% Generated by roxygen2: do not edit by hand

% Please edit documentation in R/simulate.R

\docType{methods}

\name{simulate}

\alias{simulate}

\alias{simulate,ANY,missing,missing-method}

\alias{simulate,EventModel,EventData,missing-method}

\alias{simulate,EventModel,missing,FromDataSimParam-method}

\alias{simulate,EventModel,missing,missing-method}

\alias{simulate,missing,EventData,FromDataSimParam-method}

\title{The simulate methods for EventPrediction package}

\usage{

\S4method{simulate}{ANY,missing,missing}(object, data, SimParams, ...)

\S4method{simulate}{EventModel,missing,missing}(object, data, SimParams, ...)

\S4method{simulate}{EventModel,EventData,missing}(object, data, SimParams, ...)

\S4method{simulate}{EventModel,missing,FromDataSimParam}(object, data,

  SimParams, ...)

\S4method{simulate}{missing,EventData,FromDataSimParam}(data, SimParams,

  accrualGenerator = NULL, Naccrual = 0, Nsim = 10000, seed = NULL,

  limit = 0.05, longlagsettings = NULL, HR = NULL, r = NULL,

  dropout = NULL)

}

\arguments{

\item{object}{An \code{EventModel} object which contains both the data (slot event.data) and

the simulation parameters (slot simParams). If not stats::simulate will be called}

\item{data}{If used then this \code{EventData} object will be used when performing the simulations

instead of the \code{EventData} object within \code{fit}}

\item{SimParams}{A \code{FromDataSimParam} object, 

overrides the simulated parameters from the \code{EventModel} object}

\item{...}{Additional arguments to be passed to the method}

\item{accrualGenerator}{An AccrualGenerator object used for recruiting additional subjects}

\item{Naccrual}{The number of additional subjects to be recruited}

\item{Nsim}{Number of simulations to run}

\item{seed}{Integer for random number generator (for reproducability) By default NULL.}

\item{limit}{Limit for the percentiles, default is 0.05 which corresponds

to [0.05, 0.95]}

\item{longlagsettings}{A LongLagSettings object to control the behaviour of the algorithm for subjects whos last date

is a long time from the analysis date. Using this argument can have a large impact on the results - see vignette for further details}

\item{HR}{The hazard ratio: an advanced option which allows two arm trials to be simulated. This replicates the 

Predict from parameters functionality but uses the recruitment times found in \code{data}. See the vignette for

further details}

\item{r}{The allocation ratio: see \code{HR} argument.}

\item{dropout}{if subjects drop out in study (due to competing risks not as there is a finite follow up time)

then this argument should contain a list with proportion and time and optionally shape i.e.

\code{dropout=list(proportion=0.03,time=365,shape=1.2)} meaning in the absence of events 3% of subjects

will have dropped out after 365 days with a Weibull hazard rate with shape=1.2. If shape is not included then 

it defaults to 1 (exponential rate). If dropout is NULL then no subjects will drop out}

}

\value{

A \code{FromDataResults} object

}

\description{

These methods are for the predict from data part of the package 

and simulate. All functions described here are wrappers for the

missing,missing,EventData,FromDataSimParams-method

}

\details{

See the stats::simulate method for details of the stats simulate function

}