st: margins with 4-way interaction

[Theocharis Kromydas <theocharis.kromydas@strath.ac.uk>]

Dear Statalisters

I investigate the impact of year, country of residence, educational years and years of experience on someone's employability. In sum, I run a logistic model. My dependent variable is a binary one (unemployed=0,  employed=1) and my independent ones are a dummy variable for year (0=2004, 1=2010), a dummy for country(values 1 to 19), years of education( continuous variable) and years of working experience (continuous variable). I also have some control variables for age, sex and some others. My main argument is that the four variables I mentioned before (year, country,  years of education and years of working experience) interrelate each other and it is very misleading to treat each variable independently. So I ended up having a 4-way interaction term which is not that easy to interpret. 

I run margins command, but I am not sure which options I need to use ( MEMs, AMEs or MERs?) for interpreting and plotting all these relations. Any ideas? 

I would appreciate any help to this.

Thanks
Harry

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/