论文信息 - First-order data sensitivity measures with applications to a multivariate signal-plus-noise problem

First-order data sensitivity measures with applications to a multivariate signal-plus-noise problem

Abstract This paper considers the use of first-order (implicit-function-based) measures of the sensitivity of statistical parameter estimates to certain elements within the data. Although the methods considered are general, the focus is on a maximum likelihood problem in a signal-plus-noise context. We evaluate the accuracy of the measures and give an example of how they will be used in data analysis for a physical system.

James C. Spall | D. C. Chin | J. Spall

[1] William S. Levine,et al. Efficient Maximum Likelihood Identification of a Positive Semi-Definite Covariance of Initial Population Statistics , 1984, 1984 American Control Conference.

[2] R. Shumway,et al. Estimation and tests of hypotheses for the initial mean and covariance in the kalman filter model , 1981 .

[3] Sanford Weisberg,et al. Discussion: Some Principles for Regression Diagnostics and Influence Analysis , 1983 .

[4] Fang-Kuo Sun,et al. A maximum likelihood algorithm for the mean and covariance of nonidentically distributed observations , 1982 .

[5] John R. B. Whittlesey,et al. A comparison of the correlational behavior of random number generators for the IBM 360 , 1968, Commun. ACM.

[6] J. Berger,et al. Empirical Bayes Estimation of Rates in Longitudinal Studies , 1983 .

[7] Richard H. Smith. Maximum likelihood mean and covariance matrix estimation constrained to general positive semi-definiteness , 1985 .

[8] R. R. Hocking,et al. The regression dilemma , 1983 .

[9] J. Spall. An approximation for analyzing a broad class of implicitly and explicitly defined estimators , 1986 .

[10] S. Weisberg,et al. Residuals and Influence in Regression , 1982 .