344 PART 6 Analyzing Survival Data

Looking at Figure 23-6, first consider the table in the Baseline Survivor Function

section, which has two columns: time in years, and predicted survival expressed

as a fraction. It also has four rows — one for each time point in which one or more

deaths was actually observed. The baseline survival curve for the example data

starts at 1.0 (100 percent survival) at time 0, as survival curves always do, but this

row isn’t shown in the output. The survival curve remains flat at 100 percent until

year two, when it suddenly drops down to 99.79 percent, where it stays until year

seven, when it drops down to 98.20 percent, and so on.

In the Descriptive Stats section near the start of the output in Figure 23-6, the

average age of the 11 patients in the example data set is 51.1818 years, so the base-

line survival curve shows the predicted survival for a patient who is exactly 51.1818

years old. But suppose that you want to generate a survival curve that’s custom-

ized for a patient who is a different age — like 55 years old. According to the PH

model, you need to raise the entire baseline curve to some power h. This means

you have to exponentiate the four tabulated points by h.

In general, h depends on two factors:»

» ^{The value of the predictor variable for that patient. In this example, the value}

of age is 55.»

» ^{The values of the corresponding regression coefficients. In this example, in}

Figure 23-6, you can see 0.3770 labeled as Coeff. in the regression table.

FIGURE 23-6:

Output of PH

regression for

generating

prognostic

curves.