Re: test for small paired sample size

Knut Krueger wrote:
Hi to all
is there any meaningful analysis for the following data:
a: 62 57 230

b: 10587 5721 3550

we have only three pairs of data and everybody can realize that "a" is
increasing and "b" is decreasing. But is there any statistical function
for such a small sample size to get any "p-value" (for the journals...)

Well you could do an ANCOVA, and the p-value for the slope being different is just under 0.05. But quite frankly, I would tell the journal to sod off if they insist on p-values, and suggest that the editors learn to use their common sense (hmm, I might not express it in quite those terms, though). Just be clear that any test is not justified, because of the small sample size.

Bob

--
Bob O'Hara

Dept. of Mathematics and Statistics
P.O. Box 68 (Gustaf Hällströmin katu 2b)
FIN-00014 University of Helsinki
Finland

Telephone: +358-9-191 51479
Mobile: +358 50 599 0540
Fax: +358-9-191 51400
WWW: http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results - EEB: http://www.jnr-eeb.org
.

Relevant Pages

  • test for small paired sample size
    ... is there any meaningful analysis for the following data: ... But is there any statistical function for such a small sample size to get any "p-value" ... With regards Knut ...
    (sci.stat.edu)
  • test for small paired sample size
    ... is there any meaningful analysis for the following data: ... But is there any statistical function ... for such a small sample size to get any "p-value" ... With regards Knut ...
    (sci.stat.math)