em_by_feature: List containing output of the EM algorithm run for each...

In jstarling1/varstar: What the package does (short line)

Description

This object is the result of running emAllFeatures function for data sets each containing the class column and the single feature. Generated using maxiter=1000, conv=.00001.

Usage

em_by_feature

Format

A list object with four elements:

$est_mixing_props

Matrix of estimated class proportions (cols) for each feature (rows)

$feature_MSEs

Vector of MSEs for each feature, for estimated props. vs unknown props.

$feature_iter

Vector of number of iterations to EM convergence for each feature.

$feature_log

List of vectors of log-likelihood functions for each feature..

...

jstarling1/varstar documentation built on May 20, 2019, 2:12 a.m.