Open AccessJournal Article10.1111/J.1468-0084.2005.00143.X

Evaluating PcGets and RETINA as Automatic Model Selection Algorithms

- 01 Dec 2005

- Oxford Bulletin of Economics and Statist...

- Vol. 67, Iss: 67, pp 837-880

TL;DR: Monte Carlo simulation results assess the null and non-null rejection frequencies of the RETINA and PcGets model selection algorithms in the presence of nonlinear functions.

Abstract: The paper describes two automatic model selection algorithms, RETINA and PcGets, briefly discussing how the algorithms work and what their performance claims are. RETINA's Matlab implementation of the code is explained, then the program is compared with PcGets on the data in Perez-Amaral, Gallo and White (2005, Econometric Theory, Vol. 21, pp. 262–277), ‘A Comparison of Complementary Automatic Modelling Methods: RETINA and PcGets’, and Hoover and Perez (1999, Econometrics Journal, Vol. 2, pp. 167–191), ‘Data Mining Reconsidered: Encompassing and the General-to-specific Approach to Specification Search’. Monte Carlo simulation results assess the null and non-null rejection frequencies of the RETINA and PcGets model selection algorithms in the presence of nonlinear functions.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions in "Evaluating pcgets and retina as automatic model selection algorithms" ?

The paper describes RETINA and brie y discusses how it works and what the performance claims are.

2. What are the future works in "Evaluating pcgets and retina as automatic model selection algorithms" ?

The results are promising ; automated methods of model selection have a high level of success and should be dominant in econometric modelling in the future.. The ease with which the signi cance of non-linearities can be tested with relatively low cost is most useful.. Non-linear functions may simply be re ecting a few outliers and vastly different results may be obtained by removing these observations.. Further investigation into the types of non-linear functions that should be tested for is needed.

Table 3: RETINA and PcGets: Non-linear models from PGW excluding two outliers.

Table 20: RETINA and PcGets: linear models for Krolzig and Hendry (2001).

Table 1: RETINA and PcGets: Linear models from PGW.

Table 2: RETINA and PcGets: Linear models for PGW excluding 2 outliers.

Table 4: RETINA and PcGets: Non-linear models from PGW.

Table 8: Results for Hoover and Perez (1999) Model 3.

Citations

Journal Article•10.1057/JORS.1979.126

Forecasting Economic Time Series

Stephen Taylor

- 01 May 1979

- Journal of the Operational Research Soci...

993

Book•10.1057/9780230244405

Palgrave Handbook of Econometrics

Terence C. Mills, +1 more

- 01 Jan 2009

459

•Journal Article•10.1111/J.0013-0133.2005.00979.X

The Properties of Automatic Gets Modelling

David F. Hendry, +1 more

- 01 Mar 2005

- The Economic Journal

TL;DR: In this paper, the authors show how model selection can be non-distortionary: approximately unbiased "selection estimates" are derived, with reported standard errors close to the sampling standard deviations of the estimated DGP parameters, and a near-unbiased goodness-of-fit measure.

...read moreread less

415

Empirical Model Discovery and Theory Evaluation

David F. Hendry

- 01 Jan 2010

166

Journal Article•10.1111/J.1468-0084.2004.102_1.X

We Ran One Regression

David F. Hendry, +1 more

- 01 Dec 2004

- Oxford Bulletin of Economics and Statist...

TL;DR: Fernandez et al. as discussed by the authors showed that only one regression is really needed, namely the general unrestricted model, appropriately reduced to a parsimonious encompassing, congruent representation.

...read moreread less

164

...

Expand

References

Journal Article•10.1016/S0169-2070(96)00719-4

Testing the equality of prediction mean squared errors

David I. Harvey, +2 more

- 01 Jun 1997

- International Journal of Forecasting

TL;DR: In this article, the authors analyse the behaviour of two possible tests, and of modifications of these tests designed to circumvent shortcomings in the original formulations, and make a recommendation for one particular testing approach for practical applications.

...read moreread less

2.1K

Journal Article•10.1057/JORS.1979.126

Forecasting Economic Time Series

Stephen Taylor

- 01 May 1979

- Journal of the Operational Research Soci...

993

•Posted Content

Forecasting Economic Time Series

Michael P. Clements, +1 more

- 01 Jan 1998

- Research Papers in Economics

TL;DR: The authors provide a formal analysis of the models, procedures, and measures of economic forecasting with a view to improving forecasting practice, and they find that conclusions which can be established formally for constant-parameter stationary processes and correctly-specified models often do not hold when unrealistic assumptions are relaxed.

...read moreread less

906

Data mining reconsidered: encompassing and the general-to-specific approach to specification search

Kevin D. Hoover, +1 more

- 01 Jan 1999

TL;DR: In this article, the authors examined the efficacy of the general-to-specific modeling approach associated with the LSE school of econometrics using a simulation framework and developed a mechanical algorithm which mimics some aspects of the search procedures used by LSE practitioners.

...read moreread less

466

•Journal Article•10.1016/S0165-1889(00)00058-0

Computer automation of general-to-specific model selection procedures

Hans-Martin Krolzig, +1 more

- 01 Jun 2001

- Journal of Economic Dynamics and Control

TL;DR: In this article, the authors consider econometric model selection from a computer-automation perspective, focusing on general-to-specific reductions, embodied in PcGets.

...read moreread less

448

...

Expand

Evaluating PcGets and RETINA as Automatic Model Selection Algorithms

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions in "Evaluating pcgets and retina as automatic model selection algorithms" ?

2. What are the future works in "Evaluating pcgets and retina as automatic model selection algorithms" ?

Figures

Citations

Forecasting Economic Time Series

Palgrave Handbook of Econometrics

The Properties of Automatic Gets Modelling

Empirical Model Discovery and Theory Evaluation

We Ran One Regression

References

Testing the equality of prediction mean squared errors

Forecasting Economic Time Series

Forecasting Economic Time Series

Data mining reconsidered: encompassing and the general-to-specific approach to specification search

Computer automation of general-to-specific model selection procedures

Related Papers (5)

Data mining reconsidered: encompassing and the general-to-specific approach to specification search

Estimating the Dimension of a Model

The Properties of Automatic Gets Modelling

Computer automation of general-to-specific model selection procedures

Testing for Higher Order Serial Correlation in Regression Equations when the Regressors Include Lagged Dependent Variables