Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: significances

To   stata <>
Subject   st: significances
Date   Thu, 27 Jul 2006 09:20:45 +0200


I analyse data from a study: I have to calculate p-values to check if the
percentage of symptoms by patients and controls are significantly different.

I have data before treatment, after and at follow up (by control only before).

For control versus patients at admission (before) I receive a correctly
calculated p-value.
E.g.: tab febbef thapatient, exact

MY PROBLEM is to calculate the p-values over time:
I tried to do "before versus after" and "before versus follow-up", but that
gives "false p-values" (not what I'm looking for).

E.g.: tab febbef febaft, exact
      tab febbef febcon, exact

febbef: fever at admission (control + patients)
febaft: fever after treatment (only patients)
febfol: fever at follow-up (only patients)
thapatient: if =1 it's a HAT patient if =0 it's a control

Is there another method to calculate p-values over time? perhaps ANOVA test?
(but I don't understand for what that really is and how does it function)

I hope I was clear by my explanation.

I would be happy if someone could help me!



This message was sent using IMP, the Internet Messaging Program.

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index