This function allows to compute a neural network using the PLANN method.
sPLANN(formula, data, pro.time=NULL, inter, size = 32, decay = 0.01,
maxit = 100, MaxNWts = 10000, trace = FALSE, ...)The formula object.
The fitted nnet object.
The data frame given with the computed Intervals column added.
The base data frame with the duplicated rows based on the Intervals column.
The function call for the creation of the nnet object.
The interval length.
The number of units in the hidden layer.
The value of the parameter for weight decay.
The value of the parameter for maxit.
The value of the parameter for MaxNWts.
The name(s) of the covariate(s) used in the model.
The values of time and event.
The model covariates values.
The intervals limits values.
The rows with a missing value in the data base.
a formula object, with the response on the left of a ~ operator, and the terms on the right. The response must be a survival object as returned by the Surv function.
A data frame in which to look for the variables included in the formula.
A numeric value with the maximum prognostic. If NULL, the maximum prognostic time is the last time for wich an event is observed.
A numeric value representing the length of the intervals.
A numeric value for the number of units in the hidden layer. Default is set to 32
A numeric value for the parameter for weight decay. Default is set to 0.01
A numeric value for the maximum number of iterations. Default is set to 100.
The maximum allowable number of weights. There is no intrinsic limit in the code, but increasing MaxNWts will probably allow fits that are very slow and time-consuming. Default is set to 10000
A logical argument for tracing optimization. Default is set to FALSE.
Further arguments passed to or from other methods.
The nnet loss function parameter is fixed to entropy as Biganzoli's PLANN method minimize the cross-entrophy loss function which correspondS to maximizing the loglikelihood.
Biganzoli E, Boracchi P, Mariani L, and et al. Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med, 17:1169-86, 1998.
data(dataK)
splann <- sPLANN(Surv(time, event) ~ sex + stade + delay, data=dataK, inter=365,
size=32, decay=0.01, maxit=100, MaxNWts=10000)
print(splann)
Run the code above in your browser using DataLab