predict.LogisticR {MethylIT}  R Documentation 
Predict using a logistic model obtained from the output of
function evaluateDIMPclass
.
## S3 method for class 'LogisticR' predict(object, newdata = NULL, type = c("all", "class", "posterior"), num.cores = 1L, tasks = 0L, ...)
object 
To use with function 'predict'. An object from 'LogisticR'
class. A logistic model given by function

newdata 
To use with function 'predict'. New data for classification prediction. Optionally, an object from class "GRanges", a list of GRanges, "pDMP" or "InfDIv", in which to look for variables with which to predict. If omitted, the fitted linear predictors are used. 
type 
The type of output required. Possible outputs are: 'class', "posterior" and "all". The default is "all". 
num.cores, tasks 
Paramaters for parallele computation using package

... 
Not in use. 
This function is specific for predictions based on a logistic model
given by function evaluateDIMPclass
. A logistic model is
obtained with 'glm' regression can be used directly with function
'predict' from 'stats' package.
If type is set to 'all', then the original 'newdata' with two columns
added, predicted classes and 'posterior' probabilities, in the
metacolumns of each GRange object are given. If 'newdata' is null, then
the predictions given for the model by function
predict.glm
are returned. if type is set to 'class'
or to "posterior", then the unlisted predited classification or
posterior classification probabilities are returned.