grouplasso2pop_gt_cv_fixedgrid: Choose tuning parameters by crossvalidation for...

In gregorkb/semipadd2pop: Combine two data sets to fit semiparametric additive models

Choose tuning parameters by crossvalidation for grouplasso2pop_gt when given a fixed grid of lambda and eta values

Description

Choose tuning parameters by crossvalidation for grouplasso2pop_gt when given a fixed grid of lambda and eta values

Usage

grouplasso2pop_gt_cv_fixedgrid(
  Y1,
  Z1,
  Se1,
  Sp1,
  X1,
  groups1,
  E.approx1 = FALSE,
  Y2,
  Z2,
  Se2,
  Sp2,
  X2,
  groups2,
  E.approx2 = FALSE,
  rho1,
  rho2,
  lambda.seq,
  eta.seq,
  n.folds,
  b1.init.arr,
  b2.init.arr,
  w1,
  w2,
  w,
  AA1,
  AA2,
  Com,
  tol = 0.001,
  maxiter = 500,
  report.prog = TRUE
)

Arguments

Y1	Group testing output for data set 1 in the format as output by one of the functions individual.assay.gen, masterpool.assay.gen, dorfman.assay.gen, or array.assay.gen.
Z1	Group testing output for data set 1 in the format as output by one of the functions individual.assay.gen, masterpool.assay.gen, dorfman.assay.gen, or array.assay.gen.
Se1	A vector of testing sensitivities, where the first element is the testing specificity for pools and the second entry is the test specificity for individual testing, if applicable.
Sp1	A vector of testing specificities, where the first element is the testing specificity for pools and the second entry is the test specificity for individual testing, if applicable.
X1	the matrix with the observed covariate values for data set 1 (including a column of ones for the intercept)
groups1	a vector indicating to which group each covariate of data set 2 belongs
E.approx1	a logical indicating whether the conditional expectations in the E-step should be computed approximately or exactly for data set 1
Y2	Group testing output for data set 2 in the format as output by one of the functions individual.assay.gen, masterpool.assay.gen, dorfman.assay.gen, or array.assay.gen.
Z2	Group testing output for data set 2 in the format as output by one of the functions individual.assay.gen, masterpool.assay.gen, dorfman.assay.gen, or array.assay.gen.
Se2	A vector of testing sensitivities, where the first element is the testing specificity for pools and the second entry is the test specificity for individual testing, if applicable.
Sp2	A vector of testing specificities, where the first element is the testing specificity for pools and the second entry is the test specificity for individual testing, if applicable.
X2	the matrix with the observed covariate values for data set 2 (including a column of ones for the intercept)
groups2	a vector indicating to which group each covariate of data set 2 belongs
E.approx2	a logical indicating whether the conditional expectations in the E-step should be computed approximately or exactly for data set 2
rho1	weight placed on the first data set
rho2	weight placed on the second data set
lambda.seq	the sequence of lambda values
eta.seq	the sequence of eta values
n.folds	the number of crossvalidation folds
b1.init.arr	array of initial values for beta1
b2.init.arr	array of initial values for beta2
w1	group-specific weights for different penalization across groups in data set 1
w2	group-specific weights for different penalization across groups in data set 2
w	group-specific weights for different penalization toward similarity for different groups
AA1	a list of the matrices A2j
Com	the indices of the covariate groups which are common in the two datasets
tol	a convergence criterion
maxiter	the maximum allowed number of iterations (EM steps)

Value

a list containing the fits over a grid of lambda and eta values as well as the vector of lambda values and the vector of eta values

