Dear List, Does anybody know how to predict an ordinal response variable from high-throughput gene expression microarray data sets. I've tried an ordinal logistic regression model by calling "lrm" function from package "Design". However, this ordinal logistic regression can only allow at most 9 X variables. Thanks, Shirley

Shirley, The globaltest package can handle binary, multinomial (nominal), and continuous response with very large numbers of predictors. I'm not sure it does ordinal response (with proportional odds), though. John Stevens Utah State University -----Original Message----- From: bioconductor-bounces@stat.math.ethz.ch [mailto:bioconductor- bounces@stat.math.ethz.ch] On Behalf Of shirley zhang Sent: Friday, October 16, 2009 9:28 AM To: Bioconductor Mailing List Subject: [BioC] predict an ordinal response variable from high- throughput gene expression data Dear List, Does anybody know how to predict an ordinal response variable from high-throughput gene expression microarray data sets. I've tried an ordinal logistic regression model by calling "lrm" function from package "Design". However, this ordinal logistic regression can only allow at most 9 X variables. Thanks, Shirley _______________________________________________ Bioconductor mailing list Bioconductor at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/bioconductor Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor