MRH (version 2.2)

plot.MRH: Plots the hazard rate (with credible bands) of an MRH object.

Description

plot.mrh plots the hazard rate of an MRH object with the 95% credible interval bounds included as dashed lines.

Usage

"plot"(x, maxStudyTime, main = "", xlab = "Time", 
ylab = "Hazard Rate", plot.type = 'h', 
interval = TRUE, alpha.level = 0.05, smooth.graph = FALSE, 
smooth.df = NULL, combine.graphs = TRUE, log.ratio = TRUE,...)

Arguments

x

x is an MRHobject: Either 1) an MRH fitted object or 2) MCMC chains produced by the estimateMRH routine, converted to an MRH object using MRH() or as.MRH().

maxStudyTime

The maximum observed or censored failure time needs to be entered when the text file of MCMC chains is used instead of the active MRH fitted object for calculation of the hazard rate.

main

The main title of the graph.

xlab

The label of the x-axis.

ylab

The label of the y-axis.

plot.type

Denotes whether the hazard rate, cumulative hazard, survival function or hazard ratio (for the case of non-proportional hazards) should be plotted, specified with 'h', 'H', 'S', or 'r' respectively. Default plot is the hazard rate.

interval

Set to TRUE or FALSE if the credible interval bounds should also be included in the plot. Default is TRUE.

alpha.level

1 minus the credible level of the interval. Default is 0.05.

smooth.graph

Should be set equal to TRUE if the user would like a graph of the smoothed hazard rate using smooth.spline(). Default is set to FALSE.

smooth.df

The degrees of freedom to be used in the smoothed graph of the hazard rate. If the user does not enter a value, it is set to 1/2 of the number of bins.

combine.graphs

If the MCMC chains are from a non-proportional hazards model, combine.graphs can be set to FALSE if the user would like to view the hazard rates or ratios separately. The default is TRUE, combining the hazard rates or ratios in to one graph.

log.ratio

In the non-proportional hazards models, this denotes whether the log-ratio of the hazard rates should be plotted over time (log.ratio = TRUE) or if the ratio of the hazard rates should be plotted instead (log.ratio = FALSE). The default is a plot of the log-ratio of the hazard rates.

...

Arguments to be passed to methods, such as graphical parameters (see par).

Examples

# These MRH fit portion of the examples are from the 
# estimateMRH() help page.  
# They do not need to be re-run if the objects 
# are already in the active workspace.
data(cancer)
cancer$censorvar = cancer$status - 1
## Not run: 
# fit.lung = estimateMRH(formula = Surv(time, censorvar) ~ 
# 	age + as.factor(sex) + ph.karno, data = cancer,
# 	M = 3, maxStudyTime = 960, burnIn = 200, maxIter = 1000, 
# 	thin = 1, outfolder = 'MRH_lung')## End(Not run)

data(tongue)
## Not run: 
# fit.tongue = estimateMRH(formula = Surv(time, delta) ~ 
# 	nph(type), data = tongue, M = 4, 
# 	burnIn = 200, maxIter = 2000, thin = 1, outfolder = 'MRH_tongue_nph')## End(Not run)
	
# Plot the hazard rate, cumulative hazard, 
# and survival function of the lung model side-by-side:
## Not run: 
# par(mfrow = c(1,3))
# plot(fit.lung, main = 'Hazard rate')
# plot(fit.lung, plot.type = 'H', main = 'Cumulative hazard')
# plot(fit.lung, plot.type = 'S', main = 'Survival function')## End(Not run)

# Plot the hazard rates for the tongue (i.e. non-proportional hazards) 
# model with smoothed estimates.
## Not run: 
# plot(fit.tongue, smooth.graph = TRUE)## End(Not run)
# Separate the graphs for less crowding
## Not run: 
# plot(fit.tongue, smooth.graph = TRUE, combine.graphs = FALSE)## End(Not run)
# Plot the hazard ratios
## Not run: 
# plot(fit.tongue, plot.type = 'r')## End(Not run)

# Plot the hazard rate of the lung model using the chains. 
# This requires maxStudyTime to be entered.
## Not run: 
# lung.chains = MRH(read.table('MRH_lung/MCMCchains.txt', header = TRUE))
# plot(lung.chains, maxStudyTime = 960)## End(Not run)