On approximate validation of models: a Kolmogorov-Smirnov-based approach
From MaRDI portal
Publication:2665785
Abstract: Classical tests of fit typically reject a model for large enough real data samples. In contrast, often in statistical practice a model offers a good description of the data even though it is not the "true" random generator. We consider a more flexible approach based on contamination neighbourhoods around a model. Using trimming methods and the Kolmogorov metric we introduce a functional statistic measuring departures from a contaminated model and the associated estimator corresponding to its sample version. We show how this estimator allows testing of fit for the (slightly) contaminated model vs sensible deviations from it, with uniformly exponentially small type I and type II error probabilities. We also address the asymptotic behavior of the estimator showing that, under suitable regularity conditions, it asymptotically behaves as the supremum of a Gaussian process. As an application we explore methods of comparison between descriptive models based on the paradigm of model falseness. We also include some connections of our approach with the False-Discovery-Rate setting, showing competitive behavior when estimating the contamination level, although applicable in a wider framework.
Recommendations
- Box-constrained monotone approximations to Lipschitz regularizations, with applications to robust testing
- Publication:4203643
- Some properties of two-sample Kolmogorov-Smirnov test in the case of contamination of one of the samples
- Nonparametric goodness-of-fit
- scientific article; zbMATH DE number 5770591
Cites work
- A contamination model for the stochastic order
- A stochastic process approach to false discovery control.
- Building and using semiparametric tolerance regions for parametric multinomial models
- Data analysis and approximate models. Model choice, location-scale, analysis of variance, nonparametic regression and image analysis
- Data features1
- Directional differentiability for supremum-type functionals: statistical applications
- Estimating the proportion of false null hypotheses among a large number of independently tested hypotheses
- scientific article; zbMATH DE number 5604036 (Why is no real title available?)
- scientific article; zbMATH DE number 646828 (Why is no real title available?)
- scientific article; zbMATH DE number 3092166 (Why is no real title available?)
- Least favorable pairs for special capacities
- Limiting distributions of Kolmogorov-Smirnov type statistics under the alternative
- Model assessment tools for a model false world
- Nonparametric Likelihood Confidence Bands for a Distribution Function
- Nonparametric Validation of Similar Distributions and Assessment of Goodness of Fit
- On \(p\)-values
- One-sided inference about functionals of a density
- Rates of convergence for partial mass problems
- Robust asymptotic statistics
- Robust Estimation of a Location Parameter
- Similarity of samples and trimming
- The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality
- Trimmed Comparison of Distributions
- Uniformly powerful goodness of fit tests
- Uniqueness and approximate computation of optimal incomplete transportation plans
Cited in
(5)- A contamination model for the stochastic order
- A uniform kernel trick for high and infinite-dimensional two-sample problems
- Bootstrap tests for almost goodness-of-fit
- Box-constrained monotone approximations to Lipschitz regularizations, with applications to robust testing
- Model assessment tools for a model false world
This page was built for publication: On approximate validation of models: a Kolmogorov-Smirnov-based approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2665785)
