On Fri, 04 Jul 2003 10:56:43 GMT, "BarBarella" <[EMAIL PROTECTED]> wrote:
> Sorry for my english. I need help. I want to do analysis of variance for > repeated measures (two independent variables one of 2 levels and second 3 > levels) and I want to make contrast between level nr 1 and (level nr > 2,3)from the second variable Is it statisticly correct to do such analisys? > I will make this on Statistica. The ordinary test for contrasts in repeated measures, these days, is performed as a paired t-test between the cells -- that is, similar to the one-sampled test that the contrast is zero when it is scored up and tested alone. That is the good way of testing (even) the trend components, and, IIRC, it is how BMDP used to do those tests. I don't know what the other packages do, for trends or otherwise; so I would want to carry out the t-tests to check, even if I could specify the contrasts in the ANOVA. - Maybe someone else will know about the packages. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html "Taxes are the price we pay for civilization." Justice Holmes. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
