[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Error component models

From   Dimitris Pavlopoulos <>
Subject   st: Error component models
Date   Wed, 07 Nov 2007 13:48:24 +0100

Dear statalisters,

I want to run an error component model for earnings in the framework of Ramos (2003), Cappellari (2004), Dickens (2000). These models extend the typical random effects model

y_it = m_i + e_it

by applying several specifications to the individual effects m_i (random walk, random growth) and to the error term e_it (AR(1) or ARMA models). An example is the following model of Ramos (2003):

y_icat = g_c * a_t [m_i + h_i * a_it + u_iat] + z_c * v_it

u_iat = u_i(a-1)(t-1) + p_iat
v_it = r * v_it + l_t * e_it

and i stands for the individual, c for cohort, a for age, t for time. g_c and a_t are shifters for cohort and time respectively.

These models are estimated with the use of minimum distance estimation. Estimation of some these models is possible in SAS. Does anyone know how to estimate them in STATA? Is there any module for them? I have found references to an old module from L. Cappellari (mindist) that was presented in one Stata meeting but it does not appear anywhere. Moreover, from what I understand it does not cover all the usual specifications that are used in the literature.

I would very much appreciate your help.

Best regards,


Cappellari, L. (2004). The dynamics and inequality of Italian men?s earnings. long-term changes or transitory fluctuations. Journal of Human Resources, 39 (2), 475-499.

Dickens, R. (2000b). The evolution of individual male earnings in Great Britain: 1975-95. Economic Journal, 110, 27-49.

Ramos, X. (2003). The covariance structure of earnings in Great Britain, 1991-1999. Economica, 70, 353-374.


* For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index