Biostatistical Software
NIKOLA KOCEV
Institute for Medical Statistics and Informatics, School
of Medicine, University of Belgrade, Belgrade, Serbia
nkocev@EUnet.yu
Synonyms
Statistical software; Statistical packages
Definition
Biostatistics – is the application of statistics to the analysis
of biological and medical data. Biostatistical
software is a suite of computer programs specialized
for statistical analysis of biological and medical data. It
enables people to obtain the results of standard statistical
procedures and statistical significance tests, without
requiring low-level numerical programming. Most
statistical packages also provide facilities for data management.
Basic Characteristics
Nowadays, very often, biostatistics uses general statistical
packages, which include many procedures that are
seldom used in the solution of biostatistical problems.
Statistical software used for biostatistics’ problems
should encompass routine procedures, such as: data
entry and data management; summarizing information
from data in tables and graphs and summary statistics;
probability, probability distribution, randomization of
patients, sufficient sample size to have adequate statistical
power; for making inference from data: confidence
intervals and hypothesis test; specifying α – type error
I, β – type error II and power analysis; estimating
and comparing mean or differences in mean; comparing
three or more means (ANOVA); estimating and comparing
proportions; associations and prediction; statistical
methods (parametric and nonparametric) for analyzing
survival data; statistical methods for multiple
variables; evaluating diagnostic procedures, time series
analysis, etc.
Bearing in mind that different statistical software’s contain
routine procedures more developed than other software’s,
we are frequently compelled to use more than
one statistical package in the process of solving one particular
biostatistics’ problem. Also, given the moment
in time that we are all living in, statistical software’s
tend to become rapidly outdated forcing software vendors
to continually update and correct their product
(often issuing patches or service releases that correct
errors and bugs). Consequently, buyers – via vendor’s
web sites – can provide themselves with information
regarding errors, bugs, macros and add-ons that extend
the capability of the basic package. The same way, they
are offered the possibility of a free 30-day trial of fully
functional new version which enables them to test them
with their own biostatistics’ problems.
All in all, there are no data management packages
available on the market which are designed and
optimized for biostatics’ softwares, nevertheless, each
package comes with the data entry and data management
options and it is their functionality that permits
data adjustments for particular statistics’ routine procedures
and for connection with the existing database
systems.
Statistical Software
for Successful Biostatistics’ Problem-Solving
For a successful biostatistics’ problem-solving, it is
possible to use one of the commercial packages, general
public license packages, analysis packages with statistics
add-ons, as well as some general purpose languages
with statistics libraries. Consistent with that, some of
the aforementioned are described later.
SAS/STAT® Software
(www.sas.com)
From traditional analysis of variance and predictive
modeling to exact methods and statistical visualization
techniques, SAS/STAT software provides tools for
both specialized and enterprizewide analytical needs.
Key features: analysis of variance, regression, categorical
data analysis, multivariate analysis, survival analysis,
psychometric analysis, cluster analysis, nonparametric
analysis, survey data analysis, multiple imputation
for missing values, study planning.
SAS/ETS contains popular forecasting methods such
as regression analysis, trend extrapolation, exponential
smoothing, Winter’s method (additive and multiplicative),
ARIMA (Box-Jenkins) and dynamic or transfer
function models.
JMP
(http://www.jmp.com/)
SAS created the JMP desktop statistical discovery software,
that uses a structured, problem-centered approach
for exploring and analyzing data. The intelligent interface
guides users to the adequate analyzes. JMP automatically
displays graphs with statistics, enabling users
to visualize and uncover data patterns.
BMDP
(http://www.statsol.ie/html/bmdp/bmdp_home.
html)
BMDP has its roots as biomedical analysis packages
from the late 1960s. It is a comprehensive library
of statistical routines from simple data description
to advanced multivariate analysis, and is backed by
extensive documentation. Each individual BMDP subprogram
is based on the most competitive algorithms
available and has been rigorously field-tested. The
BMDP package contains over 40 interrelated statistical
programs. All of the programs share common instructions
and convenience features to save time and effort.
SPSS
(www.spss.com)
Data Analysis with Comprehensive Statistics Software,
statistical and data management package for analysts
and researchers. SPSS forWindows is a modular, tightly
integrated, full-featured product line for the analytical
process – planning, data collecting, data access,
data management and preparation, data analysis, reporting,
and deployment. Using a combination of add-on
modules and stand-alone software that work seamlessly
with SPSS Base enhances the capabilities of this statistics
software. The SPSS Programmability Extension™
enables analytic and application developers to extend
the SPSS command syntax language to create procedures
and applications – and perform even the most
complex jobs – within SPSS.
