predict.GammaMixt {MethylIT.utils} | R Documentation |
This is an utility function to get the density, probailities,
and posterior probability predictions based on a given DMP's Mixtures of
Gamma Distributions (GMD) model, obtained with function
gammaMixtCut
.
## S3 method for class 'GammaMixt' predict(gmd, pred = "quant", q = 0.95, div.col = NULL, interval = NULL)
gmd |
An object carrying the best nonlinear fit for a distribution model
obtained with function |
pred |
Type of prediction resquested: *density* ("dens"),*quantiles* ("quant"), *random number* ("rnum"), *probabilities* ("prob"), or classification *posterior probability* ("postPrb"). |
q |
numeric vector of quantiles, probabilities or an interger if
pred = "rnum", or A "pDMP"or "InfDiv" object obtained with functions
|
div.col |
An integer. If 'q' is "pDMP"or "InfDiv" object, then it is the column number for the divergence of methylation levels used in the estimation of model 'gmd'. Default: NULL. |
interval |
a vector containing the end-points of the interval to be searched for the quantile(s). An interval would be, e.g., 'interval = c(min(x), max(x))', where 'x' is the variable used to estimate model 'gmd'. |
num.cores, tasks |
Paramaters for parallele computation using package
|
Predictions are based on the best model fit returned by function
nonlinearFitDist
. The possible prediction are: *density*,
*quantiles*, *random number* or *probabilities*.