R help - Nov 2011 - One-way repeated measures ANOVA

Hi all,

I'm trying to run a repeated measures ANOVA on some univariate ecological
data that was collected over two growing seasons. I ran the test using the
methodology found on this website:

http://rtutorialseries.blogspot.com/2011/02/r-tutorial-series-one-way-repeated.html

Upon running the actual ANOVA I got this error message:

"> rmanova=anova(yearmodel, idata=yearframe, idesign=~yearfactor)
Warning message:
In function (object, ..., test = c("Pillai", "Wilks",
"Hotelling-Lawley",  :
  models with response "NULL" removed because response differs from
model 1"

And the p-values I get in the anova summary are completely off, judging by
the t-tests I did on the same data.

The dataset is small (n=6) and was arranged so that the data from the two
different years was arranged in two columns ("2010", "2011).

I've pasted the rest of the code below for reference. I'd appreciate any
suggestions as to what the issue here is!

Thanks,
Varina

transect=read.csv("Transect data.csv")

attach(transect)


replicates=c(1,2)

yearfactor=as.factor(replicates)

yearframe=data.frame(yearfactor)

yearbind=cbind(transect$TP10, transect$TP11)

yearmodel=lm(yearbind~1)


rmanova=anova(yearmodel, idata=yearframe, idesign=~yearfactor)

summary(rmanova)

	[[alternative HTML version deleted]]

Dear Varina,

I think that you may be confusing the Anova() function in the car package
(which takes an idesign argument) with the standard R anova() function.

I hope this helps,
 John

--------------------------------
John Fox
Senator William McMaster
  Professor of Social Statistics
Department of Sociology
McMaster University
Hamilton, Ontario, Canada
http://socserv.mcmaster.ca/jfox



> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Varina Crisfield
> Sent: November-18-11 10:11 AM
> To: r-help at r-project.org
> Subject: [R] One-way repeated measures ANOVA
> 
> Hi all,
> 
> I'm trying to run a repeated measures ANOVA on some univariate
> ecological data that was collected over two growing seasons. I ran the
> test using the methodology found on this website:
> 
> http://rtutorialseries.blogspot.com/2011/02/r-tutorial-series-one-way-
> repeated.html
> 
> Upon running the actual ANOVA I got this error message:
> 
> "> rmanova=anova(yearmodel, idata=yearframe, idesign=~yearfactor)
> Warning message:
> In function (object, ..., test = c("Pillai", "Wilks",
"Hotelling-
> Lawley",  :
>   models with response "NULL" removed because response differs
from
> model 1"
> 
> And the p-values I get in the anova summary are completely off, judging
> by the t-tests I did on the same data.
> 
> The dataset is small (n=6) and was arranged so that the data from the
> two different years was arranged in two columns ("2010",
"2011).
> 
> I've pasted the rest of the code below for reference. I'd
appreciate
> any suggestions as to what the issue here is!
> 
> Thanks,
> Varina
> 
> transect=read.csv("Transect data.csv")
> 
> attach(transect)
> 
> 
> replicates=c(1,2)
> 
> yearfactor=as.factor(replicates)
> 
> yearframe=data.frame(yearfactor)
> 
> yearbind=cbind(transect$TP10, transect$TP11)
> 
> yearmodel=lm(yearbind~1)
> 
> 
> rmanova=anova(yearmodel, idata=yearframe, idesign=~yearfactor)
> 
> summary(rmanova)
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.