Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
This paper argues that time-series regression analysis is of only very limited use for understanding the determinants of income inequality. The argument is based on a combination of results from the time series econometrics literature and several characteristics of inequality itself, principally nonstationarity of the data in most inequality regression models, and the weak theoretical foundations underlying the models. A sample of postwar US data is used to illustrate the problems involved.