Cause Y is belong to [0, 1], when I try the linear regression, I get a lot of negative predicted value when doing the forecast, so I would like to try the logistic regression.

The problem I meet is that, is there any hypothesis for using logistic regression? I choose the family as binomial, the model result is what I would like to see, but I remember that binomial is for 0, 1(classified) problem, can I model the loss rate this way here? Do I need to do any hypothesis test?

Thanks for the kindly help. ]]>

I have some experimental data for animals with tumours. Unfortunately, they were not followed individually during a time course, but evaluated as groups. As a result, I have 6 predictors only for animals that have survived for each time point. I would like to test which of these covariates significantly increases/decreases the chance of survival. Is there a way to still use Cox's regression, or there are better options? ]]>

For my dissertation I am looking at the temporal order of physiological and behavioural events before a voluntary action. I have 12 different repeated measures variables including: Time of intention (W), Readiness potential 1 (as measured by task A) Readiness potential 2 (task A), RPmax (task A), ERDalpha(task A), ERDbeta (task A), Time of probed intention (T), Readiness potential 1 (as measured by task B) Readiness potential 2 (task B), RPmax (task B), ERDalpha(task B), ERDbeta (task B).

And with these variables in order to establish the order of events I need to make many many comparisons (and use the appropriate bonferroni correction).

My issue is that some of the variables are normally distributed and some aren't - for example, time of intention (W) is normally distributed, but Readiness potential is not.

I know that if one of your varibles is not normallly distributed, you should use a non-parametric test ie Wilcoxons. But should I be using Wilcoxons for some of theses comparisons and then for the odd comparison jump back to a t-test? Or should I just use Wilcoxons for all my comparisons?

Thanks ]]>