Topic Review - Newest First (only newest 5 are displayed)

rqayyum

Re: Free software

For sample size calculations, two free softwares that I have found very helpful are

1. PS - which can be obtained at from the following address:
http://biostat.mc.vanderbilt.edu/twiki/bin/view/Main/PowerSampleSize

2. G*Power3 - which can be downloaded from the following site:
http://www.psycho.uni-duesseldorf.de/abteilungen/aap/gpower3/

anwer_khur

Free software

Two free software for interested practitioners: (i) CONFINT15 and (ii) BP1CI

Anwer
-----------------------------------
CONFINT15

DESCRIPTION

This program performs calculations of the probability that a specified
one-group study (specification includes sample size) will produce a
confidence interval (CI) of at most a particular length. It also
calculates the sample size necessary to achieve a desired such
probability.

CONFINT15 will perform calculations for

One-sample binomial
One-sample Poisson
Mean of the One-Sample Normal
SD of the One-Sample Normal
Hazard of One-Sample Exponential Survival Distribution
Mean survival of the One-Sample Sirvival Distribution

HOW TO GET IT

The program is free (no charge, Fortran 95 source included) and is
available
from the following URL. The distribution includes source,
documentation,
a Win32 executable and a MAC executable.

http://biostatistics.mdanderson.org/SoftwareDownload

WHAT'S NEW?

This is an update which now includes the survival calculations and the
standard deviation of the normal distribution.

EXAMPLE:

The true probability of an event is 0.5. We want a study large enough
that the probability that a 95% confidence interval (via
Clopper-Pearson) has length at most 0.1 is 80%. What sample size is
required?

Answer: 403

COMMENT: I recently announced BP1CI. This is a totally different
program. BP1CI is used to obtain a CI when the data is at hand.
CONFINT15 is used to plan a study (particularly the sample size) and
there no data is involved in its use.

-----------------------------------------
DESCRIPTION

BP1CI (Binomial Poisson 1-sample Confidence Intervals) calculates
exact confidence limits on the probability of event for the one-sample
binomial distribution or on the total number of events for the
one-sample Poisson distribution using the Clopper-Pearson method.

HOW TO GET IT

The program is free (no charge, Fortran 95 source included) and is
available
from the following URL. The distribution includes source,
documentation,
a Win32 executable and a MAC executable.

http://biostatistics.mdanderson.org/SoftwareDownload

WHAT'S NEW?

This is an update which improves the user interface. The program
still
runs only at the command line -- no gui, sorry.

EXAMPLES:

What is the 95% Clopper-Pearson confidence interval when 3 out of 20
trials yield an event?

Answer: [0.0321,0.3789]

What is the 95% CI on the Poisson mean, when a Poisson process yields
100 events?

Answer: [82.266,121.63]

COMMENT:

On one of the groups to which this was posted, it was asked whether
there is a formula for the Clopper-Pearson CI. The answer is yes, but
it involves the inverse of the F distribution (for the binomial) or
the chi-square (for the Poisson) and so is not usually terribly
useful. BP1CI computes these inverses.