This function is a wrapper from the STPGA package to obtain the best subset of individuals to predict a group of individuals minimizing the predicted error variance (PEV). Is used internally in the TP.prep function.
PEV(PCAs,candidates,Test,ntoselect, npop, nelite, mutprob, niterations, lambda)
nxk PCA matrix from the predictor variables.
vector of names for the population without the test set.
name of the individuals in the test or VP set.
number of individuals to select in the training population.
number of solutions at each iteration.
number of elite solutions for TP pops.
probability of mutation for each solution
number of iterations
scalar shrinkage in PEV.
If all parameters are correctly indicated the program will return:
a list with the names of the TP populations. Each element of the list corresponds to each population size specified in the 'tp.size' argument.
Akdemir, Deniz. "Training population selection for breeding value" prediction. 2014.