estimateModelParameters: Estimate the SCAMPI model paramteres alpha, beta, mu and tau from the data

Description

Estimate the parameter values with maximum likelihood (MLE) or a method of moments approach (LSE), or both (all)

Usage

estimateModelParameters(method = "all", ccList, peptides = NULL,  numIter = 10, verbose = FALSE)

Arguments

method

method to be used for the parameter estimation; can be all (MLE and LSE, default), LSE or MLE

ccList

list of pre-processed connected components

peptides

data frame with pre-processed peptide info (only used for LSE)

numIter

number of successful munerical optimizations to perform (only used for MLE, see details)

verbose

If TRUE, detailed output is provided.

Value

Named list of vectors with at least four named elements: alphaH, betaH, muH and tauH (estimates for the four model parameters). The name of the list elements corresponds to the parameter estimation method, namely LSE or MLE.

Details

To use method="MLE" the inverses of the covariance matrices (of the connected components) are needed. Depending on the chosen parameters, this can lead to stability issues. To avoid the function from crashing, a try(...) bolck is used: the parameter estimation is performed until it was successful numIter times. Among these numIter sets, the one with the lowest negative log-likelihood value is returned.

Examples

Run this code

## Not run: 
# data("leptoSRM")
# 
# dataChecked <- checkInputData(scampi(peptides=leptoSRMpeptides, 
#                                      proteins=leptoSRMproteins, 
#                                      edgespp=leptoSRMedgespp),
#                               rescaling=FALSE)
# tmpPrepro <- preprocessInputData(dataChecked)
# dataPrepro <- tmpPrepro[["dataPrepro"]]
# ppGraph <- tmpPrepro[["ppGraph"]]
# myCCList <- tmpPrepro[["ccList"]]
# rm("tmpPrepro")
# scampiParam <- estimateModelParameters(method="all", ccList=myCCList,
#                                        peptides=dataPrepro@peptides,
#                                        numIter=10)
# ## End(Not run)