
##    2   56   19   18    7    5    2    1 2289

## [1] "Frequency table after encoding"
## q103_age_non_resi_f. 103. In order of age, what number are you considering all of your non-resident f
##         0         1         2 3 or more      <NA> 
##         2        56        19        33      2289

Indirect PII - Categrical: 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("q005_urban_rural", "abvmed_qualindex")
capture_tables (indirect_PII)

# Recode those with very specific values.

Matching and crosstabulations: Run automated PII check

# Not enough variables for matching possible

Open-ends: review responses for any sensitive information, redact as necessary

# !!! No open-ends

GPS data: Displace

# !!! No GPS

Save 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)