Sectoral Wage Convergence: A Nonparametric Distributional Analysis
The large shift of U.S. employment from goods producers to service producers has generated concern over future income distribution, because of perceived large relative pay differences. This paper applies a nonparametric density overlap statistic to compare the sectors? distribution of full-time, weekly wages at all wage levels. To counter problematic features of Current Population Survey data--sampling variation at infrequent wage rates and extensive rounding at common wage rates--we employ nonparametric density-estimation procedures to isolate the underlying shapes of the densities. The validity and accuracy of these two approaches when combined is supported by Monte Carlo simulations. Standard errors and confidence intervals indicate that our results are statistically significant.
Broad similarity between goods and services wage distributions is found throughout the period from 1969 to 1993; however, the densities slowly diverge until 1980, after which they tend to converge. By the 1990s, the estimated densities are more than 95 percent identical. The breadth of this similarity and steady recent convergence are not easily identified by typical comparison statistics. Furthermore, the wage densities are most comparable in the central deciles, a finding that disputes the bimodal characterization of service-sector wages. Two potential explanations for the time pattern of the overlapping coefficient are considered by forming hypothetical distributions, but neither of these explanations removes the pattern.
Suggested citation: Schweitzer, Mark, 1996. “Sectoral Wage Convergence: A Nonparametric Distributional Analysis,” Federal Reserve Bank of Cleveland, Working Paper no. 96-11.