rm(list=ls(all=t))

Setup filenames

filename <- "0_t2_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)
## --------
## This is sdcMicro v5.6.0.
## For references, please have a look at citation('sdcMicro')
## Note: since version 5.0.0, the graphical user-interface is a shiny-app that can be started with sdcApp().
## Please submit suggestions and bugs at: https://github.com/sdcTools/sdcMicro/issues
## --------
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
## Loading required package: sp
## Checking rgeos availability: TRUE
## 
## Attaching package: 'raster'
## The following object is masked from 'package:dplyr':
## 
##     select
## The following object is masked from 'package:sdcMicro':
## 
##     freq
## rgdal: version: 1.5-23, (SVN revision 1121)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 3.2.1, released 2020/12/29
## Path to GDAL shared files: C:/Users/Usuario/Documents/R/win-library/3.6/rgdal/gdal
## GDAL binary built with GEOS: TRUE 
## Loaded PROJ runtime: Rel. 7.2.1, January 1st, 2021, [PJ_VERSION: 721]
## Path to PROJ shared files: C:/Users/Usuario/Documents/R/win-library/3.6/rgdal/proj
## PROJ CDN enabled: FALSE
## Linking to sp version:1.4-5
## To mute warnings of possible GDAL/OSR exportToProj4() degradation,
## use options("rgdal_show_exportToProj4_warnings"="none") before loading rgdal.
## Overwritten PROJ_LIB was C:/Users/Usuario/Documents/R/win-library/3.6/rgdal/proj
## Loading required package: spatstat.data
## Loading required package: spatstat.geom
## spatstat.geom 2.1-0
## 
## Attaching package: 'spatstat.geom'
## The following objects are masked from 'package:raster':
## 
##     area, rotate, shift
## Loading required package: spatstat.core
## Loading required package: nlme
## 
## Attaching package: 'nlme'
## The following object is masked from 'package:raster':
## 
##     getData
## The following object is masked from 'package:dplyr':
## 
##     collapse
## Loading required package: rpart
## spatstat.core 2.1-2
## Loading required package: spatstat.linnet
## spatstat.linnet 2.1-1
## 
## spatstat 2.1-0       (nickname: 'Comedic violence') 
## For an introduction to spatstat, type 'beginner'
## rgeos version: 0.5-5, (SVN revision 640)
##  GEOS runtime version: 3.8.0-CAPI-1.13.1 
##  Linking to sp version: 1.4-5 
##  Polygon checking: TRUE
## 
## Spatial Point Pattern Analysis Code in S-Plus
##  
##  Version 2 - Spatial and Space-Time analysis
## 
## Attaching package: 'splancs'
## The following object is masked from 'package:raster':
## 
##     zoom
## The following object is masked from 'package:dplyr':
## 
##     tribble
## Loading required package: spam
## Loading required package: dotCall64
## Loading required package: grid
## Spam version 2.6-0 (2020-12-14) is loaded.
## Type 'help( Spam)' or 'demo( spam)' for a short introduction 
## and overview of this package.
## Help for individual functions is also obtained by adding the
## suffix '.spam' to the function name, e.g. 'help( chol.spam)'.
## 
## Attaching package: 'spam'
## The following objects are masked from 'package:base':
## 
##     backsolve, forwardsolve
## See https://github.com/NCAR/Fields for
##  an extensive vignette, other supplements and source code
## 
## Attaching package: 'geosphere'
## The following object is masked from 'package:spatstat.geom':
## 
##     perimeter
## 
## Attaching package: 'tibble'
## The following object is masked from 'package:splancs':
## 
##     tribble

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

# Remove date of birth

dropvars <- c("t1_dob_calculated") 
mydata <- mydata[!names(mydata) %in% dropvars]

Indirect PII - Categorical: Recode, encode, or Top/bottom coding for extreme values

indirect_PII <- c("t1_a1_child_present",
                  "t1_a2_ch_present_status",
                  "t1_a3_ch_back",
                  "t1_child_age")

capture_tables (indirect_PII)

Matching and crosstabulations: Run automated PII check

#!!!Not enough demographic information to conduct matching

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)