[BioC] ERROR: No residual degrees of freedom in linear model fits

Gordon K Smyth smyth at wehi.EDU.AU
Sat Apr 26 03:11:28 CEST 2014


Dear Jesus,

The error message seems reasonably self explanatory.

The data needs to have replicate samples (i.e., there should be more 
microarrays than there are columns to the design matrix), otherwise it is 
impossible to estimate variability or to do any statistical tests.

This is a basic requirement of any statistical analysis, even a simple 
univariate t-test.

Your data appears to have no replicates.

Best wishes
Gordon

> Date: Thu, 24 Apr 2014 19:40:50 +0000
> From: jesus urbano <jdug22 at hotmail.com>
> To: "bioconductor at stat.math.ethz.ch" <bioconductor at stat.math.ethz.ch>
> Subject: [BioC] ERROR: No residual degrees of freedom in linear model
> 	fits
>
> Dear group,
>
> On trying to use eBayes function in a microarray analysis, I received the next error:
>
> Error in ebayes(fit = fit, proportion = proportion, stdev.coef.lim = stdev.coef.lim,  :
>  No residual degrees of freedom in linear model fits
>
> I would be very pleasant if you could give me a solution to this problem 
> or show me another way to obtain a toptable without use the eBayes 
> function.
>
>
> Thanks you very much for your attention.
>
> Jesús D.

______________________________________________________________________
The information in this email is confidential and intend...{{dropped:5}}


More information about the Bioconductor mailing list