Article
Statistics & Probability
Danijel Kivaranovic, Hannes Leeb
Summary: Research on valid inference after model selection is actively exploring the polyhedral method for constructing confidence intervals, with varying lengths depending on the model and computation complexity. Simulation results suggest that the sufficient condition for infinite length is met unless the selected model includes almost all or almost none of the available regressors. Additionally, kappa-quantiles exhibit a similar behavior for kappa close to 1 in the distribution of confidence interval lengths.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2021)
Article
Economics
Dongxiao Han, Jian Huang, Yuanyuan Lin, Guohao Shen
Summary: We propose a robust post-selection inference method based on the Huber loss for regression coefficients in high-dimensional linear models with heavy-tailed and asymmetric error distributions. The method demonstrates desirable properties and is applicable to scenarios with heteroscedasticity. Simulation studies and an application to genomic data validate its performance.
JOURNAL OF ECONOMETRICS
(2022)
Article
Statistics & Probability
Andrea C. Garcia-Angulo, Gerda Claeskens
Summary: Conditioning on the event of selecting a model leads to the construction of uniformly optimal conditional confidence distributions, which can be used for valid postselection inference, including the construction of confidence intervals and hypothesis tests.
SCANDINAVIAN JOURNAL OF STATISTICS
(2023)
Article
Multidisciplinary Sciences
Shu-Fei Wu
Summary: This paper presents interval estimation methods for the scale parameter of two-parameter exponential distribution, and proposes two methods for the joint confidence region. The optimal method of the confidence region is determined by simulation comparison based on confidence region area. The proposed methods are validated through a biometrical example.
Article
Biology
A. Mccloskey
Summary: I propose a new type of confidence interval that allows correct asymptotic inference after model selection without assuming any model is correctly specified. This hybrid confidence interval combines techniques from selective inference and post-selection inference to provide a short interval across various data realizations. The results show that hybrid confidence intervals have correct asymptotic coverage over a broad class of probability distributions with no bound on scaled model parameters. Monte Carlo experiments and an empirical application on diabetes disease progression predictors demonstrate the desirable length and coverage properties of these confidence intervals in small samples.
Article
Physics, Multidisciplinary
Wei Dai, Ka Wai Tsang
Summary: Linear models are widely used in econometrics to analyze relationships and estimate parameters. However, empirical studies have shown that these models often do not fit real-world data well, and their selection is a critical issue. In the era of big data, one approach is to consider a large number of covariates and use model selection. However, many model selection methods perform poorly in practice due to insufficient sample size, especially for financial data that are often correlated and have small samples. This study addresses the challenge of constructing accurate confidence intervals after model selection, and proposes a resampling approach with consistent estimators. Theoretical, simulation, and empirical results demonstrate the advantages of this method.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Mathematics
Liang Wang, Huizhong Lin, Yuhlong Lio, Yogesh Mani Tripathi
Summary: This paper considers the problem of interval estimation for the parameters of the generalized inverted exponential distribution. Different pivotal quantities are proposed based on upper record values, and exact and generalized confidence intervals are constructed for the unknown model parameters and reliability indices. Conventional likelihood based approximate confidence intervals are also provided for comparison purposes using observed Fisher information matrix. Moreover, prediction intervals are constructed for future records based on the proposed pivotal quantities and likelihood procedures.
Article
Statistics & Probability
Tijana Zrnic, Michael I. Jordan
Summary: In data-driven statistical inference, the guarantees provided by classical theories disappear. This study proposes a solution based on algorithmic stability to address the problem of inference after selection. Stability is achieved through randomization of selection and allows for nontrivial post-selection corrections for classical confidence intervals. Importantly, the method is computationally efficient and does not require Markov chain Monte Carlo sampling.
ANNALS OF STATISTICS
(2023)
Article
Mathematical & Computational Biology
Michael P. Fay, Keith Lumbard
Summary: This article presents a method based on sign test for handling paired data and calculating effect estimates and confidence intervals. It proposes a confidence interval compatible with exact sign test, and supports the conjecture of guaranteed coverage through extensive numerical calculations.
STATISTICS IN MEDICINE
(2021)
Article
Statistics & Probability
Hoda Kamranfar, Kambiz Ahmadi, Mitra Fouladirad
Summary: This paper deals with statistical inference for lifetime data in presence of imperfect maintenance. The maximum likelihood estimation procedure and Bayesian estimators are discussed and applied. Sensitivity analysis and assessment of model misspecification are also conducted.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2022)
Article
Statistics & Probability
Sen Zhao, Daniela Witten, Ali Shojaie
Summary: This paper presents a simple two-step procedure for conducting inference on parameters in a high-dimensional linear model by using lasso model selection and fitting least squares model. Under certain assumptions, the selected variables by lasso are shown to be deterministic, leading to valid inference. This finding is utilized to develop naive confidence intervals and score tests for regression coefficients.
STATISTICAL SCIENCE
(2021)
Article
Statistics & Probability
Xiang-yu Shi, Bo Liang, Qi Zhang
Summary: This paper explores the application of post-selection inference in generalized linear models and presents new methods for post-selection inference for penalized least squares method. Empirical results demonstrate that the proposed methods outperform existing ones.
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
(2022)
Article
Mathematics, Applied
R. Alshenawy, Navid Feroze, Ali Al-Alwan, Mahreen Saleem, Sahidul Islam
Summary: This study discusses the posterior estimation for the parameters of the Burr type II distribution and compares its modeling capability with seven classes of lifetime distributions, showing that the Burr type II distribution can efficiently replace commonly used distributions.
