What medical school, and are you supposed to be getting someone else to run your analysis? Have you seen this?
http://statpages.org/logistic.htmlAlso, be aware that the limiting sample size for logistic regression is the number of
events, not the number of observations, where
event = the outcome category with the lower count. To avoid overfitting the model, you should have at least 10 events per model parameter, although 15-20 events per parameter would be better.
HTH.
MladenM wrote
Hay, guys
I am looking for someone willing to help me with my science project. I need someone who can do logistic regression and here's the thing: I was doing a research on the prevalence of the early childhood caries (ECC) on the group of 112 children. Parents also got the test with 10 questions (multiple choice answers) about risk factors. I need someone to do logistic regression and find out the correlation between the risk factors and the presence of the ECC. I made the data base with all the answers and the goal is to find out witch factor or factors led to the development of ECC. I go to medical school and statistics is not something I'm familiar with and i have very little time.
If there is someone who can help me, please e-mail me to send you a data base!
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/"When all else fails, RTFM."
PLEASE NOTE THE FOLLOWING:
1. My Hotmail account is not monitored regularly. To send me an e-mail, please use the address shown above.
2. The SPSSX Discussion forum on Nabble is no longer linked to the SPSSX-L listserv administered by UGA (
https://listserv.uga.edu/).
Locked
Database.xls (66K)