Hidalgo, Javier (2007) Specification testing for regression models with dependent data. EM, 518. Suntory and Toyota International Centres for Economics and Related Disciplines, London School of Economics and Political Science, London, UK.
Download (406Kb) | Preview
We describe and examine a consistent test for the correct specification of a regression function with dependent data. The test is based on the supremum of the difference between the parametric and nonparametric estimates of the regression model. Rather surprisingly, the behaviour of the test depends on whether the regressors are deterministic or stochastic. In the former situation, the normalization constants necessary to obtain the limiting Gumbel distribution are data dependent and difficult to estimate, so to obtain valid critical values may be difficult, whereas in the latter, the asymptotic distribution may not be even known. Because of that, under very mild regularity conditions we describe a bootstrap analogue for the test, showing its asymptotic validity and finite sample behaviour in a small Monte Carlo experiment.
|Item Type:||Monograph (Discussion Paper)|
|Additional Information:||© 2007 Javier Hildago|
|Uncontrolled Keywords:||Functional specification. Variable selection. Nonparametric kernel regression. Frequency domain bootstrap|
|Library of Congress subject classification:||H Social Sciences > HB Economic Theory|
|Journal of Economic Literature Classification System:||C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods: General > C14 - Semiparametric and Nonparametric Methods
C - Mathematical and Quantitative Methods > C2 - Econometric Methods: Single Equation Models; Single Variables > C22 - Time-Series Models
|Sets:||Collections > Economists Online
Research centres and groups > Suntory and Toyota International Centres for Economics and Related Disciplines (STICERD)
Departments > Economics
Actions (login required)
|Record administration - authorised staff only|