Outlier tests for logistic regression: A conditional approach

Bedrick, Edward J.; Hill, Joe R.

doi:10.1093/biomet/77.4.815

Cited by 19 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The logistic slippage model, which closely resembles the mean-shift outlier model for linear regression problems [43], was explicitly considered in [14] and leads to the removal of outliers from the fit. However, since the number and position of outlying cases are generally unknown, one should in principle compare the exclusion of 0 ≤ k n ≤ n/2 points from the fit (if one is willing to assume that less than half of the data are in fact contaminated).…”

Section: Robust Logistic Regressionmentioning

confidence: 99%

“…We consider a two-class logistic regression model affected by data contamination (i.e., outliers) and comprising irrelevant covariates. Specifically, we focus on the logistic slippage model, where the number, position and strength of the outliers are unknown [14,43]. The main idea is to enforce integer constraints on the number of outlying cases and relevant features in order to improve the interpretability of the model and its robustness.…”

Section: Miprob: Robust Variable Selection Under the Logistic Slippage Modelmentioning

confidence: 99%

“…Here optimality refers to the fact the the global optimum of the underlying "double" combinatorial problem is indeed achievable and, even if the algorithm is stopped before convergence, one can obtain optimality guarantees by monitoring the gap between the best feasible solution and the problem relaxation [11,12]. Specifically, we consider an L 0 sparsity assumption on the coefficients [13] and a logistic slippage model for the outlying observations [14]. We further build upon the work in [7] and rely on L 0 -constraints to detect outlying cases and select relevant features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Variable Selection with Optimality Guarantees for High-Dimensional Logistic Regression

Insolia

Kenney

Calovi

et al. 2021

Stats

View full text Add to dashboard Cite

High-dimensional classification studies have become widespread across various domains. The large dimensionality, coupled with the possible presence of data contamination, motivates the use of robust, sparse estimation methods to improve model interpretability and ensure the majority of observations agree with the underlying parametric model. In this study, we propose a robust and sparse estimator for logistic regression models, which simultaneously tackles the presence of outliers and/or irrelevant features. Specifically, we propose the use of L0-constraints and mixed-integer conic programming techniques to solve the underlying double combinatorial problem in a framework that allows one to pursue optimality guarantees. We use our proposal to investigate the main drivers of honey bee (Apis mellifera) loss through the annual winter loss survey data collected by the Pennsylvania State Beekeepers Association. Previous studies mainly focused on predictive performance, however our approach produces a more interpretable classification model and provides evidence for several outlying observations within the survey data. We compare our proposal with existing heuristic methods and non-robust procedures, demonstrating its effectiveness. In addition to the application to honey bee loss, we present a simulation study where our proposal outperforms other methods across most performance measures and settings.

show abstract

Section: Robust Logistic Regressionmentioning

confidence: 99%

Section: Miprob: Robust Variable Selection Under the Logistic Slippage Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Variable Selection with Optimality Guarantees for High-Dimensional Logistic Regression

Insolia

Kenney

Calovi

et al. 2021

Stats

View full text Add to dashboard Cite

show abstract

“…Stefanski et al (1986) proposed bounded influence estimators which minimize certain functionals of the asymptotic covariance matrix. Bedrick and Hill (1990) developed tests for single and multiple outliers assuming a logistic slippage model. Morgenthaler (1992) explored the consequences of replacing the L,-norm by the L,-norm in the derivation of quasi-likelihoods.…”

Section: Comments and Conclusionmentioning

confidence: 99%

Regression Diagnostics for Binomial Data from the Forward Search

Atkinson

Riani

2001

J Royal Statistical Soc D

View full text Add to dashboard Cite

Summary. We suggest a simple robust method for the detection of atypical and influential observations in binomial data. Our technique is based on a forward search procedure which orders the observations from those most in agreement with a specified generalized linear model to those least in agreement with it. The effectiveness of the forward search estimator in detecting masked multiple outliers, and more generally in ordering binomial data, is shown by means of three data sets. Plots of diagnostic quantities during the forward search clearly show the effect of individual observations on residuals and test statistics. These examples reveal the strength of our method in showing the structure of the data in a way which is more simple and effective than it would be by using standard deletion diagnostic procedures.

show abstract

“…Bedrick and Hill (1990) test whether there are outliers with respect to a simple logistic regression model without background in this data set. Bedrick and Hill (1990) test whether there are outliers with respect to a simple logistic regression model without background in this data set.…”

Section: Examplementioning

confidence: 99%

Robust Statistics, Data Analysis, and Computer Intensive Methods

Rieder¹

1996

Lecture Notes in Statistics

View full text Add to dashboard Cite

Outlier tests for logistic regression: A conditional approach

Cited by 19 publications

References 22 publications

Robust Variable Selection with Optimality Guarantees for High-Dimensional Logistic Regression

Robust Variable Selection with Optimality Guarantees for High-Dimensional Logistic Regression

Regression Diagnostics for Binomial Data from the Forward Search

Robust Statistics, Data Analysis, and Computer Intensive Methods

Contact Info

Product

Resources

About