Dear experts, I am using the LASSO method (a shrinkage and selection method for linear regression) to create regression models. I am using the package "glmnet" My aim is to calculate an overall p-value for a certain regression model with a certain lambda. I would like to do this with a likelihood ratio test. Therefore, I need the likelihood of the model.
Unfortunately, for the function "glmnet" I can find only in the documentary the output "dev" which is explained as "The fraction of (null) deviance explained (for "elnet", this is the R-square). The deviance calculations incorporate weights if present in the model. The deviance is defined to be -2*(loglike_sat - loglike), where loglike_sat is the loglikelihood for the saturated model (a model with a free parameter per observation)". Actually, is there a way to get directly the likelihood of a certain model? Thank you so much Holger -- View this message in context: http://r.789695.n4.nabble.com/overall-p-value-for-LASSO-model-resulting-from-glmnet-tp3013699p3013699.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ 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.