You'll need to tell us more before anyone can be much help.
1. Is there only one treatment A, or are there several treatments to
be compared?
2. Is "time" important (in the sense of length of time between initial
and final measures, for example, not just in distinguishing
between "before" and "after")?
3. What models (of the behavior of your variable "X" as a function of
your treatment(s) "A") have you in mind?
On Tue, 20 Feb 2001, DSJAY wrote:
> I am now handling a experiment about the effect of treatment A on test
> X with time. Same measurement of test X are done before and after
> treatment A in different time interval. Some people used paired t-test
> to investigate the results and some used ANOVA to analyze the data.
>
> I think paired t-test and ANOVA are not suitable in this case.
Why do you think so? What about either model strikes you as unsuitable,
or not adequately representing the situation? (And which particular
ANOVA model(s) are you referring to? It seems unlikely in the extreme
that there is NO analysis-of-variance model that would apply to the
situation you have (Ohowever inadequately) described.
> I am [in?] doubt about what kind of test is suitable. Any suggestion?
Not without more descriptive information.
----------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 (603) 535-2597
Department of Mathematics, Boston University [EMAIL PROTECTED]
111 Cummington Street, room 261, Boston, MA 02215 (617) 353-5288
184 Nashua Road, Bedford, NH 03110 (603) 471-7128
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
