Hi I am not familiar with glmer but maybe you can try to give to prediction only values with BMI>25. As you did not provide data nor any code something like (untested)
predict(fit, newdata=olddata[olddata$BMI>25,]) Regards Petr > -----Original Message----- > From: r-help-boun...@r-project.org [mailto:r-help-bounces@r- > project.org] On Behalf Of Alexander Snijders > Sent: Monday, September 03, 2012 1:13 PM > To: r-help@r-project.org > Subject: [R] select specific rows from regression output > > Hello everyone, > > I have a data set that contains characteristics of 25,000 patients of > 92 different hospitals. I have run a regression to capture the > probability these patients will have a complication after a certain > operation. Now, I actually want to predict the probability per patient, > using the outcome of the regression, but I just certain patients > involved in the prediction. So, I want to use the estimated parameters > of the full regression, but after that, I only want patients with > certain characteristics in my prediction matrix. For example, only > patients with BMI >25. > > My regressional formula looks as follows: fit = glmer(response ~ > sex+bmi+asa+ (1|center), data=data, family=binomial), and my normal > prediction formula: pred=fit@X %*% fit@fixef. I hope someone can help > me! > > Greetings, Alex > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting- > guide.html > and provide commented, minimal, self-contained, reproducible code. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
