Depth estimators and tests based on the likelihood principle with application to regression

@inproceedings{OssietzkyDepthEA,
  title={Depth estimators and tests based on the likelihood principle with application to regression},
  author={Christine H. M{\"u}ller Carl von Ossietzky}
}
  • Christine H. Müller Carl von Ossietzky
We investigate depth notions for general models which are derived via the likelihood principle. We show that the so-called likelihood depth for regression in generalized linear models coincides with the regression depth of Rousseeuw and Hubert (1999) if the dependent observations are appropriately transformed. For deriving tests, the likelihood depth is extended to simplicial likelihood depth. The simplicial likelihood depth is always a U-statistic which is in some cases not degenerated. Since… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 25 references

Robustness of deepest regression

S. Van Aelst, P. J. Rousseeuw
J. Multivariate Anal • 2000
View 15 Excerpts
Highly Influenced

Regression depth (with discussion)

P. J. Rousseeuw, M. Hubert
J. Amer. Statist. Assoc • 1999
View 18 Excerpts
Highly Influenced

On depth and deep points : a calculus

View 7 Excerpts
Highly Influenced

Estimators related to U -processes with applications to multivariate medians: asymptotic normality

M. A. Arcones, Z. Chen, E. Giné
Ann. Statist • 1994
View 9 Excerpts
Highly Influenced

Breakdown properties of location estimates based on halfspace depth and projected outlyingness

D. L. Donoho, M. Gasko
Ann. Statist • 1992
View 6 Excerpts
Highly Influenced

On a notion of data depth based on random simplices

R. Y. Liu
Ann. Statist • 1990
View 6 Excerpts
Highly Influenced

Measuring overlap in logistic regression

A. Christmann, P. J. Rousseeuw
Computational Statistics and Data Analysis 28, • 2001
View 4 Excerpts
Highly Influenced

General notions of statistical depth function

Y. Zuo, R. Serfling
Ann. Statist • 2000
View 4 Excerpts
Highly Influenced

Structural properties and convergence results for contours of sample statistical depth functions

Y. Zuo, R. Serfling
Ann. Statist • 2000
View 5 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…