XLSTAT: Calculate Sample Size and Power for a Cox Regression in Excel

 

Background

XLSTAT provides a tool for applying the Cox proportional hazards regression model and estimating power or required sample size before analysis.

To ensure valid results, key decisions must be made:

• Define the null (H0) and alternative (Ha) hypotheses.

• Choose the appropriate statistical test.

• Set the type I error (alpha), typically at 5%.

• Minimize the type II error (beta), with power = 1 - beta. A power of 0.9 is often desired.

Power calculations are essential before starting an experiment to determine the necessary sample size.

In this case, we aim to evaluate the effect of several variables on survival time in ovarian cancer patients. We want a test power of 0.9 and expect 40% of individuals to be uncensored. The sample size will be calculated accordingly using XLSTAT.

 

Setting Up

• Open XLSTAT.

• Click on the Life Sciences/ Power analysis menu and select the Cox model feature.

• Once the button is clicked, the dialog box pops up. 

In the General tab:

• Choose the objective Find the sample size.

• Enter the various desired parameters including the event rate at 0.4.

• The alpha is 0.05. The desired power is 0.9.

In the Chart tab:

• The simulation plot option is activated and the size of sample 1 will be represented on the vertical axis and the power on the horizontal axis.

• The power varies between 0.8 and 0.95 in intervals of 0.01.

• Click on the OK button to launch the computations.

• The results are displayed on a new Excel sheet.

 

Interpreting the Results

The first table gathers the parameters used as input.

The second table gathers the results of the calculation as well as an interpretation of the results.

We see that 10 individuals per sample are sufficient to obtain a power as close as possible to 0.9.

The following table gathers the calculations obtained for each value of the power between 0.8 and 0.95.

The simulation plot shows the evolution of the sample size as a function of the power. We see that for a power of 0.8, 8 individuals are sufficient per sample and that for a power of 0.95 we arrive at 13 individuals.