Examples

grouplasso2pop_gt_data <- get_grouplasso2pop_data( n1 = 1000, n2 = 1200, response = "gt")

grouplasso2pop_gt_grid.out <- grouplasso2pop_gt_grid(Y1 = grouplasso2pop_gt_data$Y1$I,
                                                     Z1 = grouplasso2pop_gt_data$Y1$A,
                                                     Se1 = grouplasso2pop_gt_data$Y1$Se,
                                                     Sp1 = grouplasso2pop_gt_data$Y1$Sp,
                                                     X1 = grouplasso2pop_gt_data$X1,
                                                     groups1 = grouplasso2pop_gt_data$groups1,
                                                     E.approx1 = grouplasso2pop_gt_data$Y1$E.approx,
                                                     Y2 = grouplasso2pop_gt_data$Y2$I,
                                                     Z2 = grouplasso2pop_gt_data$Y2$A,
                                                     Se2 = grouplasso2pop_gt_data$Y2$Se,
                                                     Sp2 = grouplasso2pop_gt_data$Y2$Sp,
                                                     X2 = grouplasso2pop_gt_data$X2,
                                                     groups2  = grouplasso2pop_gt_data$groups2,
                                                     E.approx2 = grouplasso2pop_gt_data$Y2$E.approx,
                                                     rho1 = 1,
                                                     rho2 = 1,
                                                     n.lambda = 10,
                                                     n.eta = 5,
                                                     lambda.min.ratio = 0.01,
                                                     lambda.max.ratio = 0.50,
                                                     eta.min.ratio = 0.01,
                                                     eta.max.ratio = 1,
                                                     w1 = grouplasso2pop_gt_data$w1,
                                                     w2 = grouplasso2pop_gt_data$w2,
                                                     w = grouplasso2pop_gt_data$w,
                                                     AA1 = grouplasso2pop_gt_data$AA1,
                                                     AA2 = grouplasso2pop_gt_data$AA2,
                                                     Com = grouplasso2pop_gt_data$Com,
                                                     tol = 1e-3,
                                                     maxiter = 500,
                                                     report.prog = TRUE)

grouplasso2pop_gt_cv_fixedgrid.out <- grouplasso2pop_gt_cv_fixedgrid(Y1 = grouplasso2pop_gt_data$Y1$I,
                                                                     Z1 = grouplasso2pop_gt_data$Y1$A,
                                                                     Se1 = grouplasso2pop_gt_data$Y1$Se,
                                                                     Sp1 = grouplasso2pop_gt_data$Y1$Sp,
                                                                     X1 = grouplasso2pop_gt_data$X1,
                                                                     groups1 = grouplasso2pop_gt_data$groups1,
                                                                     E.approx1 = grouplasso2pop_gt_data$Y1$E.approx,
                                                                     Y2 = grouplasso2pop_gt_data$Y2$I,
                                                                     Z2 = grouplasso2pop_gt_data$Y2$A,
                                                                     Se2 = grouplasso2pop_gt_data$Y2$Se,
                                                                     Sp2 = grouplasso2pop_gt_data$Y2$Sp,
                                                                     X2 = grouplasso2pop_gt_data$X2,
                                                                     groups2  = grouplasso2pop_gt_data$groups2,
                                                                     E.approx2 = grouplasso2pop_gt_data$Y2$E.approx,
                                                                     rho1 = 1,
                                                                     rho2 = 1,
                                                                     lambda.seq = grouplasso2pop_gt_grid.out$lambda.seq,
                                                                     eta.seq = grouplasso2pop_gt_grid.out$eta.seq,
                                                                     n.folds = 5,
                                                                     b1.init.arr = grouplasso2pop_gt_grid.out$b1.arr,
                                                                     b2.init.arr = grouplasso2pop_gt_grid.out$b2.arr,
                                                                     w1 = grouplasso2pop_gt_data$w1,
                                                                     w2 = grouplasso2pop_gt_data$w2,
                                                                     w = grouplasso2pop_gt_data$w,
                                                                     AA1 = grouplasso2pop_gt_data$AA1,
                                                                     AA2 = grouplasso2pop_gt_data$AA2,
                                                                     Com = grouplasso2pop_gt_data$Com,
                                                                     tol = 1e-2,
                                                                     maxiter = 500)

gregorkb/semipadd2pop documentation built on Oct. 2, 2022, 1:37 p.m.