R help - Mar 2007 - where can I find Durbin-Waston test tables for Confidence Level 2.5% or 0.5%?

Hi all,

I am doing a two-sided DW test:

H0: rho = 0
H1: rho =/= 0

My understanding is that most test statistics tables are one-sided. It's the
way they created the table.

So from online, by doing Googling, I found a bunch of DW tables for
Confidence Level 5%.

Those tables can answer my two-sided question at 5x2 = 10% confidence level.

But what if I want two-sided test at 1% and 5% confidence level?

Then I need 0.5% and 2.5% tables on those one-sided table.

My sample size is 278, and the number of parameters is 2, these adds to the
hardship of finding a good table...

Could anybody give me some pointers of two-sided DW tables or 1-sided DW
table with 0.5% and 2.5% confidence levels?

Thanks a lot!

Moreover, I appreciate any pointers about electronic tables that I can use
in programs, I want to implement DW test myself, but let the program
searching a table automatically...

Thanks a lot!

	[[alternative HTML version deleted]]

Michael:
> I am doing a two-sided DW test:
>
> H0: rho = 0
> H1: rho =/= 0
>
> My understanding is that most test statistics tables are one-sided.
It's the
> way they created the table.
...because rho > 0 is the alternative of interest in most applications.
> So from online, by doing Googling, I found a bunch of DW tables for
> Confidence Level 5%.
Using tables for the DW test is difficult because it's distribution 
depends on the particular set of regressors used. The tables of DW just 
give upper and lower bounds.

Back when the DW test was suggested, tables was the only way to make 
application of the test feasible. Today, you would either use the exact 
combination of chi-square distributions or an asymptotic approximation 
(both implemented in dwtest() from "lmtest") or a bootstrap
approximation
(implemented in durbin.watson() from "car"). For 278 observations, the
normal approximation should be sufficient.

hth,
Z

Michael wrote:
> Hi all,
> 
> I am doing a two-sided DW test:
> 
> H0: rho = 0
> H1: rho =/= 0
> 
> My understanding is that most test statistics tables are one-sided.
It's the
> way they created the table.
> 
> So from online, by doing Googling, I found a bunch of DW tables for
> Confidence Level 5%.
> 
> Those tables can answer my two-sided question at 5x2 = 10% confidence
level.
> 
> But what if I want two-sided test at 1% and 5% confidence level?
> 
> Then I need 0.5% and 2.5% tables on those one-sided table.
> 
> My sample size is 278, and the number of parameters is 2, these adds to the
> hardship of finding a good table...
> 
> Could anybody give me some pointers of two-sided DW tables or 1-sided DW
> table with 0.5% and 2.5% confidence levels?
> 
> Thanks a lot!
> 
> Moreover, I appreciate any pointers about electronic tables that I can use
> in programs, I want to implement DW test myself, but let the program
> searching a table automatically...
  Are you aware of the implementations of this test in the car, lmtest,
and fMultivar packages?

RSiteSearch("Durbin-Watson", restrict="function") finds
those functions.
> Thanks a lot!
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code. 
-- 
Chuck Cleland, Ph.D.
NDRI, Inc.
71 West 23rd Street, 8th floor
New York, NY 10010
tel: (212) 845-4495 (Tu, Th)
tel: (732) 512-0171 (M, W, F)
fax: (917) 438-0894