×

On ridge parameters in logistic regression. (English) Zbl 1225.62098

Summary: This article applies and investigates a number of logistic ridge regression (RR) parameters that are estimable by using the maximum likelihood (ML) method. By conducting an extensive Monte Carlo study, the performances of ML and logistic RR are investigated in the presence of multicollinearity and under different conditions. The simulation study evaluates a number of methods of estimating the RR parameter \(k\) that has recently been developed for use in linear regression analysis. The results from the simulation study show that there is at least one RR estimator that has a lower mean squared error (MSE) than the ML method for all the different evaluated situations.

MSC:

62J07 Ridge regression; shrinkage estimators (Lasso)
62J12 Generalized linear models (logistic models)
62J02 General nonlinear regression
65C05 Monte Carlo methods
Full Text: DOI

References:

[1] DOI: 10.1080/03610920500436360 · doi:10.1080/03610920500436360
[2] Haq M. S., J. Appl. Statist. Sci. 3 pp 301– (1996)
[3] DOI: 10.2307/1267351 · Zbl 0202.17205 · doi:10.2307/1267351
[4] DOI: 10.2307/1267352 · Zbl 0202.17206 · doi:10.2307/1267352
[5] DOI: 10.1080/03610927508827232 · Zbl 0296.62062 · doi:10.1080/03610927508827232
[6] Frisch R., Statistical Confluence Analysis by Means of Complete Regression Systems (1934) · Zbl 0011.21903
[7] DOI: 10.1081/STA-200056836 · Zbl 1073.62057 · doi:10.1081/STA-200056836
[8] DOI: 10.1081/SAC-120017499 · Zbl 1075.62588 · doi:10.1081/SAC-120017499
[9] DOI: 10.1080/0094965031000120181 · Zbl 1060.62073 · doi:10.1080/0094965031000120181
[10] Kibria B. M. G., Calcutta Statist. Assoc. Bull. 55 pp 211– (2004)
[11] DOI: 10.1080/03610927608827353 · Zbl 0336.62056 · doi:10.1080/03610927608827353
[12] DOI: 10.2307/2285832 · Zbl 0319.62049 · doi:10.2307/2285832
[13] DOI: 10.1080/03610910802592838 · Zbl 1160.62337 · doi:10.1080/03610910802592838
[14] DOI: 10.1016/S0895-4356(96)00236-3 · doi:10.1016/S0895-4356(96)00236-3
[15] DOI: 10.1080/03610929308831183 · Zbl 0786.62071 · doi:10.1080/03610929308831183
[16] DOI: 10.1080/03610928408828664 · doi:10.1080/03610928408828664
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.