Premium
STOCHASTIC PROCESS MODELS AND THE DISTRIBUTION OF EARNINGS *
Author(s) -
Osberg Lars
Publication year - 1977
Publication title -
review of income and wealth
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.024
H-Index - 57
eISSN - 1475-4991
pISSN - 0034-6586
DOI - 10.1111/j.1475-4991.1977.tb00014.x
Subject(s) - economics , earnings , microdata (statistics) , distribution (mathematics) , econometrics , stochastic modelling , accounting , mathematics , population , sociology , finance , mathematical analysis , demography , census
This article examines several hypotheses concerning the stochastic nature of year to year variations in individual incomes in light of newly available microdata on individual earnings. In particular, the models of Solow (1951), Champernowne (1953), and Rutherford (1955) are examined in some detail, and their predictions as to changes to be expected in the distribution of individual incomes are tested. The author concludes that the distributions arrived at using these models are not very similar either to each other or to the actual distribution of earnings. Thus, he believes that as an “explanation” of earnings dynamics stochastic process models are unsatisfactory. He further criticizes these models on the grounds that they foster a bias toward the belief in the inevitability, and perhaps desirability, of the current distribution of earnings.