Modelling income processes with lots of heterogeneity

Martin Browning; Mette Ejrnæs; Javier Alvarez

doi:10.1111/j.1467-937X.2010.00612.x

Modelling income processes with lots of heterogeneity

Martin Browning, Mette Ejrnæs, Javier Alvarez

Department of Economics

52 Citations (Scopus)

Abstract

We model earnings processes allowing for lots of heterogeneity across agents. We also introduce an extension to the linear ARMA model which allows the initial convergence in the long run to be different from that implied by the conventional ARMA model. This is particularly important for unit root tests, which are actually tests of a composite of two independent hypotheses. We fit to a variety of statistics including most of those considered by previous investigators. We use a sample drawn from the Panel Study of Income Dynamics (PSID), and focus on white males with a high-school degree. Despite this observable homogeneity, we find more latent heterogeneity than previous investigators. We show that allowance for heterogeneity makes substantial differences to estimates of model parameters and to outcomes of interest. Additionally, we find strong evidence against the hypothesis that any worker has a unit root.

Original language	English
Journal	Review of Economic Studies
Volume	77
Issue number	4
Pages (from-to)	1353-1381
Number of pages	29
ISSN	0034-6527
DOIs	https://doi.org/10.1111/j.1467-937X.2010.00612.x
Publication status	Published - Oct 2010

Access to Document

10.1111/j.1467-937X.2010.00612.x

Cite this

@article{aed354a0b0ec11df825b000ea68e967b,

title = "Modelling income processes with lots of heterogeneity",

abstract = "We model earnings processes allowing for lots of heterogeneity across agents. We also introduce an extension to the linear ARMA model which allows the initial convergence in the long run to be different from that implied by the conventional ARMA model. This is particularly important for unit root tests, which are actually tests of a composite of two independent hypotheses. We fit to a variety of statistics including most of those considered by previous investigators. We use a sample drawn from the Panel Study of Income Dynamics (PSID), and focus on white males with a high-school degree. Despite this observable homogeneity, we find more latent heterogeneity than previous investigators. We show that allowance for heterogeneity makes substantial differences to estimates of model parameters and to outcomes of interest. Additionally, we find strong evidence against the hypothesis that any worker has a unit root.",

author = "Martin Browning and Mette Ejrn{\ae}s and Javier Alvarez",

year = "2010",

month = oct,

doi = "10.1111/j.1467-937X.2010.00612.x",

language = "English",

volume = "77",

pages = "1353--1381",

journal = "Review of Economic Studies",

issn = "0034-6527",

publisher = "Oxford University Press",

number = "4",

}

TY - JOUR

T1 - Modelling income processes with lots of heterogeneity

AU - Browning, Martin

AU - Ejrnæs, Mette

AU - Alvarez, Javier

PY - 2010/10

Y1 - 2010/10

N2 - We model earnings processes allowing for lots of heterogeneity across agents. We also introduce an extension to the linear ARMA model which allows the initial convergence in the long run to be different from that implied by the conventional ARMA model. This is particularly important for unit root tests, which are actually tests of a composite of two independent hypotheses. We fit to a variety of statistics including most of those considered by previous investigators. We use a sample drawn from the Panel Study of Income Dynamics (PSID), and focus on white males with a high-school degree. Despite this observable homogeneity, we find more latent heterogeneity than previous investigators. We show that allowance for heterogeneity makes substantial differences to estimates of model parameters and to outcomes of interest. Additionally, we find strong evidence against the hypothesis that any worker has a unit root.

AB - We model earnings processes allowing for lots of heterogeneity across agents. We also introduce an extension to the linear ARMA model which allows the initial convergence in the long run to be different from that implied by the conventional ARMA model. This is particularly important for unit root tests, which are actually tests of a composite of two independent hypotheses. We fit to a variety of statistics including most of those considered by previous investigators. We use a sample drawn from the Panel Study of Income Dynamics (PSID), and focus on white males with a high-school degree. Despite this observable homogeneity, we find more latent heterogeneity than previous investigators. We show that allowance for heterogeneity makes substantial differences to estimates of model parameters and to outcomes of interest. Additionally, we find strong evidence against the hypothesis that any worker has a unit root.

U2 - 10.1111/j.1467-937X.2010.00612.x

DO - 10.1111/j.1467-937X.2010.00612.x

M3 - Journal article

SN - 0034-6527

VL - 77

SP - 1353

EP - 1381

JO - Review of Economic Studies

JF - Review of Economic Studies

IS - 4

ER -

Modelling income processes with lots of heterogeneity

Abstract

Access to Document

Fingerprint

Cite this