The Properties of Automatic "GETS" Modelling
After reviewing the simulation performance of general-to-specific automatic regression-model selection, as embodied in "PcGets", we 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. The handling of theory-based restrictions, non-stationarity and problems posed by collinear data are considered. Finally, we consider how "PcGets" can handle three 'intractable' problems: more variables than observations in regression analysis; perfectly collinear regressors; and modelling simultaneous equations without "a priori" restrictions. Copyright 2005 Royal Economic Society.
Year of publication: |
2005
|
---|---|
Authors: | Hendry, David F. ; Krolzig, Hans-Martin |
Published in: |
Economic Journal. - Royal Economic Society - RES, ISSN 1468-0297. - Vol. 115.2005, 502, p. 32-32
|
Publisher: |
Royal Economic Society - RES |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Automatic model selection: a new instrument for social science
Hendry, David F., (2004)
-
Hendry, David F., (2004)
-
Sub-sample model selection procedures in general-to-specific modelling
Hendry, David F., (2004)
- More ...