In 2009, Wilkinson and Pickett published a popular book called The Spirit Level, in which they claim that many social problems are significantly worse in more unequal countries (whether rich or poor). In particular, they considered violent crimes, and observed a significant positive correlation between economic inequality and homicide rates, with r = 0.47 and a p-value of 0.02 (see here).
Inequality can be quantified with the Gini index, which measures the distribution of family income in a country. The more nearly equal a country’s income distribution, the lower its Gini index, e.g., a Scandinavian country with an index of 25. The more unequal a country’s income distribution, the higher its Gini index, e.g., Israel, the USA or Singapore with an index of 40 or above. If income were distributed with perfect equality the index would be zero; if income were distributed with perfect inequality, the index would be 100.
The data originally used by Wilkinson and Pickett are from the United Nations, and date from before 2009. This task involves reproducing the same analysis, but using more recent data.
- State the null and alternative hypotheses for Wilkinson and Pickett’s original research question about inequality and homicide rates, both in plain language and in symbols.
- Explain what statistical approach is appropriate to test such hypotheses (including whether it should be a 1- or 2-tailed test), and why.
- Download the following datasets: homicide rates | Gini index
- Use your favorite software (Excel, Minitab, etc.) to carry out the chosen test – in particular, produce a diagram similar in style to this one.
- Interpret the obtained test statistic and p-value in relation to the stated hypotheses.
- State an appropriate conclusion in plain language.
- Is the original claim by Wilkinson & Pickett reproduced? Discuss.