PDA

View Full Version : Study planning software (X-post)



Ton Van Den Bogert
11-16-1993, 06:17 AM
Dear Biomch-L readers,

The software described in the following announcement may be
useful for biomechanical studies. Most of us are familiar
(unfortunately) with the situation where statistical analysis
could not provide a good answer to the research question. This
software helps you to prevent such problems by considering
statistical analysis in the planning stage. The software is in
the public domain. I have not tried this, so comments are
welcome.

-- Ton van den Bogert, Biomch-L moderator

>From: bwb@odin.mda.uth.tmc.edu (Barry W. Brown)
>Newsgroups: comp.lang.fortran,sci.math.num-analysis,sci.math.stat,sci.stat.math,comp.programm ing,sci.stat.consult
>Subject: ANNOUNCE - Sample Size, Power, Etc. Program
>Date: 9 Nov 1993 15:49:34 GMT
>Organization: University of Texas M.D. Anderson Cancer Center


STPLAN 4.0

STPLAN performs power, sample size, and related calculations needed to
plan 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.

The following testing situations are covered by STPLAN:

Studies with Outcomes Distributed According to the Binomial Distribution
One-sample test
Two-sample test
Two-sample above and below the median
Fisher's exact
Matched pairs test for equality of proportions
Conservative versus expensive treatment
Two-sample test in which one group is a historic control
K-sample
Case-control
Sample size correction for loss of subjects over time

Studies with Outcomes Distributed According to the Poisson Distribution
One-sample test
Two-sample test

Studies with Outcomes Distributed According to the Normal Distribution
One-sample test
Two-sample test, equal variances
Two-sample test, unequal variances
Two-sample log-normal

Studies with Outcomes Distributed According to the Exponential Distribution
One-sample test
Two-sample test

Studies whose Outcome is a Set of Survival Times.
Randomized clinical trial for exponential survival times
Comparison with a historic control - exponential survival
Randomized clinical trial - two different hazard rates depending on time

Studies whose Outcome is the Correlation Coefficient
One-sample test


MAJOR CHANGES IN 4.0

The major changes are: (1) the ability to produce tables of any one
quantity as a function of any other, and (2) a complete report format
that allows exact reconstruction of the calculation. In addition
three new testing calculations have been added.

A TASTE OF THE OUTPUT OF THE NEW VERSION

***** Two-sample Binomial (Arcsin approximation) *****


These calculations are for a two sided test.

Probability of an event in group 1 ...... .200

Probability of an event in group 2 ...... .400

Significance level ...................... .050

Number of equal
trials in each group Power

10.000 .166
20.000 .287
30.000 .402
40.000 .507
50.000 .599
60.000 .678
70.000 .744
80.000 .799
90.000 .843
100.000 .878
110.000 .906
120.000 .929
130.000 .946
140.000 .959
150.000 .969

HOW TO GET IT

The source code is available by anonymous ftp from
odin.mda.uth.tmc.edu. (129.106.3.17).

Source

/pub/unix/stplan-4.0-tar.Z

MSDOS Executable

/pub/stplan40.exe

This is an self-extracting file containing an MSDOS executable
version of Stplan plus documentation. The file was created with a
licensed copy of PkZip. STPLAN was compiled using the Watfor compiler
and so requires a 386 (or better) machine to run.

Barry W. Brown
Department of Biomathematics,
Box 237
University of Texas M. D.
Anderson Hospital
1515 Holcombe Blvd
Houston, TX 77030

bwb@odin.mda.uth.tmc.edu
internet address is (129.106.3.17)