I tried some full model logistics regressions and some pared down versions. I also tried the covariance greater than 0.09999 and that didn't look good. So the best logit model I found was for just the first three variables. I spent an hour on this tonight. So I have spent about 14 hours on this final project so far. I need to spend another 76 hours still. I am just printing my R session form this work.