GDP per capita, PPP (current international $)
- Rows
- 8,512
- Columns
- 4
- Data range
- 1990-01-01 to 2024-01-01
- Auto-refresh
- Re-checks its source every 30 days
World Bank World Development Indicators: GDP per capita, PPP (current international dollars). Cross-country time-series economic data.
AI analysis
Dataset Analysis: GDP per Capita, PPP (Current International $)
1. Dataset Overview & Value for Correlation Studies This dataset captures GDP per capita adjusted for purchasing power parity (PPP) across 251 countries and territories spanning 35 years (1990–2024), sourced from the World Bank's World Development Indicators API at [datahub.io](https://datahub.io/world-development-indicators/ny.gdp.pcap.pp.cd/r/-/data.csv). The PPP adjustment makes cross-country comparisons particularly meaningful by normalizing for price-level differences — a critical advantage over nominal GDP figures. With 8,512 rows representing a near-complete country-year panel, this dataset is a high-value anchor for virtually any socioeconomic correlation study. The World Bank provenance and the coverage extending to 2024 suggest reasonably current and authoritative data, though the most recent years (2023–2024) may carry preliminary estimates subject to revision.
2. Data Quality Observations Data quality here is notably strong. The total null cell count across all four columns is zero, which is exceptional for a cross-country time-series dataset of this scope — typically, smaller or lower-income nations generate significant missingness in economic indicators. Duplicate row figures are pending Phase D recomputation, which warrants a quick validation pass before joining with other datasets, but no structural red flags are visible. All 251 distinct Country Names align exactly with 251 distinct Country Codes, confirming no orphaned or mismatched country identifiers. The Value column's 8,449 distinct decimal values across 8,512 rows implies minimal exact duplicates in the economic figures themselves, which is expected and appropriate. The one area to probe further is whether the zero-null count reflects genuine data completeness or imputed/forward-filled values masking true gaps.
3. Key Column Distributions The Value column tells a vivid story of global inequality. The mean of $16,288 is nearly double the median of $8,457, a hallmark of right-skewed distributions confirmed by a skewness score of 2.45 — a strong positive skew indicating that a small number of high-income countries pull the average sharply upward. The interquartile range (Q1: $3,236 → Q3: $21,623) spans roughly a 6.7× difference just within the middle 50% of observations, underscoring the profound economic disparity in the dataset. The maximum value of $180,939 (likely small high-income economies such as Luxembourg, Singapore, or Qatar in recent years) versus the minimum of $254 represents a 711× ratio, and the 610 flagged outliers (~7.2% of rows) deserve attention — these are not errors but structurally significant data points that should be retained and potentially analyzed separately. The Year column with exactly 35 distinct values and the Country Name column with 251 entities suggest a well-balanced panel, though not necessarily perfectly balanced for every country-year combination.
4. Recommended Join Key Columns The natural join strategy for cross-dataset correlation is a composite key on Country Code + Year. Country Code (ISO 3-letter standard, 251 distinct values) is preferable to Country Name for joining, as country names vary in spelling and formatting across sources (e.g., "Korea, Rep." vs. "South Korea"). The Year column, stored as a full date (YYYY-01-01 format), may require casting to a 4-digit integer year when joining with datasets that store year as a numeric type. Both join key columns carry zero nulls, making them reliable anchors. For datasets with regional rather than country-level granularity, World Bank region and income-group mappings should be merged in as a secondary lookup table.
5. Recommended Pairing Datasets for Correlation Discovery This dataset is an exceptionally versatile left-table anchor. High-value pairings include: (a) Health Indicators — life expectancy, infant mortality, or disease prevalence (e.g., WHO or World Bank health WDI series) to test the well-documented wealth-health gradient; (b) Education Data — literacy rates, school enrollment, or PISA scores to explore human capital relationships; (c) CO₂ Emissions per Capita — to analyze the Environmental Kuznets Curve hypothesis, examining whether emissions rise then fall with income; (d) Gini Coefficient / Income Inequality datasets to study whether higher GDP per capita correlates with lower or higher within-country inequality; and (e) Political/Governance Indices such as the World Bank's Worldwide Governance Indicators or Freedom House scores, to explore institutional quality and prosperity linkages. All of these share the same Country Code + Year composite key structure, enabling clean time-series panel joins.
Columns
- Year (date)
- Country Name (string)
- Country Code (string)
- Value (decimal)