Adjusted Deviance Residuals in short format
Calculates the adjusted deviance residuals for arbitrary prediction models. The adjusted deviance residuals should be approximately normal distributed, in the case of a well fitting model.
adjDevResidShort(dataSet, hazards)
dataSet |
Data set in long format. Must be of class "data.frame". |
hazards |
Estimated hazard rates of the data in long format. Hazard rates are probabilities and therefore restricted to the interval [0, 1] |
Output: List with objects:
AdjDevResid: Adjusted deviance residuals as numeric vector
Input: A list of given argument input values (saved for reference)
The argument dataSet must have a response with column name "y". The correct format of the dataset can be augmented by using dataLong.
Thomas Welchowski welchow@imbie.meb.uni-bonn.de
Gerhard Tutz and Matthias Schmid, (2016), Modeling discrete time-to-event data, Springer series in statistics, Doi: 10.1007/978-3-319-28158-2
Gerhard Tutz, (2012), Regression for Categorical Data, Cambridge University Press
library(survival) # Transform data to long format heart[, "stop"] <- ceiling(heart[, "stop"]) set.seed(0) Indizes <- sample(unique(heart$id), 25) randSample <- heart[unlist(sapply(1:length(Indizes), function(x) which(heart$id==Indizes[x]))),] heartLong <- dataLongTimeDep(dataSet=randSample, timeColumn="stop", censColumn="event", idColumn="id", timeAsFactor=FALSE) # Fit a generalized, additive model and predict hazard rates on data in long format library(mgcv) gamFit <- gam(y ~ timeInt + surgery + transplant + s(age), data=heartLong, family="binomial") hazPreds <- predict(gamFit, type="response") # Calculate adjusted deviance residuals devResiduals <- adjDevResidShort (dataSet=heartLong, hazards=hazPreds)$Output$AdjDevResid devResiduals
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.