#This function is to trace the selection path
selpath(data, weights, ranktable, ncores, family, C, alpha_u):ranking table from ranking step
:generalized model families
the dataframe should be arranged in the way such that columns are X1,X2,X3....,Xp, status. Where Xi's are variables and status is the outcome(for the logistic regression, the outcome is 0/1)
no of parallel computing cores
the number of permutation times
the upper significance level
In a binomial model, weights: =TRUE: if weighted version is desired; =FALSE, otherwise ; In other models,weights: =vector of weights of the same size as the sample size N: if weighted version is desired;=FALSE, otherwise (other generalized model)
selpoint: a list. it contains each selected variable point,information includes 1)vslist: the variable sect before selecting this variable listed in 'selvar' 2)alpha.range: the variable will be selected within this alpha range 3)pval: pvalue of the variable 4)selvar:selected variable 5)vslist:variable sect after selecting the variable listed in 'selvar'
sel.nodes: a list. deviance distributions used for selecting the new variable; it includes 1)vslist: the variable sect before the new selection 2)dev.dist: the permutation for selecting the new variable 3)vtlist that has i)pval: pvalue of the proposed variable ii)selvar: selected variable (the proposed variable is NULL if not selected) iii)dev:deviance contributed by the proposed variable