rm(list=ls(all=t))

Setup filenames

filename <- "Section_15" # !!!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("eh_s15q1", "eh_s15q2", "eh_s15q3", "eh_s15q4", "eh_s15q5", "eh_s15q6", "eh_s15q7", "eh_s15q8",
                  "eh_s15q9", "eh_s15q10", "eh_s15q11", "eh_s15q12", "eh_s15q13", "eh_s15q14", "eh_s15q15",
                  "eh_s15q16", "eh_s15q17", "eh_s15q18", "eh_s15q19", "eh_s15q20", "eh_s15q21", "eh_s15q22",
                  "eh_s15q23", "eh_s15q24")
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

# !!!No Open-ends

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)