Regression Models with Data-based Indicator Variables
Ordinary least squares estimation of an impulse-indicator coefficient is inconsistent, but its variance can be consistently estimated. Although the ratio of the inconsistent estimator to its standard error has a "t"-distribution, that test is inconsistent: one solution is to form an index of indicators. We provide Monte Carlo evidence that including a plethora of indicators need not distort model selection, permitting the use of many dummies in a general-to-specific framework. Although <link rid="b22">White's (1980)</link> heteroskedasticity test is incorrectly sized in that context, we suggest an easy alteration. Finally, a possible modification to impulse 'intercept corrections' is considered. Copyright 2005 Blackwell Publishing Ltd.
Year of publication: |
2005
|
---|---|
Authors: | Hendry, David F. ; Santos, Carlos |
Published in: |
Oxford Bulletin of Economics and Statistics. - Department of Economics, ISSN 0305-9049. - Vol. 67.2005, 5, p. 571-595
|
Publisher: |
Department of Economics |
Saved in:
Saved in favorites
Similar items by person
-
Regression Models with Data-based Indicator Variables link rid="fn1">*
Hendry, David F., (2005)
-
Regression Models with Data-based Indicator Variables
Hendry, David F., (2004)
-
Selecting a Regression Saturated by Indicators
Johansen, Søren, (2007)
- More ...