Volume 44, Number 173,
April-June 2013
Automatic Stabilization and Social Security:
Brazil, Mexico, Costa Rica and Chile
Eloy Fisher
ESTIMATION METHODS AND ECONOMETRICS MODELING ( ...continuation )

Model 1 (aols)

Whereis the first difference in logs between the flow (in and out) for country i in time t, is the current unemployment rate in logs for country i in time t, is the natural unemployment rate in logs for country i in time t (estimated since 1980, is the first difference in the cyclical variation for unemployment in logs, is the first difference in inflation for country i in time t and is the error in the model. Likewise, in light of the fact that the Chilean program is not contribution-based, a second set of regressions were ran to check if the program structure had some type of effect on the aggregate results.

Secondly, an overall estimate F test was conducted (Hausman test) to measure the relevance of an estimator of fixed effects. This test involves measuring if there are significant differences in the regression constants that appear in the sample and looking for the presence of fixed effects. Another evaluation was performed to check whether an estimate of a panel of random effects was the most appropriate (Breusch-Pagan test). As shown in the results below, this estimate is possible through aols instead of using a panel model.

Not rejecting the null hypothesis for both tests points to the fact that the aols estimate is appropriate, and thus it is consistently verified that there are no significant fixed effects for our specifications. To account this discrepancy, our estimate also uses the Anderson-Hsiao method to specify a self-regressing model. In this model, our specification assumes the following form:

Model 2 (Anderson-Hsiao)

Where is the difference of the independent variable and . Unlike the first model, a constant is not included (because the residual is included as a group effect). Still, by differentiating the specification, the building error influences the dependent variable. In this sense, to eliminate this endogeneity, an additional difference was used as a pre-determined variable to decontaminate the specification.

The results of the estimates appear in the fifth section. The following paragraphs offer a brief description of the sample programs in the countries.

Published in Mexico, 2012-2017 © D.R. Universidad Nacional Autónoma de México (UNAM).
PROBLEMAS DEL DESARROLLO. REVISTA LATINOAMERICANA DE ECONOMÍA, Volume 48, Number 191, October-December 2017 is a quarterly publication by the Universidad Nacional Autónoma de México, Ciudad Universitaria, Coyoacán, CP 04510, México, D.F. by Instituto de Investigaciones Económicas, Circuito Mario de la Cueva, Ciudad Universitaria, Coyoacán,
CP 04510, México, D.F. Tel (52 55) 56 23 01 05 and (52 55) 56 24 23 39, fax (52 55) 56 23 00 97, www.probdes.iiec.unam.mx, revprode@unam.mx. Journal Editor: Alicia Girón González. Reservation of rights to exclusive use of the title: 04-2012-070613560300-203, ISSN: pending. Person responsible for the latest update of this issue: Minerva García, Circuito Maestro Mario de la Cueva s/n, Ciudad Universitaria, Coyoacán, CP 04510, México D.F., latest update: Nov 13th, 2017.
The opinions expressed by authors do not necessarily reflect those of the editor of the publication.
Permission to reproduce all or part of the published texts is granted provided the source is cited in full including the web address.
Credits | Contact

The online journal Problemas del Desarrollo. Revista Latinoamericana de Economía corresponds to the printed edition of the same title with ISSN 0301-7036