Income disparities among hungarian micro-regions: The mover-stayer model

Abstract

It is known that the simple Markov chain model overestimates the long run horizon mobility of the income distribution process. Dissolving the homogeneity assumption of the Markov model may lead to better forecasts. One generalisation of the Markov model, the Mover-Stayer model assumes heterogenous population: some units are moving according to a common Markov chain, but there are some (unknown) units that are not moving at all. They are called stayers.Based on the Frydman (1984) methodology if we compute both the Markov and Mover-Stayer models for Hungarian micro-regions income data, we find that the Mover-Stayer model fits better the regional relative income data than the simple Markov model. Using likelihood ratio test statistics we show that the difference is highly significant. The method is also applied for spatially conditioned data. The results show that the high persistence of relative income positions is a remarkable feature of the Hungarian economy in 1990–2003 both on a country-wide scale and local level. We also demonstrate that forecasts made on a less reliant model might lead to very ambiguous results.