[BioC] Sample size calculation - microarray experiemnt

Claus-Dieter Mayer claus at bioss.ac.uk
Thu Jul 12 18:27:14 CEST 2007

Hi Sharon,

the one term you are missing in your description is the varianceof a 
gene or (as this will differ from gene to gene) the whole variance 
distribution across genes. Without any knowledge about that it is 
impossible to answer your question.

One tool that comes to mind is the poweratlas page (www.poweratlas.org). 
As far as I remember they look at a two group comparisons only though. 
Its an interesting question, but not easy to answer, so I would be 
interested whether anybody else on the list has more wisdom to offer.

Best Wishes


Sharon wrote:
> Hi,
> We are planning to conduct a microarray time series experiment, for which we
> doing the power analysis. Our experiment will have 2 factors: time (at 10
> levels)  and treatment (at 3 levels). If we control the false positives at P
> < 0.05 (FDR),  how many samples do we require to obtain reasonable power to
> detect 1.5 fold change?
> I am aware of 2 BioC packages: ssize and sizepower, which help us to do
> power calculation. These 2 packages do not include 2-way ANOVA design. Are
> there any other packages available for sample size calculation? It will be
> of great help if you could provide pointers to useful resources.
> Thanks in advance.
> Best regards,
> Sharon
> 	[[alternative HTML version deleted]]
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor

 Dr Claus-D. Mayer                    | http://www.bioss.ac.uk
 Biomathematics & Statistics Scotland | email: claus at bioss.ac.uk
 Rowett Research Institute            | Telephone: +44 (0) 1224 716652
 Aberdeen AB21 9SB, Scotland, UK.     | Fax: +44 (0) 1224 715349

More information about the Bioconductor mailing list