Chameleon Statistics

Note: This software is available again!

Chameleon Statistics is a new statistical data analysis and data visualization package. The program provides researchers, analysts, statisticians and other users with the ability to extract meaningful information (knowledge) from their raw data. It provides comprehensive faculties for clustering, modeling and classification of data by discovering and utilizing the natural relationships which exist amongst the elements of that data.

The program is capable of processing both data files and images of varying size and complexity and can provide several kinds of graphical representation of the data. The graphical features and output of Chameleon Statistics are amongst the finest available anywhere. The program provides facilities for manually editing or manipulating the data as well as a number of analytical techniques which can be used to examine the data.

Cluster groupings are suggested by in-built hierarchical and partition clustering algorithms and classes can be defined by the user. Class models are generated based upon several density estimation techniques which are included. Classification of existing or new data is performed on the basis of class models selected by the user. The program is able to learn from such classification results and update class memberships accordingly.

Analyses for each set of data samples are kept in separate project files, with any selection of data from a given project easily being used to generate new projects. Display styles, fonts and color settings for project windows are fully configurable.

The range of facilities provided by Chameleon includes:

Importing multivariate datasets, such as survey data, experimental results, bitmap images and so on, with size limited only by available memory.

Numerical data entry via spreadsheet or graphical data entry via mouse.

Multiple graphical representations of data, e.g. histograms, 2-D/3-D scatter plots that can be rotated, images and dendrograms.

Viewing and editing of data values from within the program.

Data masking to reduce sample size or ignore unwanted samples.

User-defined weighting of variables or normalization of data according to various metrics.

A variety of standard hierarchical and partition clustering methods to find relationships within the data.

Automatic or user-specified selection of classes based upon extracted data relationships.

Parametric and non-parametric modeling of classes, such as Gaussian, k-nearest-neighbor and kernel methods.

Model-based visualization of density maps and contour maps.

Classification of data samples in memory or from file based upon defined classes and specified class models.

Learning from classifications and updating class memberships.

The ability to save entire analyses as project files or generate new subprojects from any project.

Chameleon Statistics Scientific Edition is ideal for use by organizations and individuals working with numerical data or images. It consists of the following components:

Cluster Analysis, Density Estimation, Classification & Data Visualization

These components combine perfectly to make the Scientific Edition the data analysis package of choice. It will be especially valuable to scientists and researchers working in technical fields such as artificial intelligence, pattern recognition or remote sensing.

Chameleon Statistics Professional Edition is our feature-packed general purpose statistical package which can process all kinds of data types, can intelligently handle missing and corrupted data, and which provides all of the necessary tools and techniques required to extract meaningful information and knowledge from masses of unclassified raw data. It is ideal for any individual or organization working in business and commerce, sales and marketing, data mining and knowledge discovery, or any kind of academic research.

Chameleon Statistics Professional Edition includes all of the features of the Scientific Edition, as well as the following additional components:

Automated Feature Extraction, Missing Value Handling, Multivariate Imputation, Mixed Data Type Handling & Anomaly and Outlier Detection.

Requirements: Runs on all versions of Windows from Win95 onwards (Win98, WinNT, Win2000, WinME and WinXP). Disk space: 5.5 MB.

Cost: Academic version (download only) $59.

Ordering information:
Orders may be placed by mail, e-mail, FAX, phone, or by our secure order form.

Payment can be made by American Express, MasterCard, VISA, money order, or checks drawn on US banks. Institutional purchase orders are also accepted within the USA. Call, FAX, or e-mail to place your order today! Orders will be sent out promptly. Shipping costs. Return policy. Try our convenient Currency converter.

e-mail: sales@exetersoftware.com
Phone: 1-631-689-7838, Toll-free within USA: 800-842-5892
FAX: 1-631-689-0103,
47 Route 25A, Suite 2, Setauket, NY 11733-2870 USA
Request additional information .