A Predictive Approach for Selection of Diffusion Index Models

Tomohiro Ando, Ruey S. Tsay

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this article, we propose a predictive mean squared error criterion for selecting diffusion index models, which are useful in forecasting when many predictors are available. A special feature of the proposed criterion is that it takes into account the uncertainty in estimated common factors. The new criterion is based on estimating the predictive mean squared error in forecasting with correction for asymptotic bias. The resulting estimate of bias-corrected forecast-error is shown to be consistent. The proposed criterion is a natural extension of the traditional Akaike information criterion (AIC), but it does not require the distributional assumptions for the likelihood. Results of real data analysis and Monte Carlo simulations demonstrate that the proposed criterion works well in comparison with the commonly used AIC and Bayesian information criteria.

Original languageEnglish
Pages (from-to)68-99
Number of pages32
JournalEconometric Reviews
Volume33
Issue number1-4
DOIs
Publication statusPublished - 2014 Feb

Fingerprint

Index model
Diffusion index
Akaike information criterion
Mean squared error
Predictors
Common factors
Forecast error
Monte Carlo simulation
Asymptotic bias
Bayesian information criterion
Uncertainty

Keywords

  • Approximate factor model
  • Common factor
  • Generated regressor
  • Panel data
  • Predictive measure

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

A Predictive Approach for Selection of Diffusion Index Models. / Ando, Tomohiro; Tsay, Ruey S.

In: Econometric Reviews, Vol. 33, No. 1-4, 02.2014, p. 68-99.

Research output: Contribution to journalArticle

Ando, Tomohiro ; Tsay, Ruey S. / A Predictive Approach for Selection of Diffusion Index Models. In: Econometric Reviews. 2014 ; Vol. 33, No. 1-4. pp. 68-99.
@article{f8db38ae41794b228547fe2396fbd30e,
title = "A Predictive Approach for Selection of Diffusion Index Models",
abstract = "In this article, we propose a predictive mean squared error criterion for selecting diffusion index models, which are useful in forecasting when many predictors are available. A special feature of the proposed criterion is that it takes into account the uncertainty in estimated common factors. The new criterion is based on estimating the predictive mean squared error in forecasting with correction for asymptotic bias. The resulting estimate of bias-corrected forecast-error is shown to be consistent. The proposed criterion is a natural extension of the traditional Akaike information criterion (AIC), but it does not require the distributional assumptions for the likelihood. Results of real data analysis and Monte Carlo simulations demonstrate that the proposed criterion works well in comparison with the commonly used AIC and Bayesian information criteria.",
keywords = "Approximate factor model, Common factor, Generated regressor, Panel data, Predictive measure",
author = "Tomohiro Ando and Tsay, {Ruey S.}",
year = "2014",
month = "2",
doi = "10.1080/07474938.2013.807105",
language = "English",
volume = "33",
pages = "68--99",
journal = "Econometric Reviews",
issn = "0747-4938",
publisher = "Taylor and Francis Ltd.",
number = "1-4",

}

TY - JOUR

T1 - A Predictive Approach for Selection of Diffusion Index Models

AU - Ando, Tomohiro

AU - Tsay, Ruey S.

PY - 2014/2

Y1 - 2014/2

N2 - In this article, we propose a predictive mean squared error criterion for selecting diffusion index models, which are useful in forecasting when many predictors are available. A special feature of the proposed criterion is that it takes into account the uncertainty in estimated common factors. The new criterion is based on estimating the predictive mean squared error in forecasting with correction for asymptotic bias. The resulting estimate of bias-corrected forecast-error is shown to be consistent. The proposed criterion is a natural extension of the traditional Akaike information criterion (AIC), but it does not require the distributional assumptions for the likelihood. Results of real data analysis and Monte Carlo simulations demonstrate that the proposed criterion works well in comparison with the commonly used AIC and Bayesian information criteria.

AB - In this article, we propose a predictive mean squared error criterion for selecting diffusion index models, which are useful in forecasting when many predictors are available. A special feature of the proposed criterion is that it takes into account the uncertainty in estimated common factors. The new criterion is based on estimating the predictive mean squared error in forecasting with correction for asymptotic bias. The resulting estimate of bias-corrected forecast-error is shown to be consistent. The proposed criterion is a natural extension of the traditional Akaike information criterion (AIC), but it does not require the distributional assumptions for the likelihood. Results of real data analysis and Monte Carlo simulations demonstrate that the proposed criterion works well in comparison with the commonly used AIC and Bayesian information criteria.

KW - Approximate factor model

KW - Common factor

KW - Generated regressor

KW - Panel data

KW - Predictive measure

UR - http://www.scopus.com/inward/record.url?scp=84885359114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885359114&partnerID=8YFLogxK

U2 - 10.1080/07474938.2013.807105

DO - 10.1080/07474938.2013.807105

M3 - Article

AN - SCOPUS:84885359114

VL - 33

SP - 68

EP - 99

JO - Econometric Reviews

JF - Econometric Reviews

SN - 0747-4938

IS - 1-4

ER -