Abstract:
We use a boosting algorithm to forecast changes in three income- and three consumption-based inequality measures. Unlike the existing literature, which basically deals with in-sample predictability, we analyze the role of large number of predictors in out-of-sample prediction of inequality growth. Further, deviating from the annual data-based literature on inequality, we study quarterly UK data covering the period from 1975Q1 to 2016Q1. We find that the boosted forecasting models, at forecasting horizons of up to one year, have to differing extents predictive value for changes in the six different inequality measures. Evidence of predictability is stronger on balance when we use information criteria that result in relatively parsimonious forecasting models than information criteria that are more generous in this regard. In addition to lagged inequality measures, stock-market developments and fiscal deficits, and to a lesser extent the real interest rate, economic policy uncertainty, and output growth turn out to be predictors that are often selected by the algorithm.
