RE: [R] the test result is quite different,why?

From: John Fox <jfox_at_mcmaster.ca>
Date: Sun 05 Jun 2005 - 00:58:48 EST


Dear ronggui,

You're fitted different variance models: in bptest(), you're modeling the variance using any linear combination of the predictors, while in ncv.test() you're modeling the variance as a function of the fitted values, which is more restrictive. BTW, both bptest() and ncv.test() can do both of these tests.

John



John Fox
Department of Sociology
McMaster University
Hamilton, Ontario
Canada L8S 4M4
905-525-9140x23604
http://socserv.mcmaster.ca/jfox

> -----Original Message-----
> From: r-help-bounces@stat.math.ethz.ch
> [mailto:r-help-bounces@stat.math.ethz.ch] On Behalf Of ronggui
> Sent: Friday, June 03, 2005 9:59 PM
> To: r-help@stat.math.ethz.ch
> Subject: [R] the test result is quite different,why?
>
> data:http://fmwww.bc.edu/ec-p/data/wooldridge/CRIME4.dta
>
> > a$call
> lm(formula = clcrmrte ~ factor(year) + clprbarr + clprbcon +
> clprbpri + clavgsen + clpolpc, data = cri)
> > bptest(a,st=F)
>
> Breusch-Pagan test
>
> data: a
> BP = 34.4936, df = 10, p-value = 0.0001523
>
> > bptest(a,st=T)
>
> studentized Breusch-Pagan test
>
> data: a
> BP = 10.9297, df = 10, p-value = 0.363
>
> > ncv.test(a)
> $formula
> ~fitted.values
>
> $formula.name
> [1] "Variance"
>
> $ChiSquare
> [1] 1.163501
>
> $Df
> [1] 1
>
> $p
> [1] 0.2807406
>
> $test
> [1] "Non-constant Variance Score Test"
>
> attr(,"class")
> [1] "chisq.test"
> >
>
> ______________________________________________
> R-help@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



R-help@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 Received on Sun Jun 05 01:11:28 2005

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:32:22 EST