Public employment and earnings inequality: An analysis based on conditional and unconditional quantile regressions

Studies investigating the link between public employment and earnings inequality based on micro data typically make use of conditional quantile regressions. Such analysis reveals why earnings may be more or less dispersed among public-sector than private-sector workers, but does not allow drawing conclusions about its impact on overall earnings inequality. The unconditional quantile regression technique proposed by Firpo et al. (2009) overcomes this deficiency, and this technique is applied here to show that a fall in public employment may raise or reduce earnings inequality, depending on country specificities. The paper also highlights the complementary roles of conditional and unconditional quantile regressions in investigating the determinants of earnings inequality.