plot.diagprop {crskdiag} | R Documentation |
Plots the observed and simulated cumulative sums of residuals in testing the proportionality assumption for the fitted Fine and Gray model.
## S3 method for class 'diagprop' plot(x, col = c("red", "black"), lty = c(1, 2), lwd = c(2, 1), txt.pos=c(0.85,0.1), lgd.pos="topright", xlim=NULL, ylim=NULL, select=NULL, ...)
x |
a diagprop object. |
col |
colors of the plots. The first element is used for observed process, and the second element is used for simulated processes. |
lty |
line types of the plots. The first element is used for observed process, and the second element is used for simulated processes. |
lwd |
line widths of the plots. The first element is used for observed process, and the second element is used for simulated processes. |
txt.pos |
the horizontal and vertical positions of the p-value. The assigned numbers represents the percentage in the x-y panel. |
lgd.pos |
the position of the legend. |
xlim |
the x limitation of the plots |
ylim |
the y limitation of the plots |
select |
the covariate needs to be plotted. Valid value is an integer from 1 to the number of covariates plus 1. For example, if the number of covariates is 3, then 1, 2, 3 indicates the plots of checking corresponding covariates in the formula, and 4 indicates the plot of checking the link function. Multiple values are allowed |
... |
additional arguments to plot() |
library(crskdiag) data(dat2) out2 <- diag_crr(Crsk(time,cause)~z1+z2,data=dat2,test="prop",seed=1234) plot(out2)