glmTrain_fun.Rd
Model statistics for Generalized Linear Model (GLM) regression by gene
glmTrain_fun(x, y, family = binomial)
x | An \(p \times n\) predictor matrix. |
---|---|
y | A response vector. |
family | A description of the error distribution and link function to
be used in the model. The default is |
The slope coefficient from the GLM for each gene.
While this function currently supports any GLM family from the
family
function, this function is only called in the
model fitting step (via the internal superpc.train
) function
and not in the test statistic calculation step (in the
superpc.st
function). We would like to support Poisson
regression through the glm
function, as well as n-ary
classification through multinom
and ordinal logistic
regression through polr
.