Robust regularized singular value decomposition with application to mortality data
Authors:
- Lingsong ZhangLZLingsong Zhang
- Haipeng ShenHSHaipeng Shen
- Jianhua Z. HuangJHJianhua Z. Huang
Open Access
- 1 September 2013
- journal article
- research article
- Published by Institute of Mathematical Statistics in The Annals of Applied Statistics
- Vol. 7 (3) , 1540-1561
Abstract
We develop a robust regularized singular value decomposition (RobRSVD) method for analyzing two-way functional data. The research is motivated by the application of modeling human mortality as a smooth two-way function of age group and year. The RobRSVD is formulated as a penalized loss minimization problem where a robust loss function is used to measure the reconstruction error of a low-rank matrix approximation of the data, and an appropriately defined two-way roughness penalty function is used to ensure smoothness along each of the two functional domains. By viewing the minimization problem as two conditional regularized robust regressions, we develop a fast iterative reweighted least squares algorithm to implement the method. Our implementation naturally incorporates missing values. Furthermore, our formulation allows rigorous derivation of leave-one-row/column-out cross-validation and generalized cross-validation criteria, which enable computationally efficient data-driven penalty parameter selection. The advantages of the new robust method over nonrobust ones are shown via extensive simulation studies and the mortality rate application.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Use of multiple singular value decompositions to analyze complex intracellular calcium ion signalsThe Annals of Applied Statistics, 2009
- The Analysis of Two-Way Functional Data Using Two-Way Regularized Singular Value DecompositionsJournal of the American Statistical Association, 2009
- Functional principal components analysis via penalized rank one approximationElectronic Journal of Statistics, 2008
- Functional Data Analysis for Sparse Longitudinal DataJournal of the American Statistical Association, 2005
- A Tutorial on MM AlgorithmsThe American Statistician, 2004
- Smoothed functional principal components analysis by choice of normThe Annals of Statistics, 1996
- Robust Singular Value Decompositions: A New Approach to Projection PursuitJournal of the American Statistical Association, 1993
- Design of anSFunction for Robust Regression Using Iteratively Reweighted Least SquaresJournal of Computational and Graphical Statistics, 1992
- Least Median of Squares RegressionJournal of the American Statistical Association, 1984
- Lower Rank Approximation of Matrices by Least Squares With Any Choice of WeightsTechnometrics, 1979