One-sample non-parametric test

[Martin P. Holt-2]

Hi,

I'm using version 12.01. I'm looking for a non-parametric single sample
test. I expect to find the Wilcoxon signed rank test for a single sample,
but I can't find it. There's the Kolmogorov-Smirnov test, but I understand
that to be for testing normality. I feel I must be missing something, so I'm
turning to the list. Any ideas ?

TIA,

Martin

[Jennifer Thompson]

Hi Martin,

If you go to Analyse > Nonparametric tests > 2 related samples you
should find the Wilcoxen test.

Cheers,

Jennifer

On 9/29/06, Martin P. Holt <[hidden email]> wrote:

> Hi,
>
> I'm using version 12.01. I'm looking for a non-parametric single sample
> test. I expect to find the Wilcoxon signed rank test for a single sample,
> but I can't find it. There's the Kolmogorov-Smirnov test, but I understand
> that to be for testing normality. I feel I must be missing something, so I'm
> turning to the list. Any ideas ?
>
> TIA,
>
> Martin
>

[Marta García-Granero]

Hi Martin

You have to trick SPSS to be able to run the one sample Wilcoxon
signed ranks test: compute a new variable (actually, a constant) with
the value of the population median, then run a paired samples Wilcoxon
test pairing your variable with the one with the population median.

MPH> I'm using version 12.01. I'm looking for a non-parametric single sample
MPH> test. I expect to find the Wilcoxon signed rank test for a single sample,
MPH> but I can't find it. There's the Kolmogorov-Smirnov test, but I understand
MPH> that to be for testing normality. I feel I must be missing something, so I'm
MPH> turning to the list. Any ideas ?




--
Regards,
Dr. Marta García-Granero,PhD           mailto:[hidden email]
Statistician

---
"It is unwise to use a statistical procedure whose use one does
not understand. SPSS syntax guide cannot supply this knowledge, and it
is certainly no substitute for the basic understanding of statistics
and statistical thinking that is essential for the wise choice of
methods and the correct interpretation of their results".

(Adapted from WinPepi manual - I'm sure Joe Abrahmson will not mind)

[Martin P. Holt-2]

Thanks, Jennifer. But this is a two-sample test - the Wilcoxon name seems to
get everywhere ! I'm looking for the single sample test, or an equivalent.

Best Wishes,

Martin

[Martin P. Holt-2]

Thanks, Marta....that worked a treat.

Best Regards,

Martin