STPLAN
Double Precision Study Planning Calculations
Description
STPLAN performs power, sample size, and related calculations needed
to plan frequentist studies. Parameters of a test include those necessary to
describe the distributions under the null and alternative hypotheses,
sample sizes, significance levels, and power. Given values for all but
one parameter, STPLAN will calculate the value of that one parameter.
This product does not require registration before downloading. However, if
you do register first, we can notify you of updates to the software.
The distribution includes command line executables for Windows and Macintosh
(PowerPC and Intel) as well as source code.
The following testing situations are covered by STPLAN:
- Binomial Distribution
- One-sample
- Two-sample
- Two-sample above and below median
- Fisher's exact
- Matched pairs
- Conservative/expensive treatment
- Two-sample test in which one group is a historic control
- K-sample
- Case-control
- Matched Case-Control
- Sample size correction for loss of subjects over time
- Poisson Distribution
- Normal Distribution
- One-sample
- Two-sample, equal variances
- Two-sample, unequal variances
- Two-sample log-normal
- Exponential Distribution
- Survival Times
- One Sample
- Randomized clinical trial with exponential survival
- Historic control with exponential survival
- Randomized trial with two hazard rates
- The Correlation Coefficient
The user's manual is available
here.
Contact: Barry W. Brown
Software developed by
- Barry W. Brown
- Christopher Brauner
- Albert Chan
- David Gutierrez
- Jay Herson
- James Lovato
- James Polsley
- Kathy Russell
- John Venier
Language: Fortran 77
Known issues
One-Sample Survival Studies: When the significance is specified, the calculations are performed assuming a one-sided test, regardless of whether a one-sided or a two-sided test is specified. As far as we know the one-sided calculations are correct.
Documentation: For some studies, the examples in the User's Guide (stplan_user.pdf) show menus and study specifications that no longer correspond to the current menu-driven command-line interface for these studies.
