# Tag Info

5

There are quite a few ways to work around it. Jittering the variables mildly to smear the lines apart First, since both age and the outcome are nicely discrete, we can afford to mildly jitter them in order to show some trends. The trick is to use transparency in the line color so that it's easier to discern the magnitude of overlapping. library(geepack) ...

4

This is perfectly fine. You are considering two different variables each measured once per subject. One contains the 'pre' values, the other the 'post' values. I think you are mixing up independence between observations (subjects) and independence of variables. Please note that in your situation, you might want to analyze differences between pre and post, ...

4

None of those correlations you think aren't OK really aren't OK. The correlation is just a measure of linear relationship. Sometimes you need to know the extent of a relationship that you know exists, such as this one, or any of the others you listed. In this case they may want to know the amount of correlation for a variety of reasons ranging from needing ...

3

I think it depends on what you are trying to do with your data. Technically, it is okay to correlate repeated measures from the same subject in the sense that it is mathematically possible. But if you trying to draw some kind of inference (for example, causality) from your data, simply correlated two observations that are from the same subject is not going ...

1

You can estimate the intraclass correlation coefficient (ICC) (wikipedia link). It tells you how correlated the behavioral responses are for the same individual. It is defined as: $$ICC = \tau^2 / (\tau^2 + \sigma^2),$$ where $\tau^2$ is the "intercept" variance and $\sigma^2$ is the residual variance. Substituting the estimated values into the equation ...

1

It depends on 1) How much data is missing and 2) Why there is missing data. If there is very little missing then your 3 methods will give approximately equal results; the median is probably better than the mean, since it isn't affected by outliers, but deletion won't do too much damage unless the data are very not missing at random (see below). If there is ...

1

I think your request for the "overall correlation" may be asking the wrong question. If you already know that you have varied factor1 and factor2, the correlations you want to look for are conditional the combination of those factors. It is unlikely the independent variables have absolutely 0 effect on the dependent variables, so looking at the total ...

Only top voted, non community-wiki answers of a minimum length are eligible