Abstract: We say that two probabilities are similar at level if they are contaminated versions (up to an fraction) of the same common probability. We show how this model is related to minimal distances between sets of trimmed probabilities. Empirical versions turn out to present an overfitting effect in the sense that trimming beyond the similarity level results in trimmed samples that are closer than expected to each other. We show how this can be combined with a bootstrap approach to assess similarity from two data samples.
Recommendations
Cites work
- scientific article; zbMATH DE number 3986407 (Why is no real title available?)
- scientific article; zbMATH DE number 272681 (Why is no real title available?)
- A Robust Version of the Probability Ratio Test
- A general trimming approach to robust cluster analysis
- Assessing when a sample is mostly normal
- Asymptotics for \(L_2\) functionals of the empirical quantile process, with applications to tests of fit based on weighted Wasserstein distances
- Best approximations to random variables based on trimming procedures
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- Consistency of the \(\alpha \)-trimming of a probability. Applications to central regions
- Free boundaries in optimal transport and Monge-Ampère obstacle problems
- Least favorable pairs for special capacities
- Limiting distributions of Kolmogorov-Smirnov type statistics under the alternative
- Minimax tests and the Neyman-Pearson lemma for capacities
- On the Huber-Strassen theorem
- Robust Estimation of a Location Parameter
- Some asymptotic theory for the bootstrap
- The optimal partial transport problem
- Trimmed Comparison of Distributions
- Trimmed \(k\)-means: An attempt to robustify quantizers
- Uniqueness and approximate computation of optimal incomplete transportation plans
- \(k\)-sample test based on the common area of kernel density estimators
Cited in
(14)- Models for the assessment of treatment improvement: the ideal and the feasible
- Interpoint distance based two sample tests in high dimension
- Box-constrained monotone approximations to Lipschitz regularizations, with applications to robust testing
- On approximate validation of models: a Kolmogorov-Smirnov-based approach
- Distributionally robust stochastic programs with side information based on trimmings
- On the topological data analysis extensions and comparisons
- A contamination model for the stochastic order
- Directional differentiability for supremum-type functionals: statistical applications
- Detecting relevant changes in the mean of nonstationary processes -- a mass excess approach
- The empirical cost of optimal incomplete transportation
- Searching for a common pooling pattern among several samples
- Rates of convergence for partial mass problems
- Wide consensus aggregation in the Wasserstein space. Application to location-scatter families
- Trimmed Comparison of Distributions
This page was built for publication: Similarity of samples and trimming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q418241)
