[R-sig-Geo] Cliff and Ord modified t-test for autocorrelated datasets

[Roger Bivand]

On Wed, 1 Aug 2007, Marco Helbich wrote:

> Dear list,
>
> I've got two autocorrelated datasets and want to perform a two-sample t-test
> comparing the means. Because of the autocorrelation the t-test assumtions
> are violated. In Cliff & Ord (1981, Spatial Processes, Ch. 7.2) I read that
> there is an alternative modified t-test, which considers autocorrelation. Is
> such a test implemented in R or somewhere else? Can anybody give me a
> helping hand?

The test isn't implemented as far as I know, but it shouldn't be too 
difficult to try, all of the bits to do the first kind (7.4, 7.8, 7.9) are 
present. What is really needed is a reproducible example so that an 
implementation in R could be checked. I'll see if I still have a copy of 
the 1975 paper somewhere, full-text is not (yet) available for Environment 
& Planning.

Hope this helps,

Roger

>
> I appreciate every hint! Thanks.
> Marco
> __________________
>
> Marco Helbich
> ISR
> Postgasse 7/4/2
> A-1010, Vienna
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no