rm(list=ls(all=t))

Setup filenames

filename <- "Section_11" # !!!Update filename
functions_vers <-  "functions_1.8.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

# !!!No small locations

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

# !!!Include relevant variables in list below (Indirect PII - Categorical, and Ordinal if not processed yet)

indirect_PII <- c("s11q1",
                  "s11q3",
                  "s11q5",
                  "s11q7",
                  "s11q9",
                  "s11q11",
                  "s11q13",
                  "s11q15",
                  "s11q17",
                  "s11q19",
                  "s11q22")
capture_tables (indirect_PII)

# Recode those with very specific values. 
# !!!No specific values

Matching and crosstabulations: Run automated PII check

# !!! Insufficient demographic data

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

# !!! Identify open-end variables here: 
open_ends <- c("s11q1_why",
               "s11q3_why",
               "s11q5_why",
               "s11q7_why",
               "s11q9_why",
               "s11q11_why",
               "s11q13_why",
               "s11q15_why",
               "s11q17_why",
               "s11q19_why",
               "s11q20_why",
               "s11q22_why")

report_open (list_open_ends = open_ends)


# Review "verbatims.csv". Identify variables to be deleted or redacted and their row number 

mydata$s11q13_why[1581] <- "[language]"

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)