Hi everyone, sorry if this is a stupid question!

I am doing a study into the effects of sleep deprivation on risk taking. I have one independent variable which is sleep deprivation and three dependent variables which are all measures of risk taking (Risk Score, Hazard Perception Score, and Sensation Seeking Scale score).

To analyse the data (in SPSS) I have used a MANOVA with the fixed factor set as the groups tested (2 groups: control group non-sleep deprived and the test group who are sleep deprived) and the dependent variables set as the ones mentioned above.

The results of the MANOVA indicate that the groups tested do have an affect on my dependent variables (as a whole and separately). If what I have done so far is correct (big if) what should my next step be as I would like to know what this affect is, I'm thinking perhaps a Pearson's correlation or linear regression?

Thank you for your time and help!

Hey Redrum,

I am familiar with SPSS and various other data software programs (SPS JMP, DataDesk, R, etc.). This stuff is not always easy. Do you mind explaining how you are able to say this: "The results of the MANOVA indicate that the groups tested do have an affect on my dependent variables (as a whole and separately)." Hypothesis tests? Statistics? Error?

There are a quite a few ways to tackle this, and I have used SPSS pretty recently (and also own a pretty thick and expensive book on it). If you want to attach a data set in whatever format you have, I could look over it and act as another set of eyes. I may or may not be able to direct you some.

For your own edification/convenience, allow me to list the Assumptions of Manova from Discovering Statistics Using SPSS by Andy Field (second edition): (Of course, you may already know all this)

1) Independence: Are your observations statistically independent?

2) Random Sampling: Your data should be randomly sampled from the population of interest and measured at an interval level.

3) Multivariate normality: In ANOVA, we assume that our dependent variable is normally distributed within each group. In the case of MANOVA, we assume that the dependent variables (collectively) have multivariate normality with groups.

4) Homogeneity of covariance matrices: In ANOVA, it is assumed that the variances in each group are roughly equal (homogeneity of variance). In MANOVA we must assume that this is true for each dependent variable, but also that the correlation between any two dependent variables is the same in all groups. This assumption is examined by testing whether the population variance-covariance matrices of the different groups in the analysis are equal.

You are also, of course, free to PM me. Hopefully I can be of some help.
-Andy