rm(list=ls(all=t))

Setup filenames

filename <- "A_t2_Child_Availability" # !!!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 

#!!!Save flagged dictionary in .csv format, add "DatasetReview" to name and continue processing data with subset of flagged variables

Direct PII: variables to be removed

# !!!Include any Direct PII variables
#!!!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

# Focus on variables with a "Lowest Freq" in dictionary of 30 or less. 

# Remove date of birth

dropvars <- c("t2_q2_dob_dd") 
mydata <- mydata[!names(mydata) %in% dropvars]

dropvars <- c("t2_q2_dob_mm") 
mydata <- mydata[!names(mydata) %in% dropvars]

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("t2_a1_child_at_home",
                  "t2_a2_child_not_home",
                  "t2_q1_age",
                  "t2_q2_dob_yy",
                  "bl_t1_t2",
                  "bl_t1_t2_ad1")

capture_tables (indirect_PII)

# Recode those with very specific values.

Matching and crosstabulations: Run automated PII check

# !!!Insufficient demographic information

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

#!!!No Open-ends

GPS data: Displace

#!!!NO GPS variables

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)