Valid post-selection inference
From MaRDI portal
Abstract: It is common practice in statistical data analysis to perform data-driven variable selection and derive statistical inference from the resulting model. Such inference enjoys none of the guarantees that classical statistical theory provides for tests and confidence intervals when the model has been chosen a priori. We propose to produce valid ``post-selection inference by reducing the problem to one of simultaneous inference and hence suitably widening conventional confidence and retention intervals. Simultaneity is required for all linear functions that arise as coefficient estimates in all submodels. By purchasing ``simultaneity insurance for all possible submodels, the resulting post-selection inference is rendered universally valid under all possible model selection procedures. This inference is therefore generally conservative for particular selection procedures, but it is always less conservative than full Scheffe protection. Importantly it does not depend on the truth of the selected submodel, and hence it produces valid inference even in wrong models. We describe the structure of the simultaneous inference problem and give some asymptotic results.
Recommendations
- Exact post-selection inference, with application to the Lasso
- Valid post-selection inference in model-free linear regression
- MODEL SELECTION AND INFERENCE: FACTS AND FICTION
- Selective inference after likelihood- or test-based model selection in linear models
- Conditional predictive inference post model selection
Cites work
- A Note on Quantiles in Large Samples
- Asymptotic properties of maximum likelihood estimators based on conditional specification
- Can one estimate the conditional distribution of post-model-selection estimators?
- CAN ONE ESTIMATE THE UNCONDITIONAL DISTRIBUTION OF POST-MODEL-SELECTION ESTIMATORS?
- Confidence sets based on penalized maximum likelihood estimators in Gaussian regression
- Distributional results for thresholding estimators in high-dimensional Gaussian regression models
- Frequentist Model Average Estimators
- scientific article; zbMATH DE number 3141625 (Why is no real title available?)
- scientific article; zbMATH DE number 4100415 (Why is no real title available?)
- scientific article; zbMATH DE number 46309 (Why is no real title available?)
- MODEL SELECTION AND INFERENCE: FACTS AND FICTION
- Mostly harmless econometrics. An empiricist's companion.
- Note on a Conditional Property of Student's t¹
- On model uncertainty and its statistical implications. Proceedings of a workshop, held in Groningen, Netherlands, September 25-26, 1986
- On preliminary test and shrinkage M-estimation in linear models
- On the distribution of penalized maximum likelihood estimators: the LASSO, SCAD, and thresholding
- On the distribution of the adaptive LASSO estimator
- On the Large-Sample Minimal Coverage Probability of Confidence Intervals After Model Selection
- PERFORMANCE LIMITS FOR ESTIMATORS OF THE RISK OR DISTRIBUTION OF SHRINKAGE-TYPE ESTIMATORS, AND SOME GENERAL LOWER RISK-BOUND RESULTS
- Random Packings and Coverings of the Unit n-Sphere
- Sparse estimators and the oracle property, or the return of Hodges' estimator
- The Conditional Level of Student's t Test
- The Conditional Level of the F-Test
- The distribution of a linear predictor after model selection: unconditional finite-sample distributions and asymptotic approximations
- The distribution of model averaging estimators and an impossibility result regarding its estima\-tion
- THE FINITE-SAMPLE DISTRIBUTION OF POST-MODEL-SELECTION ESTIMATORS AND UNIFORM VERSUS NONUNIFORM APPROXIMATIONS
- The Focused Information Criterion
- Valid post-selection inference
Cited in
(only showing first 100 items - show all)- Distribution-free predictive inference for regression
- Confidence intervals for high-dimensional inverse covariance estimation
- An automated approach towards sparse single-equation cointegration modelling
- Spatial variable selection and an application to Virginia Lyme disease emergence
- Sparse estimation of Cox proportional hazards models via approximated information criteria
- On the post selection inference constant under restricted isometry properties
- Selective inference after likelihood- or test-based model selection in linear models
- Uniform asymptotic inference and the bootstrap after model selection
- Scalable methods for Bayesian selective inference
- Estimation of selected parameters
- Rejoinder on: ``High-dimensional simultaneous inference with the bootstrap
- Asymptotically honest confidence regions for high dimensional parameters by the desparsified conservative Lasso
- Weighted-average least squares estimation of generalized linear models
- Exact post-selection inference for the generalized Lasso path
- Logistic regression: from art to science
- Uniformly valid confidence sets based on the Lasso
- High-dimensional inference: confidence intervals, \(p\)-values and R-software \texttt{hdi}
- Simultaneous high-probability bounds on the false discovery proportion in structured, regression and online settings
- Only closed testing procedures are admissible for controlling false discovery proportions
- Multicarving for high-dimensional post-selection inference
- Selective inference for latent block models
- Selective inference for additive and linear mixed models
- Informative goodness-of-fit for multivariate distributions
- In defense of the indefensible: a very naïve approach to high-dimensional inference
- Some perspectives on inference in high dimensions
- Confidence intervals for parameters in high-dimensional sparse vector autoregression
