Global search regression: A new automatic model-selection technique for cross-section, time-series, and panel-data regressions
Pablo Gluzmann
Center for Distributive, Labor and Social Studies
Argentine National Council of Scientific and Technological Research
and National University of La Plata
La Plata, Argentina
[email protected]
|
Demian Panigo
Center for Worker Innovation
Argentine National Council of Scientific and Technological Research
National University of Moreno
and National University of La Plata
La Plata, Argentina
[email protected]
|
Abstract. In this article, we present gsreg, a new automatic model-selection
technique for cross-section, time-series, and panel-data regressions. Like
other exhaustive search algorithms (for example, vselect), gsreg
avoids characteristic path-dependence traps of standard approaches as well as
backward- and forwardlooking approaches (like PcGets or relevant transformation
of the inputs network approach). However, gsreg is the first code that
1) guarantees optimality with out-of-sample selection criteria; 2) allows
residual testing for each alternative; and 3) provides (depending on user
specifications) a full-information dataset with outcome statistics for every
alternative model.
View all articles by these authors:
Pablo Gluzmann, Demian Panigo
View all articles with these keywords:
gsreg, automatic model selection, vselect, PcGets, RETINA
Download citation: BibTeX RIS
Download citation and abstract: BibTeX RIS
|
