--- title: "Biostatistics III in R" author: - Code by Annika Tillander, Andreas Karlsson and Mark Clements output: prettydoc::html_pretty: theme: cayman highlight: github --- # Exercise 1: Life tables and Kaplan-Meier estimates of survival # ```{r setup, cache=FALSE, message=FALSE, echo=FALSE} library('knitr') read_chunk('../q1.R') opts_chunk$set(cache=FALSE, fig.width=7, fig.height=6) options(width=90) ``` ## (a) Hand calculation: Life table and Kaplan-Meier estimates of survival ## The results are contained in an [Excel file](exercise1.xls) and are also shown in the R output below. ## (b) Using R to validate the hand calculations done in part 1 (a) ## First, load the `biostat3` library: ```{r loadDependencies, message=FALSE} ``` Following are the life table estimates. Note that in the lectures, when we estimated all-cause survival, there were 8 deaths in the first interval. One of these died of a cause other than cancer so in the cause-specific survival analysis we see that there are 7 ‘deaths’ and 1 censoring (Stata uses the term ‘lost’ for lost to follow-up) in the first interval. ```{r lifeTable} ``` Following is a table of Kaplan-Meier estimates. Although it’s not clear from the table, the person censored (lost) at time 2 was at risk when the other person dies at time 2. On the following is a graph of the survival function. ```{r KaplanMeier} ```