- Spatially relaxed inference on high-dimensional linear models
- Conditional selective inference for robust regression and outlier detection using piecewise-linear homotopy continuation
- Selection of mixed copula for association modeling with tied observations
- Post-model-selection inference in linear regression models: an integrated review
- Uniformly valid confidence intervals post-model-selection
- Rejoinder on: ``Hierarchical inference for genome-wide association studies: a view on methodology with software
- Focused model selection for linear mixed models with an application to whale ecology
- Models as approximations. I. Consequences illustrated with linear regression
- Models as approximations. II. A model-free theory of parametric regression
- Larry Brown's contributions to parametric inference, decision theory and foundations: a survey
- Statistical theory powering data science
- Post hoc confidence bounds on false positives using reference families
- High-dimensional CLT: improvements, non-uniform extensions and large deviations
- Valid post-selection inference in model-free linear regression
- Bootstrapping and sample splitting for high-dimensional, assumption-lean inference
- Inference for L₂-boosting
- Exploration of the variability of variable selection based on distances between bootstrap sample results
- Selective inference via marginal screening for high dimensional classification
- A knockoff filter for high-dimensional selective inference
- On Hodges' superefficiency and merits of oracle property in model selection
- Frequentist model averaging in structural equation modelling
- On the impact of model selection on predictor identification and parameter inference
- Optimal configurations of lines and a statistical application
- On various confidence intervals post-model-selection
- Optimal finite sample post-selection confidence distributions in generalized linear models
- A nonparametric sequential learning procedure for estimating the pure premium
- Selective inference after feature selection via multiscale bootstrap
- The costs and benefits of uniformly valid causal inference with high-dimensional nuisance parameters
- Exact post-selection inference, with application to the Lasso
- Constraints versus priors
- Statistical learning and selective inference
- Post-selection inference following aggregate level hypothesis testing in large-scale genomic data
- Valid post-selection inference
- Rates of convergence of the adaptive LASSO estimators to the oracle distribution and higher order refinements by the bootstrap
- Inference after variable selection in linear regression models
- Principled statistical inference in data science
- Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
- Testing for Neglected Nonlinearity Using Regularized Artificial Neural Networks
- Selective inference with unknown variance via the square-root Lasso
- Statistical proof? The problem of irreproducibility
- A simulation based method for assessing the statistical significance of logistic regression models after common variable selection procedures
- Penalized likelihood and multiple testing
- On the least-squares model averaging interval estimator
- Post-selection point and interval estimation of signal sizes in Gaussian samples
- Post-selection inference for _1-penalized likelihood models
- Robust inference on average treatment effects with possibly more covariates than observations
- Log-linear Bayesian additive regression trees for multinomial logistic and count regression models
- On the length of post-model-selection confidence intervals conditional on polyhedral constraints
- Exploratory inference: localizing relevant effects with confidence
- Regularized projection score estimation of treatment effects in high-dimensional quantile regression
- Bayesian Inference Is Unaffected by Selection: Fact or Fiction?
- scientific article; zbMATH DE number 7626707 (Why is no real title available?)
- Assumption Lean Regression
- Least-Square Approximation for a Distributed System
- Projection-based Inference for High-dimensional Linear Models
- Post-selection inference of generalized linear models based on the lasso and the elastic net
- Inferactive data analysis
- A bootstrap Lasso+partial ridge method to construct confidence intervals for parameters in high-dimensional sparse linear models
- FANOK: knockoffs in linear time
- Likelihood ratio test in multivariate linear regression: from low to high dimension
- Bayesian semiparametric functional mixed models for serially correlated functional data, with application to glaucoma data
- Excess optimism: how biased is the apparent error of an estimator tuned by SURE?
- Valid post-selection inference in high-dimensional approximately sparse quantile regression models
- Post-selection estimation and testing following aggregate association tests
- Selection-corrected statistical inference for region detection with high-throughput assays
- MODEL SELECTION AND INFERENCE: FACTS AND FICTION
- Asymptotics of selective inference
- Inference After Model Selection
- A multi-resolution theory for approximating infinite-\(p\)-zero-\(n\): transitional inference, individualized predictions, and a world without bias-variance tradeoff
- Robust Q-learning
- Confidence sets based on thresholding estimators in high-dimensional Gaussian regression models
- Optimal model averaging for divergent-dimensional Poisson regressions
- The Perils of Balance Testing in Experimental Design: Messy Analyses of Clean Data
- Statistical Inference Enables Bad Science; Statistical Thinking Enables Good Science
This page was built for publication: Valid post-selection inference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q355109)
