Skip to main content
Variable Correlation Explorer

50+ Variable Correlation Engine

Plot any two variables against each other across 204 countries. Explore relationships between health, wealth, lifestyle, diet, environment, and happiness with regression statistics, colour-coded regions, and pre-computed strongest correlations.

Configure Scatter Plot
X-Axis
Y-Axis
0 years Use lag to find delayed effects (e.g. tobacco use → cancer deaths: 20-30yr lag)
✨ Featured Correlations
Click any pairing to load it instantly into the scatter plot above
r = --
R2 = --
--
N = -- countries
Loading...
Each dot is a country. Hover for details.
Strongest Correlations
Pre-computed from all variable pairs. Click any row to plot it.
Counterfactual Simulator: "What If?"
What would happen to death rates if a country changed its risk factors?
Current: -- New: --

Ecological fallacy warning: These estimates are based on cross-country correlations and assume a causal relationship. Individual-level effects may differ significantly. This is for exploration only -- not medical or policy advice.

Correlation Matrix Heatmap
Select variables to build a custom NxN correlation grid. Click any cell to view the scatter plot.
Animated Bubble Chart
Watch countries evolve over time. Each bubble is a country — size = population, colour = region.
2023
What Makes a Healthy Country?
Top predictors of life expectancy, ranked by correlation strength
Country Outlier Report
Select a country to see which variables it's an outlier on
Country Clusters (k-Means)
PCA projection of 14 health and development variables
Cluster Membership
Countries grouped by similar health and development profiles
Multiple Regression: What Predicts Death Rates?
Which combination of factors best explains cross-country differences in each cause of death?

⚠️ Ecological analysis: These are cross-country (ecological) regressions, not individual-level. Results should NOT be interpreted as causal relationships. R² shows the variance explained by the model.

Change-Point Detection
Identifying structural breaks in mortality trends — when did things fundamentally change?
Natural Experiments in Global Health
Countries that experienced sudden policy changes or events — nature's randomised trials

Mortality and Socioeconomic Correlations

What drives death rates? Explore the statistical relationships

The Correlation Explorer enables you to investigate statistical relationships between mortality rates and key socioeconomic indicators. By plotting cause-specific death rates against GDP per capita, Gini inequality, and income classification, you can explore the macro-level factors associated with national mortality patterns.

Each scatter plot positions 204 countries as data points, colour-coded by World Bank income group or world region. Hover over any country to see its exact values. This tool is useful for researchers, students, and analysts seeking to understand the broader determinants of health at the population level.

Frequently Asked Questions
What correlations can I explore?

The Correlation Explorer lets you plot mortality rates against socioeconomic variables including GDP per capita, Gini inequality index, and World Bank income classification. You can examine relationships for total mortality or specific causes of death across 204 countries.

Does correlation mean causation in mortality data?

No. The correlations shown are observational associations, not causal relationships. For example, higher GDP is associated with lower death rates, but many confounding factors (healthcare investment, education, sanitation) drive this relationship. The tool is designed for exploratory analysis, not causal inference.

What is the Gini index and how does it relate to mortality?

The Gini index measures income inequality on a scale from 0 (perfect equality) to 1 (maximum inequality). Research suggests that higher inequality is associated with worse health outcomes, including higher mortality rates, though the relationship is complex and debated among economists and epidemiologists.