Nothing
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++#
#++++++++++++++++++ Evaluate logistic drop-out model +++++++++++++++++++#
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++#
#' Compute value of logistic dropout function given with scale boundaries
#'
#' Computes value of logistic function for one observation and uses offset
#' to correct model. The drop-out magnitude boundary parameter scaOffset is
#' set in here.
#'
#' @seealso \link{evalDropoutModel_comp}
#'
#' @param vecPiModel (numeric vector length linear model) Linear model
#' for drop-out rate in logit space.
#' @param vecPiPredictors (vector length of predictors) Predictors of
#' the drop-out rate in the linear model. Minimum are a constant
#' offset and log of the negative binomial mean parameter.
#' Other gene-specific predictors can be added.
#'
#' @return scaDropoutRate (scalar)
#' Drop-out rate estimate.
#'
#' @author David Sebastian Fischer
evalDropoutModel <- function(vecPiModel,
vecPiPredictors){
# Set offset parameter
scaOffset <- 0.001
scaDropoutRate <- scaOffset+(1-2*scaOffset)*1/(1+exp(-(vecPiPredictors %*% vecPiModel )))
return(scaDropoutRate)
}
#' Compiled function: evalDropoutModel
#'
#' Pre-compile heavily used functions.
#' Refer to \link{evalDropoutModel}.
#'
#' @seealso \link{evalDropoutModel_comp}
#'
#' @param vecPiModel (numeric vector length linear model) Linear model
#' for drop-out rate in logit space.
#' @param vecPiPredictors (vector length of predictors) Predictors of
#' the drop-out rate in the linear model. Minimum are a constant
#' offset and log of the negative binomial mean parameter.
#' Other gene-specific predictors can be added.
#'
#' @return scaDropoutRate (scalar)
#' Drop-out rate estimate.
#'
#' @author David Sebastian Fischer
evalDropoutModel_comp <- compiler::cmpfun(evalDropoutModel)
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.