Bootstrapped Durbin– Watson Test of Autocorrelation for Small Samples
DOI:
https://doi.org/10.18034/abcjar.v3i2.39Keywords:
Bootstrap, Durbin-Watson test, Autocorrelation, Recursive BootstrapAbstract
The Durbin-Watson (DW) test is the most widely used test for autocorrelation of a first order in regression analysis. The critical value of DW test depends on X matrix. As a result, the DW test statistic falls sometime in the inconclusive region. For large sample, the DW test can be used for normal distribution. In this paper, we proposed a bootstrap critical value for small sample and compared the power properties with other procedures. Monte-Carlo study shows that the bootstrapped DW test performs better than the usual DW test with the help of power.Downloads
References
Abrahamse, A. P. J and Koerts (1969). A comparison between the power of the Durbin Watson test and the power of the BLUS test, Journal of Statistical Association, 64,938-948.
Basak, T., Rois, R., and Majumder, A. K. (2003) One sided version of the Brush-Godfrey test for testing Higher –order Autocorrelation-A distance based approach, Role of the Statistician in Achieving the Millennium Development Goals, conference papers, Bangladesh Statistical Association.
Canjels, E. (2002). A Permutation Version of the Durbin-Watson Test for Serial Correlation, Working Paper, New School University, New York.
Draper, N. R., and Smith, H. (1966). Applied Regression Analysis, John Wiley and Sons, New York.
Durbin, J., and Watson, G. S. (1971). Testing for serial correlation in least squares regression, Econometrics, 58, 1-19.
Gujarati, D. N. (2003). Basic Econometrics, 4th edition, McGraw Hill, New York.
Leong, J. and Chung, S. (2001). Bootstrap test for autocorrelation, Computational Statistics and Data Analysis, 38 (1), 49-69.
MacKinon, G. J. (2002). Bootstrap inference in econometrics, Canadian Journal of 615-645.
MacKinon, G. J. (2005). Bootstrap methods in econometrics, working paper, Department of Economics, Queen’s University, Canada.
Majumder, A. K. (1999). One sided and partially one sided hypothesis testing in econometrics, An unpublished thesis, Monash University, Australia.
Shively, T. S., Ansley, C. F. and Kohn, R. (1990). Fast evaluation of the distribution of the Durbin-Watson and other invariant test statistics in time series regression, Journal of American Statistical Association, 85, 676-685.
--0--
Downloads
Published
Issue
Section
License
How to Cite
