fitDefault: Fit target relative to driver

In byandell/CausalMST: Causal Model Selection Hypothesis Tests

Description

Fit a model for a target and get detailed results about estimated coefficients and individuals contributions to the LOD score.

Usage

fitDefault(driver, target, kinship = NULL, addcovar = NULL,
  intcovar = NULL, weights = NULL, ...)

Arguments

driver	A matrix of drivers, individuals x drivers
target	A numeric vector of target values
kinship	Optional kinship matrix.
addcovar	An optional matrix of additive covariates.
intcovar	An optional matrix of interactive covariates.
weights	An optional vector of positive weights for the individuals. As with the other inputs, it must have 'names' for individual identifiers. Ignored if ‘kinship' is provided.#’
nullcovar	An optional matrix of additional additive covariates that are used under the null hypothesis (of no driver) but not under the alternative (with driver).

Details

If kinship is absent, regression is performed. If kinship is provided, a linear mixed model is used, with a random effect estimated under the null hypothesis of no driver, and then taken as fixed and known with driver. The default version ignores kinship. See fit1 for use of kinship.

Value

A list containing * 'LR' - The overall likelihood ratio. * 'indLR' - Vector of individual contributions to the likelihood ratio. * 'df' - Model degrees of freedom.

byandell/CausalMST documentation built on May 13, 2019, 9:26 a.m.