rm(list=ls(all=t))

Setup filenames

filename <- "0_t1_gnrl_info_relabelled" # !!!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("t1_dise_code") 
mydata <- mydata[!names(mydata) %in% dropvars]

Indirect 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

# !!! No Indirect PII - Categorical

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)