Paper Info
Title
A General Method for Local Sensitivity Analysis With Application to Regression Models and Other Optimization Problems
Abstract
This article introduces a method for sensitivity analysis of general applicability. The method is based on the well-known duality property of mathematical programming, which states that the partial derivatives of the primal objective function with respect to the constraints on the right side parameters are the negative of the optimal values of the dual problem variables. For the parameters or data, for which sensitivities are sought, to appear on the right side, they are converted into artificial variables and set to their actual values, thus obtaining the desired constraints. The method is applicable to linear and nonlinear models, to normal and nonnormal models, and to least squares and other methods of estimation. In addition to its general applicability, the method is also computationally inexpensive, because the necessary information becomes available without extra calculations. The theoretical basis for the method is given and illustrated by its application to least squares, least absolute value, and minimax regression problems and to the estimation of a Weibull distribution from censored data.
Year
DOI
Venue
2004
10.1198/004017004000000509
TECHNOMETRICS
Keywords
Field
DocType
duality,influential observations,least absolute value,least squares,minimax,outliers,parameter estimation,regression diagnostics,Weibull distribution
Least squares,Econometrics,Mathematical optimization,Least trimmed squares,Partial least squares regression,Robust regression,Iteratively reweighted least squares,Generalized least squares,Non-linear least squares,Total least squares,Statistics,Mathematics
Journal
Volume
Issue
ISSN
46
4
0040-1706
Citations 
PageRank 
References 
15
1.63
3
Authors
4
Name
Order
Citations
PageRank
Enrique Castillo155559.86
Ali S. Hadi214015.04
Antonio Conejo318924.33
Alfonso Fernández-Canteli4152.30