[R] Writing summary.aov results to a file which can be opened in Excel

Julia_2010 jelsayed at imperial.ac.uk
Sat Apr 3 02:06:37 CEST 2010


Hi everyone,

I'm fairly new to R (and this forum!), so first of all apologies if this
question has already been answered (I've tried searching the forum but
haven't come across anything which has solved the problem I'm having).

I have a data frame containing an "independent variable" and a series of
potential "dependent variables",  and I'd like to find the "dependent
variable" with the strongest association to my "independent variable"
(essentially my "dependent variables" are principal components and the
"independent variable" is a systemic factor which may correlate with
one/several of the PCs and account for batch effects seen in the data I'm
working with. There may be a better way of getting at this but if there is I
don't know it!). 

Searching through a number of different forums, I decided that the manova
command might be appropriate for my purposes.  

I've carried out a MANOVA in R as follows:

depvariablesmatrix <-cbind(variables[,6:1248]) #produce a data frame
containing my dependent variables
MANOVA <- manova(as.matrix(depvariablesmatrix) ~
as.factor(variables$independentvariable))

I can access the results of this using the following:
MANOVA_results <-summary.aov(MANOVA)

This produces a list of all my results in the following format:
 
Response depvariable1 :
                                 Df  Sum Sq Mean Sq F value    Pr(>F)    
as.factor(variables$independentvariable)   55 0.58179 0.01058  30.024 <
2.2e-16 ***
Residuals                      1187 0.41821 0.00035                      
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 

 Response depvariable2:
                                 Df  Sum Sq Mean Sq F value    Pr(>F)    
as.factor(variables$independentvariable)   55 0.78587 0.01429  79.207 <
2.2e-16 ***
Residuals                      1187 0.21413 0.00018                      
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 

 Response depvariable3 :
                                 Df  Sum Sq Mean Sq F value    Pr(>F)    
as.factor(variables$independentvariable)   55 0.41267 0.00750  15.164 <
2.2e-16 ***
Residuals                      1187 0.58733 0.00049                      
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 


....etc for all my 1243 potential dependent variables. 

What I'd like to do is write these in a table format so that I can open
these results in Excel, (essentially to sort by Pr(>F)), however when I try
to write these results to a file I get the following error:

Error in as.data.frame.default(x[[i]], optional = TRUE, stringsAsFactors =
stringsAsFactors) : 
  c("cannot coerce class \"summary.aov\" into a data.frame", "cannot coerce
class \"listof\" into a data.frame")

I've tried using capture.output instead of write.table, however this doesn't
produce a tab-delimited file I can sort in Excel. 

Would anyone be able to tell me how to write these results to a
tab-delimited file which I can open and sort in Excel?

I'd appreciate any help or advice you can offer. 

Thanks!
Julia
-- 
View this message in context: http://n4.nabble.com/Writing-summary-aov-results-to-a-file-which-can-be-opened-in-Excel-tp1749775p1749775.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list