[R] R] observed power
Mark M. Span
span at psy.uva.nl
Mon Jan 29 09:43:23 CET 2001
----- Original Message -----
From: "Mark M. Span" <span at psy.uva.nl>
To: "Peter Dalgaard BSA" <p.dalgaard at biostat.ku.dk>
Sent: Monday, January 29, 2001 9:42 AM
Subject: Re: [R] observed power
> Also to me, power is more an a priori concept, best estimated before
> collecting the data. And a priori power analyses are definitely the best
way
> to control beta error probabilities. However, sometimes it may be
impossible
> to control the sample size, for example, when re-analyzing data sets that
> have been collected by others, or even comparing between analysis within
one
> experiment. In a case like this post hoc power analyses can make sense.
>
> You magically 'feld' that I referred to the SPSS output of a ANOVA, as I
> did. The manual of SPSS describes this as:
>
> - Select Observed power to obtain the power of the test when the
alternative
> hypothesis is set based on the observed value.
>
> which is very non-informative to me.
>
> The reason I wanted to compute this 'observed power' is to get an
indication
> weather my (non-significant) interaction is caused by the absence of an
> effect (observed power = 'quite high') or because I have too little
subjects
> to identify any effect.
>
> Of course I can always make an SPSS sidestep to calculate this, and my
first
> mail should not be interpreted as a critique to aov output nor as a
mission
> statement that an index for 'observed power' should be included in R. I
was
> just wondering if something *like* this is available.
>
> As for Peter Dalgaard's second mail: I am getting more and more convinced
> that SPSS indeed 'plugs in' the sampling estimates into the power
function.
>
>
>
> From: "Peter Dalgaard BSA" <p.dalgaard at biostat.ku.dk>
>
> > "Mark M. Span" <span at psy.uva.nl> writes:
> >
> > > Is there a way to obtain the observed power of an aov()?
> > >
> > > I perform an aov with one between and one within factor, and would
like
> to
> > > know the observed power of the tests, both for the main effect and the
> > > interaction. I found the package 'hpower', but sense there is a more
> > > convenient possibility. Is there?
> > >
> > > thanks
> > >
> > > Mark M. Span
> >
> > What's "observed power"? If you mean the item that SPSS has by that
> > name, I think you first have to convince us that that is a sensible
> > thing to calculate...
> >
> > --
> > O__ ---- Peter Dalgaard Blegdamsvej 3
> > c/ /'_ --- Dept. of Biostatistics 2200 Cph. N
> > (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
> > ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907
>
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
More information about the R-help
mailing list