Darwin Help

Back to Index

SvdResult

Class SvdResult - results of a least squares approximation, Ax=b

Calling Sequence  SvdResult(Norm2Err,SensitivityAnalysis,SingularValuesUsed,SingularValuesDiscarded,Norm2Indep,MinNorm2Err,SolutionVector,NData)
Selectors
NameTypeDescription

Norm2Err numericnorm of approximation |Ax-b|^2
SensitivityAnalysis list(list)results with sensitivity analysis
SingularValuesUsed list(numeric)singular values used
SingularValuesDiscarded list(numeric)singular values discarded
Norm2Indep numericnorm of independent variables, |b|^2
MinNorm2Err numeric|Ax-b|^2 is all sv were used
SolutionVector list(numeric)least squares solution, x
NData posintnumber of data points (dim A is n x m)
Methods HTMLC, print, Rand
Synopsis An SvdResult holds the result of a linear least squares approximation. Such an approximation is normally generated by SvdAnalysis or SvdBestBasis. The list with the sensitivity results has 4 entries per variable. These are the name of the variable, the result value (the x[i] value), an estimate of the standard deviation and the amount by which |Ax-b|^2 will increase if this variable would not be used. Two compute this difference, all singular values are used. This list is sorted in decreasing order of the last argument. The list is only produced if the global variable ComputeSensitivity is not set to false, otherwise it is empty.
See also SvdAnalysis,   SvdBestBasis