Alternative for a multi-level analysis

Hi all,

For my criminology thesis I am analysing police interviews and would like to research the effect (the presence of) an attorney has on whether or not a suspect gives a statement. The statement will be a dichotomous variable (0 = remaining silent 1 = giving a statement). My data is nested in the sense that I have a couple of variables on the level of the interrogation (1st, 2nd, 3rd interview and such) and on the level of the suspect himself (age, criminal career etc).

The best method, as far as I know, is doing a multi-level logistisch regression analysis tot determine whether the attorney has any influence. The problem is that I don't have the correct knowledge or experience to perform such an analysis and I don't know anyone who can. Also, I am working with SPSS and I've understood that SPSS can only do linear multi-level regressions.

Is there any alternative method I could use?

Also, the problem with performing a 'normal' logistic regression without taking the hierarchy into account is that the variables from level 2 will be disaggregated to level 1. Will this problem be solved if I only take (for instance) the first interview from every case and use that as input for the analysis? Most subjects are interviewed multiple times.

Thanks in advance for any advice. Should you have any questions, then please let me know.


Less is more. Stay pure. Stay poor.
How much time do you plan to take in doing this (months, years)?

Don't use SPSS, then.

Yeah, an option is to just look at time one data, but this will change your questions.