Parabon Crush
Statistical Data Mining

Features and Specifications

Crush Ease-of-Use Features:

  • Crush has an intuitive interface. Simply install the Parabon Crush Add-in for Microsoft® Excel® and access it from your spreadsheet's drop-down Tools menu.
  • For exceptionally large datasets, Crush can be launched directly from the command-line, circumventing Excel's data size limitations, and facilitating its incorporation into data mining workflows.
  • Search job parameters are easily specified via standard dialog interfaces.
  • Results — parameter estimates for the best models — are returned and displayed in a new workbook.
  • Job progress can be monitored from any browser via the Frontier Dashboard.
  • Crush can be used within your enterprise running atop Frontier Enterprise or accessed on-demand via the Parabon Computation Grid.

Parabon Crush is a statistical data mining application that uses the power of the Frontier Grid Platform to identify optimal explanatory regression models among the potentially vast set of all possible models. It can be used for deep correlation analysis, prediction and explanatory modeling.

Crush Technical Features:

  • Crush supports linear, logit and ordered regression analysis, and its pluggable architecture makes it easy to add others.
  • Crush identifies optimal models according to any of a variety of fitness measures, including adjusted R2, log likelihood, and root mean squared prediction error (RMSPE) via k-fold cross validation.
  • Crush searches model spaces exhaustively, combinatorially, or using opportunistic evolutionary search.
  • Crush supports programmatic execution and XML specification for easy integration into existing workflows.
  • Crush Case Studies

    Request an evaluation of Crush and tell us about your data mining needs.

Learn More about Crush

With use of the [Crush] application on Frontier, we were able to look at 34 different independent variables (producing about 8.6 billion linear combinations) in less than 24 hours of computing time." Dr. Frondorf, US Geological Survey

Crush revealed significant explanatory models that previous conventional approaches used by experienced, Ph.D. statisticians failed to find.Dr. William Petros, Pharm. D., of the Mary Babb Randolph Cancer Center

Parabon's computational grid allowed us, for the first time, to [programmatically] examine each of the billions of possible combinations of factors to find the most [statistically] powerful models. As a result, we found relationships that we had not anticipated." Eddie Reed, MD, Oncology Researcher

Access to massive computations helped find correlations that we were not otherwise able to consider." Dr. Karen Balzer, Medical Researcher at WVU