an12365@mdaali.cancer.utexas.edu (E. Neely Atkinson) (02/20/91)
Archive-name: math/stat/clinical-trials/1991-01-18
Archive: mdaali.cancer.utexas.edu:/pub/index [129.106.1.6]
Original-posting-by: an12365@mdaali.cancer.utexas.edu (E. Neely Atkinson)
Original-subject: software available - clinical trials
Reposted-by: emv@ox.com (Edward Vielmetti)
Computer code written by members of the Department of Biomathematics,
the University of Texas M. D. Anderson Cancer Center is now available.
The programs perform the following listed functions. The code can be
freely copied and used (shareware distribution is encouraged) although
the authors retain copyright for the University of Texas in order to
control possible commercial incorporation. The last section of this
message contains instructions on how to obtain it.
++++++++++++++++++++
KSB1CI
KSB1CI (k-stage binomial one group confindence intervals) finds
confidence intervals for single- or multiple-stage trials involving a
single group which have a binomial outcome. The confidence intervals
are calculated by a minor modification of the Clopper and Pearson
method to k-stage use. The lower value of the confidence limit is
that probability that causes the observed number of events or more to
have probability 1-c/2 where c is the confidence level; the upper
limit is symmetrically defined.
KSBIN1
KSBIN1 performs computations needed to plan multiple-stage experiments
involving dichotomous outcomes for a single group; the outcomes are
distributed binomially. In k-stage experiments, the results are
examined at each of k predetermined times; at each examination, the
experiment can be terminated because of either early proof of the
result or because obtaining such proof is very unlikely if the
experiment is continued. The assumption of a binomial distribution of
outcomes implies that the outcomes are independent of each other at
that the probability of the event of interest is the same for each
outcome. KSBIN1 performs its calculations only for a single group;
i.e., the case in which a comparison of the probability of event with
a fixed value.
RANLIST
RANLIST produces randomization lists and offers a primitive form of
interactive randomization. RANLIST features both restricted and
unrestricted randomization. When restricted randomization is used,
fixed or random balance points may be chosen.
STATTAB
STATTAB calculates the cumulative distribution funcions, inverses, and
values of parameters for many common statistical distributions. It
can also produce tables of any one calculated iten as a function of a
specified list of values of another item.
STPLAN
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.
WINDOWS
WINDOWS provides a variety of window/kernel/moving-average estimators.
Both fixed width and fixed number of nearest neighbor windowing is
provided. Weighting of points may be done either with boxcar or
biquartic weights. Estimates available include weighted mean, a
linear or quadratic fit, maximum or minimum value, a specified
percentile, the standard deviation, and the derivative of y with
respect to x. Cross validation is also included.
++++++++++++++++++++
How to Get It
The code is available by anonymous ftp to mdaali.cancer.utexas.edu
(129.106.1.6) as tar.Z files. Information is on file index of pub.
Directory pub contains source; msdos contains msdos executables, and
directory mac will shortly contain macintosh executables. Be sure to
read the README files on msdos or mac.
The source is also available on statlib as uuencoded tar.Z files.
For information on statlib send mail whose message is 'send index' to
statlib@temper.stat.cmu.edu. For specific information on these
packages, add the line 'send index from utexas' to the message.
MSDOS executables have been posted to CompuServe (look for keyword
'statistics' in IBMAPP). MacIntosh executables will be posted soon.
E. Neely Atkinson
an12365@mdaali.cancer.utexas.edu