How do I run a Kaplan-Meier analysis with XLSTAT-Life?
An Excel sheet with both the data and results can be downloaded by clicking here. The data have been obtained in [Gehan E.A. (1965). A generalized Wilcoxon test for comparing arbitrarily singly-censored samples. Biometrika, 52, pp 203223] and represent a randomized clinical trial investigating the effect of the drug 6-mercaptopurine on remission times (in weeks) of acute leukemia patients. Our goal is to determine if and how the drug influences the survival time, by comparing the survival curves for two groups of 21 patients, the first being treated, and the second being a control group. All 21 patients of the control group were observed to have a recurrence of their leukemia. Only 9 of the 6-MP patients had an observed recurrence time, while the 12 others were censored.
After opening XLSTAT, select the XLSTAT/XLSTAT-Life/Kaplan-Meier analysis command, or click on the corresponding button of the "XLSTAT-Life" toolbar (see below).
Once you've clicked on the button, the Kaplan-Meier analysis box will appear. Select the data on the Excel sheet. The "Time data" corresponds to the durations when the patients either relapsed or were censored. The "Status indicator" describes whether a patient relapsed (event code=1) or was censored (censored code = 0) at a given time. So that XLSTAT takes into account the information whether the patient belongs to the control or the treated group, we need to select the groups information, and to activate the "compare" option so that the comparison tests are computed.
The following charts are requested.
The computations begin once you have clicked on "OK". The results will then be displayed.
Interpreting the results of a Kaplan-Meier analysis
The results for the first group are displayed first. The first table displays a summary of the data for the "6-MP drug" patients.
The next table corresponds to the "Kaplan-Meier table". It contains the results of the Kaplan-Meier analysis with several key indicators.
The next tables give the mean and median survival time and the respective confidence intervals. Some values are missing because they could not be computed.
Then, we can visualize several curves, including the the survival distribution function (SDF, or survivor function), bounded by the confidence intervals. The circles identify the censored data.
Next, the same series of results is displayed for the control group.
We notice that the median survival time is a lot lower for the control group than for the 6-MP group (8.667 vs 21.943).
Then, we can compare the two groups. First, a series of tests is displayed in a table. From the results we can see that the difference between the two survivor functions is very significant.
Last the comparison of the two survival curves allows us to conclude to confirm that the drug impacts significantly positively the survival time of patients.
Click here for other tutorials.
Copyright © 2014 Kovach Computing Services, Anglesey, Wales. All Rights Reserved. Portions copyright Addinsoft and Provalis Research.
Last modified 9 August, 2013