DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?

DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?

We test two questions: (i) Is the Bayesian Information Criterion (BIC) more parsimonious thanAkaike Information Criterion (AIC)? and(ii) Is BICbetter than AIC for forecasting purposes? By using simulated data, we provide statistical inference of both hypotheses individually and then jointly with a m...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: MEDEL,CARLOS A, SALGADO,SERGIO C
Lenguaje:English
Publicado: ILADES. Universidad Alberto Hurtado. 2013
Materias:
AIC
BIC
information criteria
time-series models
overfitting
forecast comparison
joint hypothesis testing
Acceso en línea:http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-88702013000100003
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:scielo:S0718-88702013000100003
record_format dspace
spelling oai:scielo:S0718-887020130001000032013-07-23DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?MEDEL,CARLOS ASALGADO,SERGIO C AIC BIC information criteria time-series models overfitting forecast comparison joint hypothesis testing We test two questions: (i) Is the Bayesian Information Criterion (BIC) more parsimonious thanAkaike Information Criterion (AIC)? and(ii) Is BICbetter than AIC for forecasting purposes? By using simulated data, we provide statistical inference of both hypotheses individually and then jointly with a multiple hypotheses testing procedure to control better for type-I error. Both testing procedures deliver the same result: The BIC shows an in- and out-of-sample superiority over AIC only in a long-sample context.info:eu-repo/semantics/openAccessILADES. Universidad Alberto Hurtado.Revista de análisis económico v.28 n.1 20132013-04-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-88702013000100003en10.4067/S0718-88702013000100003
institution Scielo Chile
collection Scielo Chile
language English
topic AIC
BIC
information criteria
time-series models
overfitting
forecast comparison
joint hypothesis testing
spellingShingle AIC
BIC
information criteria
time-series models
overfitting
forecast comparison
joint hypothesis testing
MEDEL,CARLOS A
SALGADO,SERGIO C
DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?
description We test two questions: (i) Is the Bayesian Information Criterion (BIC) more parsimonious thanAkaike Information Criterion (AIC)? and(ii) Is BICbetter than AIC for forecasting purposes? By using simulated data, we provide statistical inference of both hypotheses individually and then jointly with a multiple hypotheses testing procedure to control better for type-I error. Both testing procedures deliver the same result: The BIC shows an in- and out-of-sample superiority over AIC only in a long-sample context.
author MEDEL,CARLOS A
SALGADO,SERGIO C
author_facet MEDEL,CARLOS A
SALGADO,SERGIO C
author_sort MEDEL,CARLOS A
title DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?
title_short DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?
title_full DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?
title_fullStr DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?
title_full_unstemmed DOES THE BIC ESTIMATE AND FORECAST BETTER THAN THE AIC?
title_sort does the bic estimate and forecast better than the aic?
publisher ILADES. Universidad Alberto Hurtado.
publishDate 2013
url http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-88702013000100003
work_keys_str_mv AT medelcarlosa doesthebicestimateandforecastbetterthantheaic
AT salgadosergioc doesthebicestimateandforecastbetterthantheaic
_version_ 1714206209836318720

Ejemplares similares