Sagata Regression Pro software
have been tested by datapicks.com team against viruses,
spyware, adware and was founded to be 100% clean.
We will recheck this software periodically to assure users that it remain clean. Note: this award offered by datapicks.com
should be used only by the author/publisher of the Sagata Regression Pro software.
Sagata Regression software offers the power of a professional regression package with the ease and comfort of a Microsoft Excel interface.
Features include:
Qualitative/Categorical Factors - often inputs or factors in model fitting are qualitative or categorical in nature, e.g., the type of house (brick, cape cod, or colonial) or the school district name. S.R. Pro offers completely seamless integration of categorical and continuous factors.
Efficient Backend Processing - often regression models involve thousands or even tens of thousands of data points. The efficient C++ program engine in S.R. Standard and Pro can save minutes or even hours of waiting compared with many Microsoft Excel add-in packages in these cases.
Interactive Model Generation - experts typically prefer to choose their models interactively depending upon the nature of their problem and relevant statistical information. Sagata Regression provides a powerful custom modeling feature for easy generation of second and third order models.
Interactive 3D Plot Engine - plotting the results of regression models is often key to helping decision makers visualize the impact of input variations on outputs. Sagata Regression generates visually appealing, fully adjustable surface plots.
Cross-validation/MinPRESS Automodeling - exclusive stepwise type automatic model selection approach with the advantage of cross-validation type model evaluation.
Data Weighting - weighted regression allows users to downplay the data associated with higher measurement errors.
Stepwise Regression Automodeling - offers a stepwise regression feature to select the “optimal†model automatically.
Robust Regression (for Outliers) - commonly some of the data are not entirely reliable. For these cases, alternatives to least squares regression are less influenced by a small number of aberrant observations or outliers.