StatSoft STATISTICA
(http://www.statsoft.com)
StatSoft’s flagship product line is the STATISTICA
suite of analytic software products. STATISTICA provides
the most comprehensive array of data analysis,
data management, data visualization, and data mining
procedures. Its techniques include the widest selection
of predictive modeling, clustering, classification, and
exploratory techniques in one software platform. The
STATISTICA Visual Basic language that can be used
to write custom extensions.
NCSS and PASS
(Statistical & Power Analysis Software)
(www.ncss.com)
NCSS software provides a complete, easy-to-use collection
of over 200 statistical and graphics tools to analyze
and visualize data.
PASS ( power analysis and Sample Size) software is
an easy-to-use research tool for determining the number
of subjects that should be used in a study, performs
power analysis and calculates sample sizes for over 150
statistical tests.
Mathematica,WOLFRAM RESEARCH
(http://www.wolfram.com/)
Mathematica’s statistics capabilities are part of Mathematica’s
standard add-on packages. Like any statistics
package, Mathematica provides a numerical and graphical
toolset to illustrate, simulate, and find approximate
numeric solutions to numerical problems.
Matlab
(http://www.mathworks.com/)
MATLAB® is a high-performance language for technical
computing. It integrates computation, visualization,
and programming in an easy-to-use environment where
problems and solutions are expressed in familiar mathematical
notation.
The Statistics Toolbox, for use with MATLAB®, is
a collection of statistical tools built on the MATLAB
numeric computing environment. The toolbox supports
a wide range of common statistical tasks, from random
number generation, to curve fitting, to design of experiments
and statistical process control. The toolbox provides
two categories of tools: Building-block probability
and statistics functions and Graphical, interactive
tools. The first category of tools is made up of functions
that can be called up from the command line or
from an individual’s own applications. Many of these
functions are MATLAB M-files, series of MATLAB
statements that implement specialized statistics algorithms.
R Project for Statistical Computing
(http://www.r-project.org/)
R is a language and environment for statistical computing
and graphics. It is a GNU project which is similar
to the S language and environment which was developed
at Bell Laboratories (formerly AT&T, now Lucent
Technologies) by John Chambers and colleagues. R can
be considered as a different implementation of S. There
are some important differences, but much code written
for S runs unaltered under R. R provides a broad variety
of statistical (linear and nonlinear modeling, classical
statistical tests, time-series analysis, classification,
clustering, etc.) and graphical techniques, and is highly
extensible. The S language is often the vehicle of choice
for research in statistical methodology, and R provides
an Open Source route to participation in that activity. R
is available as Free Software under the terms of the Free
Software Foundation’s GNU General Public License in
source code form.
Free Statistical Software
(http://statpages.org/javasta2.html)
This page contains links to free software packages
that can be downloaded and installed onto a computer
for stand-alone (offline, non-Internet) computing. They
are listed below, under the following general headings:
General Packages: support a wide variety of statistical
analyses; Subset Packages: deal with a specific
area of analysis, or a limited set of tests; Curve
Fitting and Modeling: to handle complex, nonlinear
models and systems; Biostatistics and Epidemiology:
especially useful in the life sciences; Surveys, Testing
andMeasurement: especially useful in the business and
social sciences; Excel Spreadsheets and Add-ins: need
a recent version of Excel; Programming Languages and
Subroutine Libraries: customized for statistical calculations;
need to learn the appropriate syntax; Scripts
and Macros: for scriptable packages, like SAS, SPSS,
R, etc.; Miscellaneous: do not fit into any of the other
categories; Other Collections of Links to Free Software.
Cross-References
Data Entry
Data Management Packages
Medical Data
Power Analysis
Statistical Procedure
Statistical Visualization Techniques
Reference
Statistics at George Mason University. A Guide to Statistical
Software 1998 Version | 2005 Version. http://www.galaxy.
gmu.edu/. Accessed 2007
Tags: belgrade serbia, confidence intervals, hypothesis test, making inference, medical statistics, medicine university, numerical programming, probability distribution, probability probability, routine procedures, significance tests, statistical package, statistical packages, statistical power, statistical procedures, statistical software, statistics probability, summary statistics, survival data, time series analysis
