Hi,

I have taken one microarray experiment and trying to implement same
statistical measures what they have done.I have taken datasets from GEO
platform with accession number GSE1557. In the experiment,about half of
double transgenic rats (dTGR) over-expressing the human renin and
angiotensinogen genes die by age 7 weeks of terminal heart failure (THF);
the other
(preterminal) half develops cardiac damage, but survives to week 7. The aim
of the study was to elucidate the difference in cardiac gene expression of
dTGR with THF compared to dTGR showing compensated cardiac hypertrophy, but
not yet THF.Experiments were conducted in age-matched 4 week-old male
untreated dTGR.Untreated dTGR were divided in two subgroups, rats with
cardiac hypertrophy (n=18) and rats with THF (n=8).Rats were killed at age 7
weeks.Total RNAs (five animals per group) were isolated from the left
ventricle.For all rgu34_a affymetrix chips were used.

Iam using maanova package. In using fitmaanova function, we have to set
variables to formula and random.Plz, suggest me what to take in formula and
random.

*fit.fix <- fitmaanova(rat, formula = ~Array+sample, random = ~Array)*
Error in fitmaanova(rat, formula = ~Array + sample, random = ~Array) :
  Not enough degree of freedom to do regression.
       You need to remove some terms in your model.
In addition: Warning message:
In any(parsed.formula$random) :
  coercing argument of type 'double' to logical
 *fit.fix <- fitmaanova(rat, formula = ~Array+sample, random = ~sample)*
Error in fitmaanova(rat, formula = ~Array + sample, random = ~sample) :
  Not enough degree of freedom to do regression.
       You need to remove some terms in your model.
In addition: Warning message:
In any(parsed.formula$random) :
  coercing argument of type 'double' to logical


But, these are working...

* fit.fix <- fitmaanova(rat, formula = ~sample, random = ~sample)*
Fitting mixed effect model...
Finish gene number 100 ...
Finish gene number 200 ...
Finish gene number 300 ...
Finish gene number 400 ...

* fit.fix <- fitmaanova(rat, formula = ~Array, random = ~Array)*
Fitting mixed effect model...
Finish gene number 100 ...
Finish gene number 200 ...
Finish gene number 300 ...
Finish gene number 400 ...
Finish gene number 500 ...
Finish gene number 600 ...
Finish gene number 700 ...
Finish gene number 800 ..


 Am unable to understand, how it is correct, as according to my experiment
.I have read all respective manuals.

        [[alternative HTML version deleted]]

______________________________________________
R-help@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.

Reply via email to