Regression Modeling for Recurrent Events Possibly with an Informative Terminal Event Using R Package reReg

Abstract

Recurrent event analyses have found a wide range of applications in biomedicine, public health, and engineering, among others, where study subjects may experience a sequence of event of interest during follow-up. The R package reReg offers a comprehensive collection of practical and easy-to-use tools for regression analysis of recurrent events, possibly with the presence of an informative terminal event. The regression framework is a general scale-change model which encompasses the popular Cox-type model, the accelerated rate model, and the accelerated mean model as special cases. Informative censoring is accommodated through a subject-specific frailty without any need for parametric specification. Different regression models are allowed for the recurrent event process and the terminal event. Also included are visualization and simulation tools.

Keywords: event plot; frailty; joint model; mean cumulative function; simulation; survival data.

Figure 1:

Illustration of the covariate effects on the rate function in (6) when $\alpha <0,\beta <0$, and $X>0$. An accelerated rate model modifies the time-scale of ${\lambda }_0\left(t\right)$ to ${\lambda }_1\left(t\right)$. An accelerated mean model modifies ${\lambda }_0\left(t\right)$ to ${\lambda }_2\left(t\right)$ in a way that the cumulative mean function of ${\lambda }_2\left(t\right)$ is a time-scale change of that of ${\lambda }_0\left(t\right)$. A Cox-type model modifies the scale of ${\lambda }_0\left(t\right)$ to ${\lambda }_3\left(t\right)$. The proposed model modifies the time-scale and the magnitude of ${\lambda }_0\left(t\right)$ simultaneously to ${\lambda }_4\left(t\right)$, either through ${\lambda }_0\left(t\right)\to {\lambda }_1\left(t\right)\to {\lambda }_4\left(t\right)$ or through ${\lambda }_0\left(t\right)\to {\lambda }_3\left(t\right)\to {\lambda }_4\left(t\right)$.

Figure 2:

Event plots produced by plot() and plotEvent().

Figure 3:

MCF plots produced by plot().

Figure 4:

Plots of baseline functions produced by plot() and plotRate().

Figure 5:

Event plot and MCF plot stratified by treatment type.