Survival Analysis Overview

Major innovation in computational speed

Compute power by formula rather than simulation even when accrual rates, hazard rates, and attrition rates vary from one time interval to the next.

Graph power as a function of study duration, accrual patterns, treatment effect, attrition, or any other parameter in just seconds and get a clear picture of that factor's impact in your study.

This speed is made possible by the new algorithm which bypasses the simulation, coupled with an extremely powerful interface. With any other program, the same task would require many hours of tedious computation.

Work interactively!

• Modify the accrual, follow-up, sample size, hazard rates, attrition, or any parameter...and immediately see the impact on power.
• Or, click “Find N” and the program will find the sample size automatically.
• The graph of cumulative survival serves as a clear and compelling picture of the treatment effect.

Click to view full size.

Create A Report with a Single Click!

Click to view full size.

Create A Report with a Single Click!

• CREATE a report which explains the study design and assumptions.
• VERIFY that all elements of the study have been specified correctly.
• USE the report as a teaching tool, and as an example of how a power analysis should be described.
• EDIT the report and include it in your study plan or grant application.
• The report is shown unedited. The group names (New treatment), time interval (months), and subject type (patients) are based on user-set preferences.

Create A Report with a Single Click!

Enter the treatment effect using a seamless interface— the graph of cumulative survival is updated automatically.

If the hazard rates are constant - enter the hazard rate OR the median survival OR the cumulative survival. The program computes the other two values and automatically updates the graph of cumulative survival.

If the hazard rates vary - one click opens a grid where you can enter the hazard rate for each interval. Proportional hazards are permitted but not required. No simulations are required to computer power, so you can still find the required sample size with a single click!

Click to view full size.

Assess the impact of all parameters in just seconds!

1. Click “Tables and Graphs.” The program picks up all parameters from the main screen and uses these to select a plausible range of values for the sample size. The initial table and graph are created immediately.
   Total time: 1 second
2. Add any number of factors with a few clicks. Here, we will use three levels of duration (12, 24, 36 months), two levels of treatment effect (risk ratio of .50 and .60), and two rates for attrition (.02 and .04). The program automatically nests the factors, populates the table, and creates the graphs.
   Total time: 20 seconds

Assess the impact of all parameters in just seconds!

Simply drag and drop columns in the table to instantly highlight the impact of any parameter. For example...

Assess the impact of study duration.
Power increases substantially as duration is increased from 12 to 24 months, but there is virtually no impact on power if the study duration is increased beyond that point.
Total time: 1 second.

Assess the impact of treatment effect.
If we elect to plan for the smaller treatment effect we will need to increase the sample size by 40 patients per group. This is true for a 24 month study (foreground) or 36 months (background).
Total time: 1 second.

Assess the impact of attrition (drop-outs).
In this example, an attrition rate of 4% per month as compared with 2% per month will have only a modest impact on power. This holds true across all levels of treatment effect and duration.
Total time: 1 second.

Use with these graphs at meetings to develop an appropriate study plan.

Include the graphs in your reports and grant applications.