Cornerstone Introduction
Cornerstone Design of Experiments
Cornerstone Principal Components
Cornerstone Extension Language
Cornerstone Control Charts
Cornerstone Multiple Regression
Cornerstone Manova
Cornerstone Distribution Fitting and Process Capability

 

Cornerstone’s Principal Components analysis module helps identify the “vital few” variables and simplifies further analysis.

Reduce Data Complexity

Today, data is collected on so many variables that it can be difficult to visualize or describe the “vital few” variables critical in your process.

Reducing the amount of data that you store and analyze, while retaining most of the information in your original data is essential for effective data analysis.

Principal components analysis is a technique for reducing the number of variables needed to represent the relationships in your data.

A Powerful Tool for Simplifying Data Analysis

Cornerstone’s Principal Components analysis module is the ideal tool for deriving new composite variables which represent the original variables in your data. You can use the Principal Components analysis module to:
· Effectively characterize and understand your data
· Determine whether a reduced number of variables can adequately represent your data
· Simplify subsequent analysis

Cornerstone’s graphical user interface makes the process of identifying principal components easy. Because Cornerstone’s analysis modules are all integrated, the principal components can be used as inputs for regression analysis, quality control analysis, or process capability studies.

Extend Your Application

Principal Components’ functionality is part of a suite of data analysis modules. The functionality in all of Cornerstone’s analysis modules is accessible through the Cornerstone™ Extension Language (CEL). CEL allows you to extend Cornerstone and to create custom, site-specific applications.

Features

Model Creation and Refinement

· Create principal components analysis
· Add or remove variables from the analysis
· Change set of observations in the analysis
· Specify confidence level
· Base calculations on correlation or covariances

Model Evaluation or Visualization

· Graph of any two variables (principal components or original responses)
· Graph of variance attributable to each principal component as a Pareto bar graph
· Graph of contribution of each original variable to any two principal components
· Table of variation explained by each principal component
· Table of coefficients of each principal component
· Table of correlation between variables
· Table of covariances between variables
· Table of principal component values for each observation

Guidance and Interpretation

· Hypertext descriptions of each graphical and tabular result
· Interpretation of results using pictorial examples.