Browse > Article
http://dx.doi.org/10.5351/KJAS.2008.21.2.327

Test of Model Specification in Box-Cox Transformed Regression Model with AR(1) Errors  

Cheon, Soo-Young (Dept. of Public Health Scoences, University of Virginia)
Yoon, Seok-Jin (LTD, HANHWA Securities Co)
Hwang, Sun-Young (Dept. of Statistics, Sookmyung Women's University)
Song, Seuck-Heun (Dept. of Statistics, Korea University)
Publication Information
The Korean Journal of Applied Statistics / v.21, no.2, 2008 , pp. 327-340 More about this Journal
Abstract
This paper derives joint and conditional Lagrange multiplier tests based on information matrix for testing functional form and/or the presence of autocorrelation in a regression model. Small sample properties of these tests are assessed by Monte Carlo study and comparisons are made with LM tests based on Hessian matrix. The results show that the proposed $LM_E$ tests have the most appropriate finite sample performance.
Keywords
Box-Cox regression model; model specification; autocorrelation; LM tests;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Baltagi, B. H. (1997). Testing linear and loglinear error components regressions against Box-Cox alternatives, Statistics & Probability Letters, 33, 63-68   DOI   ScienceOn
2 Box, G. E. P. and Cox, D.R. (1964). An analysis of transformations, Journal of the Royal Statistical Society, Ser. B, 26, 211-246
3 Davidson, R. and MacKinnon, J. G. (1984). Model specification test based on artificial linear regressions, International Economic Review, 25, 485-502   DOI   ScienceOn
4 Godfrey, L. G. and Wickens, M. R. (1981). Testing linear and log-linear regressions for functional form, Review of Economics Studies, 48, 487-496   DOI   ScienceOn
5 Davidson, R. and MacKinnon, J. G. (1985). Testing linear and loglinear regression against Box-Cox alternatives, Canadian Journal of Economics, 18, 499-517   DOI   ScienceOn