Does money buy a longer life? GDP and life expectancy

Why it makes a good exploration

The Preston curve shows that extra income helps a lot in poor countries and much less in rich ones — a logarithmic relationship. Testing it with current data, and seeing how it has moved over 30 years, is a rich statistics and modelling question.

The mathematics you'll need

• Linear and logarithmic models
• Transforming the x-variable with logarithms
• Correlation and coefficient of determination
• Comparing fitted parameters between years

Course labels show where a technique sits; using maths from outside your course is fine if you explain it clearly and say it is new to you.

Where the data comes from

Download GDP per capita (PPP) and life expectancy for all countries for two years from Gapminder, the World Bank or Our World in Data.

• Gapminder data — Long-run indicators (income, life expectancy, child mortality) — free to reuse with attribution.
• World Bank Open Data — Development indicators (GDP, life expectancy, mortality, internet use) for every country, usually from 1960.
• Our World in Data — Clean country-level time series (CO₂, population, health, energy, education) with CSV download on every chart.

Cite every source in a footnote where you use it and in your bibliography. Check the licence of any dataset you download.

A possible outline

1. Explain the data definitions (PPP, period life expectancy).
2. Plot life expectancy against GDP and against ln(GDP).
3. Fit both models and compare.
4. Repeat for 1990 and compare the curves.
5. Reflect on outliers and what the model says about causation.

Showing personal engagement

• Locate your own country and explain its residual.
• Investigate an outlier country in detail.
• Discuss what the flattening means for policy.

See Criterion C: personal engagement for what examiners look for.

Taking it further

Weight the regression by population or compare the Preston curve for child mortality.