R help - Jul 2008 - interpreting mixed model anova results

Hi, I am trying to do a repeated measures ANOVA to determine if there is a
significant difference between two sets of timecourse data. Each individual
was given a single treatment and then measured for one variable for 10 days.
Here is made-up example of what my data would look like:

data<-data.frame(subject=rep(c("A1","A2","A3","B1","B2","B3"),10),treatment=rep(c("A","B"),each=3),
day=rep(c(1:10),each=6),response=rnorm(60))

This is the code I run to test for a difference between treatments A and B
over the course of the 10 days:

aov(response~day*treatment+Error(subject), data=data)

I believe this is the correct model to use, though I could definitely be
wrong.

Here is the output I get from my actual data (using summary(aov)):

Error: subject
          Df Sum Sq Mean Sq F value   Pr(>F)
treatment  1 4258.1  4258.1  12.588 0.001344 **
Residuals 29 9810.2   338.3
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1

Error: Within
               Df Sum Sq Mean Sq F value    Pr(>F)
day             9  98345   10927 150.313 < 2.2e-16 ***
day:treatment   9   6844     760  10.461 8.374e-14 ***
Residuals     261  18974      73
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1


The p-value for "treatment" is the same as what I would get if I
lumped the
data from all 10 days together, so I assume this is not what I want here.
However, am I correct in interpreting the p-value for day:treatment as what
I want? Does this tell me that there is a difference between the two groups
over the course of the 10 days (regardless of which days actually are
different) with respect to the fact that I am measuring the same subjects
each day?

Thanks for any help!
-- 
Brooke LaFlamme

	[[alternative HTML version deleted]]

Sounds like a repeated measures design, if so then you have to incorporate
this into your model before interpreting the results. 


Brooke LaFlamme-2 wrote:
> 
> Hi, I am trying to do a repeated measures ANOVA to determine if there is a
> significant difference between two sets of timecourse data. Each
> individual
> was given a single treatment and then measured for one variable for 10
> days.
> Here is made-up example of what my data would look like:
> 
>
data<-data.frame(subject=rep(c("A1","A2","A3","B1","B2","B3"),10),treatment=rep(c("A","B"),each=3),
> day=rep(c(1:10),each=6),response=rnorm(60))
> 
> This is the code I run to test for a difference between treatments A and B
> over the course of the 10 days:
> 
> aov(response~day*treatment+Error(subject), data=data)
> 
> I believe this is the correct model to use, though I could definitely be
> wrong.
> 
> Here is the output I get from my actual data (using summary(aov)):
> 
> Error: subject
>           Df Sum Sq Mean Sq F value   Pr(>F)
> treatment  1 4258.1  4258.1  12.588 0.001344 **
> Residuals 29 9810.2   338.3
> ---
> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
> 
> Error: Within
>                Df Sum Sq Mean Sq F value    Pr(>F)
> day             9  98345   10927 150.313 < 2.2e-16 ***
> day:treatment   9   6844     760  10.461 8.374e-14 ***
> Residuals     261  18974      73
> ---
> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
> 
> 
> The p-value for "treatment" is the same as what I would get if I
lumped
> the
> data from all 10 days together, so I assume this is not what I want here.
> However, am I correct in interpreting the p-value for day:treatment as
> what
> I want? Does this tell me that there is a difference between the two
> groups
> over the course of the 10 days (regardless of which days actually are
> different) with respect to the fact that I am measuring the same subjects
> each day?
> 
> Thanks for any help!
> -- 
> Brooke LaFlamme
> 
> 	[[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.
> 
> 
-- 
View this message in context:
http://www.nabble.com/interpreting-mixed-model-anova-results-tp18298521p18299363.html
Sent from the R help mailing list archive at Nabble.com.