As of Version 7.0, CovarianceMatrixDetRatio has been renamed to "CovarianceRatios" and has become a property of LinearModelFit.
- To use CovarianceMatrixDetRatio, you first need to load the Regression Common Functions Package. You can do this by using Needs["LinearRegression`"], which will automatically load the Regression Common Functions Package, or you can load the package directly by using Needs["RegressionCommon`"].
- CovarianceMatrixDetRatio gives a list of values which measure the effect of removing a data point.
- The i element in the list is the ratio of the determinant of CovarianceMatrix for all the data points to the equivalent determinant with the i data element removed.
- A value less than 1-3 or greater than 1+3, where n is the number of data points and p is the number of parameters, may indicate a highly influential point.