World Values Survey (WVS) Data

Overview

This folder contains cleaned and processed data from the 7th Wave of the World Values Survey, merged with World Bank GDP indicators. The WVS is a global research project that explores people’s values and beliefs across different countries and cultures.

Used in: Week 2 (Data Documentation), Week 3 (Report Writing)

Files

Processed Data

WVS_random_subset2000.csv - Random subset of 2,000 respondents stratified by country
WVS_GDP_merged_data.csv - Country-level aggregated data merged with GDP and population indicators
WVS_subset.csv - Selected variables from full dataset (all respondents, waves 1-7)

Documentation

codebook.pdf - Official WVS codebook with variable definitions and survey methodology
README_WVS.md - Data processing documentation and variable descriptions

Code

cleaning.R - R script that processes raw WVS data and creates the cleaned datasets

Data Structure

WVS_random_subset2000.csv

Observations: ~2,000 individual respondents
Variables: Demographics (country, interview date, weights) + survey items (Q1-Q89, Q260-Q290)
Purpose: Manageable sample for exploration and practice

WVS_GDP_merged_data.csv

Observations: Country-year level (Wave 7 only)
Variables: Aggregated survey responses + World Bank indicators
Key variables:
- B_COUNTRY_ALPHA: ISO3 country code
- A_YEAR: Survey year (varies by country, 2017-2023)
- Q1-Q89: Aggregated survey responses (means for numeric, modes for categorical)
- GDP_USD_PPP_per_capita: GDP per capita in PPP terms
- Population: Country population

Usage Notes

Negative codes (-1 to -5) in original data have been recoded as NA
Random sampling uses seed 20250124 for reproducibility
GDP data covers 2017-2023 to match survey timing variations
See README_WVS.md for detailed processing steps

Research Applications

Common research questions using this data: - Relationship between income level and trust/happiness - Cultural differences in gender attitudes - Economic development and social values