i have Time series problem i can run model after i treat Y using Lag and rerun the model and test D-w test again and if it above the limit or near to 2 is ok?
What do you mean by near to 2?
Are you doing univariate analysis?
I am guessing that Abdalla is referring to the traditional "acceptable" threshold of the Durban-Watson statistic.
There are many different tests for assessing autocorrelation in time series data. I would recommend the Cumby-Huizinga test, or the Arellano and Bond test instead. They provide much more meaningful output, incuding statistical tests. See the following references (among others):
Arellano, M., Bond, S., 1991. Some tests of specification for panel data: Monte Carlo evidence and an application to employment equations. Review of Economic Studies, 58:2, 277-297.
Cumby, R. E. and Huizinga, J. 1992. Testing the autocorrelation structure of disturbances in ordinary least squares and instrumental variables regressions. Econometrica, 60:1, 185-195.
I hope this helps
Ariel
You can use OLS Method for univariate Lag Model but the residual distribution must be normal. The DW statistic will lie in the range of 0 to 4, with a value near 2 indicating no first order autocorrelation. Positive autocorrelation is associated with DW
values below 2, and negative autocorrelation is associated with DW values
above 2. I hope you get the answer.
Ahammad Hossain
Lecturer, Department of Natural Science, Varendra University
- Badges
- Science topic