[R] Significance testing for paired counts data with small sample size and some genuine zero values

From: michael watson (IAH-C) <michael.watson_at_bbsrc.ac.uk>
Date: Tue, 04 Mar 2008 15:24:29 +0000

Dear All

I will try and keep this succinct! The data is counts of a particular molecule in different cell types taken from the same 5 subjects. The data are paired as they come from the same subject. The aim is to determine whether the cell types differ in terms of the abundance of each of the molecules.

I first thought of a paired two-sample t-test for each pairing of cell types, but cannot log the data due to the presence of zero values.

Next was the idea of the wilcoxon signed-rank test, but that would not work with such small sample sizes.

Two questions:

  1. what is the best way to analyse these data?
  2. (more general) what is the best approach when one wishes to log counts data that contains genuine zero values?

Many thanks

The information contained in this message may be confide...{{dropped:14}}

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. Received on Tue 04 Mar 2008 - 15:44:22 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Tue 04 Mar 2008 - 17:30:18 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive