Load King and Zeng’s dataset on possible predictors of state collapse, kingzeng.csv. The website for these data contains full files and a codebook.
We will use the data to analyze a cause of homicide rates across countries and over time.
Select one possible cause of homicide rates. (If you don’t have other ideas, you can use whether a country is democratic or not as a default cause.) Use one or more machine learning algorithms to estimate the effect of that cause on homicide controlling for as many potential confounders as possible. Explain your analysis (as well as your choice of estimator) and interpret your results. How is this estimator different from those used in previous weeks?