\name{nemModelSelection}
\alias{nemModelSelection}

\title{model selection for nested effect models}
\description{Infers models with different regularization constants, compares them via the AIC criterion and returns the highest scoring one}
\usage{
nemModelSelection(lambdas,D,inference="nem.greedy",models=NULL,type="mLL",para=NULL,hyperpara=NULL,Pe=NULL,Pmlocal=NULL,Pm=NULL,local.prior.size=length(unique(colnames(D))),local.prior.bias=1,triples.thrsh=0.5,delta=1,selEGenes=FALSE,trans.close=TRUE,verbose=TRUE,...)
}

\arguments{
  \item{lambdas}{vector of regularization constants}
  \item{D}{data matrix with experiments in the columns (binary or continious)}
  \item{inference}{\code{search} to use exhaustive enumeration; or \code{triples} for triple-based inference; or \code{pairwise} for the pairwise heuristic; or \code{ModuleNetwork} for the module based inference; or \code{nem.greedy} for the greedy hillclimbing}
  \item{models}{a list of adjacency matrices for model search. If NULL, \code{enumerate.models} is used for exhaustive enumeration of all possible models.}
  \item{type}{\code{mLL} or \code{FULLmLL} or \code{CONTmLL} or \code{CONTmLLBayes} or \code{CONTmLLMAP}, see \code{nem}}
  \item{para}{vector of length two: false positive rate and false negative rate for binary data. Used by \code{mLL}} 
  \item{hyperpara}{vector of length four: used by \code{FULLmLL} for binary data}
  \item{Pe}{prior of effect reporter positions in the phenotypic hierarchy (same dimension as D)}
  \item{Pm}{prior over models (n x n matrix)}
  \item{Pmlocal}{local model prior for pairwise and triple learning. For pairwise learning generated by \code{local.model.prior} according to arguments \code{local.prior.size} and \code{local.prior.bias}}
  \item{local.prior.size}{prior expected number of edges in the graph (for pairwise learning)}
  \item{local.prior.bias}{bias towards double-headed edges. Default: 1 (no bias; for pairwise learning)}
  \item{triples.thrsh}{threshold for model averaging to combine triple models for each edge}  
  \item{delta}{regularization parameter for automated E-gene subset selection (CONTmLLMAP only)}
  \item{selEGenes}{automated E-gene subset selection (includes tuning of delta for CONTmLLMAP)}  
  \item{trans.close}{Should always transitive closed graphs be computed? Default: TRUE. NOTE: This has only an impact for the  \code{nem.greedyMAP} method.}
  \item{verbose}{do you want to see progression statements? Default: TRUE}
  \item{...}{other arguments to pass to function \code{nem} or \code{network.AIC}}
}
\details{
  \code{nemModelSelection} internally calls \code{nem} to infer a model with a given regularization constant. The comparison between models is based on the BIC or AIC criterion, depending on the parameters passed to \code{network.AIC}.
  
}
\value{
  nem object
}

\author{Holger Froehlich}


\seealso{\code{\link{nem}}, \code{\link{network.AIC}}}
\examples{
   data("BoutrosRNAi2002")
   D <- BoutrosRNAiDiscrete[,9:16]
   p <- c(.13,.05)
   res <- nemModelSelection(c(0.1,1,10),D, para=p, Pm=matrix(0,ncol=4,nrow=4))   
   
   
   plot(res,main="highest scoring model")      
}
\keyword{graphs}
\keyword{models}