Initial Setup
To start:
Download R and R Studio.
Download quartro (https://quarto.org/docs/download/). This is used to generate the report.
Download the “Paradata Module Stats.zip”
- The zipfile contains all the folders and source codes needed to conduct the paradata analysis. Extract the zipfile to a folder of your choice.
Main Project Folder
To access the project, click on the start_here_paradata_analysis which will open an Rstudio project and set the directory to the project location. There are 5 files and folders in the project as shown below.
start_here_paradata_analysis.Rproj: opens the project in R-Studio. Open the project to start the analysis.
README: contain basic information about the project.
create_report.R: This is the main R-code that users will need to modify and run to generate the final report.
R: folder contains all the Rcodes used in create_report.R
data: contains folder related to data such as the main paradata folder an
R Folder
The R folder contains 4 R-script files that is used in create_report.R. Users do not need to modify any of the scripts below and can focus instead on modifying create_report.R. Descriptions of the files are provided below in case needed.
load_requirements.R: Install and call on all the necessary packages needed for the codes to run.
0_extract_and_clean_paradara1.R: Automatically opens and clean paradata, calculate interview time between events, trim outliers (set to 1% of interview length), and automatically assign module name based on survey metadata.
0_extract_and_clean_paradara2.R: Create team data, clean up individual-level interviews, and save final cleaned paradata to Data -> 04_created folder.
Paradata_Report.qmd: Take the cleaned paradata and generate a report using quatro. Final output will be in Data -> 04_created folder.
Data Folder
Any dataset needed or created will be in this folder.
01_paradata: Zipfiles containing paradata downloaded from Survey Solutions should be put here.
02_metadata: Metadata (json file) downloaded from Survey Solutions should be put here.
03_microdata: Any dataset from the survey microdata or any other data inputs should be put here.
04_created: Cleaned paradata and the final report can be found here.