Skip to content

Power analysis for MANOVA?

9 messages · Stephan Kolassa, Mitchell Maltenfort, Adam D. I. Kramer +1 more

#
Hello,

 	I have searched and failed for a program or script or method to
conduct a power analysis for a MANOVA. My interest is a fairly simple case
of 5 dependent variables and a single two-level categorical predictor
(though the categories aren't balanced).

 	If anybody happens to know of a script that will do this in R, I'd
love to know of it! Otherwise, I'll see about writing one myself.

 	What I currently see is this, from help.search("power"):

stats::power.anova.test
                         Power calculations for balanced one-way
                         analysis of variance tests
stats::power.prop.test
                         Power calculations two sample test for
                         proportions
stats::power.t.test     Power calculations for one and two sample t
                         tests

 	Any references on power in MANOVA would also be helpful, though of
course I will do my own lit search for them myself.

Cordially,
Adam D. I. Kramer
#
Hi Adam,

My (and, judging from previous traffic on R-help about power analyses, 
also some other people's) preferred approach is to simply simulate an 
effect size you would like to detect a couple of thousand times, run 
your proposed analysis and look how often you get significance. In your 
simple case, this should be quite easy.

HTH,
Stephan


Adam D. I. Kramer schrieb:
#
http://www.amazon.com/Statistical-Power-Analysis-Behavioral-Sciences/dp/0805802835

Cohen's book was in fact the basis for the "pwr" package at CRAN.

And it does have a MANOVA power analysis, which was left out of the
"pwr" package.
On Mon, Jan 26, 2009 at 4:12 PM, Adam D. I. Kramer <adik at ilovebacon.org> wrote:

  
    
#
On Mon, 26 Jan 2009, Stephan Kolassa wrote:

            
I actually don't have much experience running monte-carlo designs like
this...so while I'd certainly prefer a bootstrapping method like this one,
simulating the effect size given my constraints isn't something I've done
before.

The MANOVA procedure takes 5 dependent variables, and determines what
combination of the variables best discriminates the two levels of my
independent variable...then the discrimination rate is represented in the
statistic (Pillai's V=.00019), which is then tested (F[5,18653] = 0.71).  So
coming up with a set of constraints that would produce V=.00019 given my
data set doesn't quite sound trivial...so I'll go for the "par" library
reference mentioned earlier before I try this.  That said, if anyone can
refer me to a tool that will help me out (or an instruction manual for RNG),
I'd also be much obliged.

Many thanks,
Adam
#
If you know what a 'general linear hypothesis test' is see

 	http://cran.r-project.org/src/contrib/Archive/hpower/hpower_0.1-0.tar.gz

HTH,

Chuck
On Mon, 26 Jan 2009, Adam D. I. Kramer wrote:

            
Charles C. Berry                            (858) 534-2098
                                             Dept of Family/Preventive Medicine
E mailto:cberry at tajo.ucsd.edu	            UC San Diego
http://famprevmed.ucsd.edu/faculty/cberry/  La Jolla, San Diego 92093-0901
#
On Mon, 26 Jan 2009, Charles C. Berry wrote:

            
I do, and am quite interested, however this package will not install on R
2.8.1: First, it said that there was no "maintainer" in the description, so
I added one (figuring that the 1991 date of the package was to blame),
however it still will not compile:

parmesan:tmp$ sudo R CMD INSTALL hpower/
* Installing to library '/usr/local/lib/R/library'
* Installing *source* package 'hpower' ...
** R
** preparing package for lazy loading
Error in parse(n = -1, file = file) : unexpected '{' at
5: ##
6: pfnc_function(q,df1,df2,lm,iprec=c(6)) {
Calls: <Anonymous> -> code2LazyLoadDB -> sys.source -> parse
Execution halted
ERROR: lazy loading failed for package 'hpower'
** Removing '/usr/local/lib/R/library/hpower'
parmesan:tmp$

...any tips?

--Adam
#
On Mon, 26 Jan 2009, Adam D. I. Kramer wrote:

            
_________^_________

AHA!

That underscore is the old 'assignment' operator - now no longer allowed.

Do a global replace of '_' with ' <- ' in the R/*.R files and it should 
install.

HTH,

Chuck
Charles C. Berry                            (858) 534-2098
                                             Dept of Family/Preventive Medicine
E mailto:cberry at tajo.ucsd.edu	            UC San Diego
http://famprevmed.ucsd.edu/faculty/cberry/  La Jolla, San Diego 92093-0901
1 day later
#
Hi Adam,

first: I really don't know much about MANOVA, so I sadly can't help you 
without learning about it an Pillai's V... which I would be glad to do, 
but I really don't have the time right now. Sorry!

Second: you seem to be doing a kind of "post-hoc power analysis", "my 
result isn't significant, perhaps that's due to low power? Let's look at 
the power of my experiment!" My impression is that "post-hoc power 
analysis" and its interpretation is, shall we say, not entirely accepted 
within the statistical community, see:

Hoenig, J. M., & Heisey, D. M. (2001, February). The abuse of power: The 
pervasive fallacy of power calculations for data analysis. The American 
Statistician, 55 (1), 1-6

And this:
http://staff.pubhealth.ku.dk/~bxc/SDC-courses/power.pdf

However, I am sure that lots of people can discuss this more competently 
than me...

Best wishes
Stephan


Adam D. I. Kramer schrieb:
1 day later
#
Thanks for the response, Stephan.

Really, I am trying to say, "My result is insignificant, my effect sizes are
tiny, you may want to consider the possibility that there really are no
meaningful differences." Computing post-hoc power makes a bit stronger of a
claim in this setting.

My real goal in this case was to put a single line on a poster that says,
"Significance using our estimates would require N observations, which is
larger than the population." I am trying to solve for N.  N in this case is
a sort of effect size.  In this case, it is indeed a simple transformation
of Pillai's V and the p-value for the study, and I do not intend to suggest
that it is anything more than that.  However, I believe that the latter
effect size makes a much more compelling case, given that a lot of people
(such as yourself) don't have much experience with Pillai's V.

--Adam
On Wed, 28 Jan 2009, Stephan Kolassa wrote: