VEplot {kyotil}

Vaccine Efficacy Plots

Description

Vaccine efficacy plots.

Usage

VEplot (object, ...) 
 
## S3 method for class 'cox.zph'
 VEplot(object, resid = TRUE, se = TRUE, df = 4, nsmo = 40, 
    var, ylab="VE", xlab="Time", xaxt="s", cex.axis=1, ...) 

## S3 method for class 'glm'
VEplot(object, X1, X2, x, ...)

## S3 method for class 'cox.zph'
 myplot(object, resid = TRUE, se = TRUE, df = 4, nsmo = 40, var, 
    coef.transform=NULL, 
    ylab=NULL, 
    xlab="Time", xaxt="s", cex.axis=1, 
    ...) 

Arguments

object

An object

resid

Boolean, whether to plot residuals

se

Boolean, whether to plot confidence band

df

degrees of freedom

nsmo

number of points used to plot the fitted spline

var

estimated variance matrix from the Cox model fit

xlab

x label

xaxt

x axis

cex.axis

cex for axis

ylab

y label

coef.transform

a function to transform Cox hazard ratio estimate

X1

a matrix of dimension k by p, where k is the length of x (see below) and p is the length of coef(object)

X2

a matrix of dimension k by p, where k is the length of x (see below) and p is the length of coef(object)

x

a vector of length k that represents the x coordinate of the VE plot

...

additional parameters

Details

VEplot and myplot.cox.zph are extensions of survival::plot.cox.zph to plot VE curve and other transformations.

myplot.cox.zph adds the following parameters to the original list of parameters in plot.cox.zph: coef.transform: a function to transform the coefficients ylab: y axis label xlab: x axis label

VEplot.glm computes a series of k VEs: for i in 1...k, VE[i] = P(Y=1|X1[i,])/P(Y=1|X2[i,]). It returns a 3 by k matrix, whose first row contains VE estimates and the second and third rows contain lower and upper bounds, respectively.

Author(s)

Youyi Fong, Dennis Chao

References

Durham, Longini, Halloran, Clemens, Azhar and Rao (1998) "Estimation of vaccine efficacy in the presence of waning: application to cholera vaccines." American Journal of Epidemiology 147(10): 948-959.

Examples

library(survival)
vfit <- coxph(Surv(time,status) ~ trt + factor(celltype) + 
              karno + age, data=veteran, x=TRUE) 
temp <- cox.zph(vfit) 

par(mfrow=c(2,2))
for (v in c("trt","age")) {
    VEplot(temp, var=v, resid=FALSE, main=v, ylab="VE", cex.axis=1.5)
    plot(temp, var=v, resid=FALSE, main=v)
}

library(survival)
fit <- glm(status ~ trt + trt*age, data=veteran) 
summary(fit)
age=seq(min(veteran$age),max(veteran$age),length=10)
out = VEplot(fit, X1=cbind(1,1,age,1*age), X2=cbind(1,0,age,0*age), x=age)
out