A sampling of the important technical details are below:

Analytic Capabilities:

• Partial Least Squares. Comprehensive implementation of NIPALS algorithm for partial least squares regression including hierarchical PLS and multi-way PLS.
• Principal Components. Comprehensive implementation of NIPALS algorithm for Principal Components Analysis including hierarchical PCA and multi-way PCA.
• Scalable to thousands or hundreds of thousands of parameters, both process parameters, in-process tests, and finished product tests.
• Integrated Graphical Analysis: Wide selection of integrated graphical techniques including batches plotted in the component space, importance plot of components, and univariate and multivariate QC Charts,
• Cross-validation. Integrated options for cross-validation to evaluate the number of components to extract.
• Quality Control. Wide selection of univariate and multivariate QC Charts for offline analysis or automatically-updated as new data are collected.

Integrated with Other STATISTICA Algorithms

• Recursive Partitioning Methods (Trees) including C&RT, CHAID, Boosted CHAID, and Random Forests
• Neural Networks. STATISTICA Neural Networks is the most technologically advanced and best performing neural networks application on the market. It offers numerous unique advantages and will appeal not only to neural network experts (by offering to them an extraordinary selection of network types and training algorithms), but also to new users in the field of neural computing (via the unique Intelligent Problem Solver, a tool that can guide the user through the necessary procedures for creating neural networks).
• Independent Components Analysis. STATISTICA ICA uses state-of-the-art methods for implementing the Independent Component Analysis algorithm to virtually any practical problem requiring separation of mixed signals into their original components. These methods include Simultaneous Extraction and Deflation techniques.
• Support Vector Machines. STATISTICA Support Vector Machine (SVM) is primarily a classier method that performs classification tasks by constructing hyperplanes in a multidimensional space that separates cases of different class labels. STATISTICA SVM supports both regression and classification tasks and can handle multiple continuous and categorical variables.
• Feature Selection. Serves as an ideal pre-processor for predictive data mining, to select manageable sets of predictors that are likely related to the dependent (outcome) variables of interest, for further analyses with any of the other methods for regression and classification available in STATISTICA.
• Design of Experiments (DOE). STATISTICA Design of Experiments offers an extremely comprehensive selection of procedures to design and analyze the experimental designs used in industrial (quality) research: 2**(k-p) factorial designs with blocking (for over 100 factors, including unique, highly efficient search algorithms for finding minimum aberration and maximum unconfounding designs, where the user can specify the interaction effects of interest that are to be unconfounded), screening designs (for over 100 factors, including Plackett-Burman designs), 3**(k-p) factorial designs with blocking (including Box-Behnken designs), mixed-level designs, central composite (or response surface) designs (including small central composite designs), Latin square designs, Taguchi robust design experiments via orthogonal arrays, mixture designs and triangular surfaces designs, vertices and centroids for constrained surfaces and mixtures, and D- and A-optimal designs for factorial designs, surfaces, and mixtures.
• Cluster Analysis. Joining, k Means and Expectation Maximization (EM) clustering methods, supporting both continuos and categorical variables. V-fold cross-validation for determining the appropriate number of clusters.
• General Linear Models. STATISTICA General Linear Models (GLM) analyzes responses on one or more continuous dependent variables as a function of one or more categorical or continuous independent variables. GLM is not only the most computationally advanced GLM tool currently on the market, but it is also the most comprehensive and complete application available, offering a larger selection of options, graphs, accompanying statistics and extended diagnostics than any other program. Designed with a "no compromise approach", GLM offers the most extensive selection of options to handle GLM's so-called "controversial problems" that do not have any widely agreed upon solutions. GLM will compute all the standard results, including ANOVA tables with univariate and multivariate tests, descriptive statistics, etc. GLM offers a large number of results and graphics options that are usually not available in other programs. GLM also offers simple ways to test linear combinations of parameter estimate; specifications of custom error terms and effects; comprehensive post-hoc comparison methods for between group effects as well as repeated measures effects, and the interactions between repeated measures.

Platform Capabilities:

• Offline and Online Methods of Use with Auto-Updating Analyses
• Automated, server-based monitoring of parameters
• Central configuration and Administration of Data Connections, Queries, Analyses and Reports
• Access Control and Permissions
• Web browser-based user interfaces
• Audit Trails
• Report Templating and Generation
• Wide Range of Graphical Data Analysis Techniques
• Audit trails
• Data Management: Data verification, cleaning, merging, etc.

Data Access and Querying

• Comprehensive tools for defining and central configuration of connections and queries to your data repositories (LIMS, process databases)