Dear R-helper,
Please suggest some methods for my question below.
We measured the amount of protein A in patient blood in pre-treatment and
post-treatment condition from 32 patients.
--------------------------------------------
Pre-treatment Post-treatment
Pat1 25 28
Pat2 19 15
Pat3 94 89
...
Pat32 49 23
------------------------------------------------
How can we prove that the treatment did not make any difference in the
amount of protein A. In another word, Pre- and post- are the same.
1) I assume that a paired t-test can work, but can I prove a null hypothesis
by not-rejecting it?
2) If I use correlation test, the best I can get is to reject a null
hypothesis that is the correlation is 0. This seems not good enough to say
treatment does not make difference. Will it be good enough by adding a Rho
value?
3) Will regression work by showing the estimate of Beta is 1?
If I have multivariate results: not only protein A, but we also tested
protein B, protein C... and total 25 different proteins for each patient in
pre- and post-conditions. How can I summary if pre- and post condition makes
difference?
Thank you so much!
Xiang
[[alternative HTML version deleted]]
Xiang Gao-2 wrote:> > How can we prove that the treatment did not make any difference in the > amount of protein A. In another word, Pre- and post- are the same. >There is no way to "prove" that there is no difference. While you could use some alternative hypothesis, people rarely understand the combination of an assumption in mm and a p-value. The preferred way in medical context is to quote the 90% confidence interval of the difference. When you say "The confidence interval of the difference between implant type A and B is -0.2 to 0.3 mm of new tooth bone growth", you give a hint about the reliability of your measurement, and leave it to the reader to judge if this is medically relevant. The story is that the new treatment with only 5% probability leads to 0.2 mm less growth (pardon, strictly not correct, but you must tell the story ...). It might be relevant for dental implants, and not relevant for the thigh. Dieter -- View this message in context: http://n4.nabble.com/how-to-prove-that-the-factor-makes-no-difference-tp1695224p1695368.html Sent from the R help mailing list archive at Nabble.com.