Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions

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 f...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Gluzmann, Pablo Alfredo, Panigo, Demian Tupac
Formato: Articulo
Lenguaje:Inglés
Publicado: 2015
Materias:
Ciencias Económicas
st0383
gsreg
Automatic model selection
vselect
PcGets
RETINA
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/123907
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-123907
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Económicas
st0383
gsreg
Automatic model selection
vselect
PcGets
RETINA
spellingShingle Ciencias Económicas
st0383
gsreg
Automatic model selection
vselect
PcGets
RETINA
Gluzmann, Pablo Alfredo
Panigo, Demian Tupac
Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
topic_facet Ciencias Económicas
st0383
gsreg
Automatic model selection
vselect
PcGets
RETINA
description 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.
format Articulo
Articulo
author Gluzmann, Pablo Alfredo
Panigo, Demian Tupac
author_facet Gluzmann, Pablo Alfredo
Panigo, Demian Tupac
author_sort Gluzmann, Pablo Alfredo
title Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
title_short Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
title_full Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
title_fullStr Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
title_full_unstemmed Global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
title_sort global search regression: a new automatic model-selection technique for cross-section, time-series, and panel-data regressions
publishDate 2015
url http://sedici.unlp.edu.ar/handle/10915/123907
work_keys_str_mv AT gluzmannpabloalfredo globalsearchregressionanewautomaticmodelselectiontechniqueforcrosssectiontimeseriesandpaneldataregressions
AT panigodemiantupac globalsearchregressionanewautomaticmodelselectiontechniqueforcrosssectiontimeseriesandpaneldataregressions
bdutipo_str Repositorios
_version_ 1764820450516402176

Ejemplares similares