#include "math/stats/glm.h"
Protected Attributes | |
const index_array_type & | VG |
const size_t | num_vgs |
vector< size_t > | inputs_per_vg |
vector_type | Rnn_sums |
vector_type | inv_Rnn_sums |
vector_type | gamma_weights |
Protected Attributes inherited from MR::Math::Stats::GLM::TestFixedHomoscedastic | |
vector< Hypothesis::Partition > | partitions |
const matrix_type | pinvM |
const matrix_type | Rm |
vector< matrix_type > | XtX |
vector< default_type > | one_over_dof |
Protected Attributes inherited from MR::Math::Stats::GLM::TestBase | |
const matrix_type & | y |
const matrix_type | M |
const vector< Hypothesis > & | c |
std::shared_ptr< Math::Zstatistic > | stat2z |
A class to compute statistics from heteroscedastic data using a fixed General Linear Model. This class produces a statistic per effect of interest: Aspin-Welsh v for contrast vectors (i.e. Rank(C) == 1), sqrt(Welsh's v^2) for Rank(C) > 1. It should be used in cases where: