Biostats SPSS Kaplan-Meier Curve

Part2

Step-by-Step Guide to Assignment 8.2

Problem 2. Kaplan-Meier Survival Analysis (Without factor or Strata)

Run a Kaplan-Meier analysis in SPSS, using Time as the Time variable and Event as the Status variable (Be sure to define the event). Do not add a factor or strata at this time.

Step 1. In the Practice_Week08_dataset with the added Time variable, Analyze ( Survival ( Kaplan-Meier.

Step 2. In the Kaplan-Meier window, select the Time to event/censor [Time] variable and place it in the Time box.

Step 3. Select the Tumor [event] variable and place it in the Status box.

Step 4. Click on the Define event button.

Step 5. In this window, select the List of values radio button, type 0 in the List of values box then click Add.

Step 6. Type 1 in the List of variables box. Click Add then click Continue.

Step 7. In the Kaplan-Meier window, click on Options.

Step 8. In the Options window, check Survival table(s) and Mean/ median survival in the Statistics area; check Survival in the Plots area. Click Continue. Click OK when you are returned to the Kaplan-Meier window.

SPSS output:

a. Produce a Survival Table (you do not need to submit this)

Your Output window should contain small Case-Processing Summary table with a VERY long Survival Table below it. This is the table you are asked to produce, but not turn in, in Problem 2b.

SPSS output:

b. Produce a plot of the survival function

c. What is the mean survival time (include confidence intervals)? What is the median survival time (include confidence intervals)? Why do you think they are so different from each other?

Means and Medians for Survival Time
Meana	Median
Estimate	Std. Error	95% Confidence Interval	Estimate	Std. Error	95% Confidence Interval
		Lower Bound	Upper Bound			Lower Bound	Upper Bound
14.017	1.026	12.007	16.027	9.000	1.097	6.849	11.151
a. Estimation is limited to the largest survival time if it is censored.

Recall that means are affected by extreme values where the median is not. Consider the frequency distribution for the Time variable that you ran in Problem 1.