JOURNAL OF FUNCTION SPACES
(2022)
Article
Chemistry, Analytical
Yusuke Nakai, Akira Noda, Eiichi Yamamoto
Summary: The stability of APIs and formulations is crucial in the pharmaceutical industry, affecting research and development feasibility, development period, and costs. To predict early-stage formulation stability accurately, we developed an algorithm combining Bayesian inference and the conventional Arrhenius equation, providing a narrow confidence interval even with data variations. Our method enables the reasonable prediction of long-term drug stability and contributes to pharmaceutical product development worldwide.
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS
(2023)
Article
Mathematics, Interdisciplinary Applications
Piero Veronese, Eugenio Melilli
Summary: This paper introduces novel point estimators and confidence intervals for the ability parameter in the Rasch model, based on a proposed confidence distribution. Simulation studies demonstrate the effectiveness of these methods compared to standard frequentist and Bayesian procedures. Using the expected length of the suggested interval, reasonable sample sizes leading to desired interval lengths can be identified.
Article
Statistics & Probability
Andrea C. Garcia-Angulo, Gerda Claeskens
Summary: Conditioning on the event of selecting a model leads to the construction of uniformly optimal conditional confidence distributions, which can be used for valid postselection inference, including the construction of confidence intervals and hypothesis tests.
SCANDINAVIAN JOURNAL OF STATISTICS
(2023)
Article
Statistics & Probability
Eugen Pircalabelu, Gerda Claeskens
Summary: We propose a high-dimensional graphical modeling approach for functional data, which addresses the issue of having more functions than available samples. By using a sparse estimator and identifying linear manifolds, we can infer the connections between functional nodes and estimate multiple related graphs simultaneously.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2023)
Article
Statistics & Probability
Jing Zhou, Gerda Claeskens
Summary: This research proposes a robust testing framework to deal with the complicated asymptotic distribution of test statistics based on regularized estimators in high dimensions. The framework is implemented using the robust approximate message passing algorithm and includes built-in bias correction. It is applicable to general convex non-differentiable loss functions and allows for inference on conditional quantiles.
STATISTICA NEERLANDICA
(2023)
Article
Statistics & Probability
Roel Verbelen, Katrien Antonio, Gerda Claeskens, Jonas Crevecoeur
Summary: This study examines the relationship between the delay in occurrence and reporting of events and proposes a flexible regression framework for the joint estimation of event occurrence and reporting. By relating this framework to an incomplete data problem, estimation is carried out using an expectation-maximization algorithm. The proposed method is elegant, easy to understand and implement, and provides accurate predictions.
STATISTICAL SCIENCE
(2022)
Article
Statistics & Probability
Ioannis Kalogridis, Gerda Claeskens, Stefan Van Aelst
Summary: Generalized linear models are flexible tools for analyzing diverse datasets, but the classical formulation has limitations such as the requirement for correctly specified parametric component and absence of atypical observations. To overcome these issues, we propose and study a family of nonparametric spline estimators that are obtained through the minimization of a penalized density power divergence. These estimators are easily implementable, offer high protection against outliers, and can be tuned for high efficiency in clean data scenarios. We demonstrate that these estimators converge rapidly under weak assumptions and showcase their competitive performance through simulation and real-data examples.
Article
Pharmacology & Pharmacy
Andrea Orellana-Manzano, Fernanda B. Cordeiro, Andrea Garcia-Angulo, Elizabeth Centeno, Maria Jose Vizcaino-Tumbaco, Sebastian Poveda, Ricardo Murillo, Derly Andrade-Molina, Mariuxi Miraba, Saurabh Mehta, Washington Cardenas
Summary: This retrospective study investigated 10,175 individuals who underwent RT-PCR tests in Ecuador from July to November 2020. The results showed no association between RT-PCR results and sex, age, or comorbidities in positive COVID-19 cases. Cotopaxi and Napo had the highest rates of positive cases, while Manabi, Santa Elena, and Guayas regions had lower rates. Drug consumption was higher in negative COVID-19 cases compared to positive cases, and acetaminophen was the most commonly consumed medication in both groups. Acetaminophen and antihistamines had higher odds of consumption in positive cases. Symptoms like fever and cough were more related to positive RT-PCR results.
FRONTIERS IN PHARMACOLOGY
(2023)
Meeting Abstract
Pharmacology & Pharmacy
Andrea Orellana Manzano, Fernanda B. Cordeiro, Andrea Garcia-Angulo, Diana Carvajal-Aldaz, Elizabeth Centeno, Maria J. Vizcaino, Sebastian Poveda, Ricardo Murillo, Derly Andrade-Molina, Saurabh Mehta, Washinton Cardenas
JOURNAL OF PHARMACOLOGY AND EXPERIMENTAL THERAPEUTICS
(2023)
Article
Economics
Lore Dirick, Gerda Claeskens, Andrey Vasnev, Bart Baesens
Summary: This study focuses on the specific nature of credit loan data and proposes the use of mixture cure models for survival analysis. The constructed models incorporate competing risks, such as early repayment and default, as well as maturity and unobserved heterogeneity within risk groups. A hierarchical expectation-maximization algorithm is developed to fit the models and estimate standard errors. Simulations and data analysis demonstrate the applicability and benefits of these models, particularly in improving event time estimation.
ECONOMETRICS AND STATISTICS
(2022)
Article
Statistics & Probability
Marija Tepegjozova, Jing Zhou, Gerda Claeskens, Claudia Czado
Summary: Quantile regression is an increasingly important field in statistical modeling. This paper introduces a nonparametric quantile regression approach based on copulas, which allows separate modeling of marginal distributions and dependence structure, resulting in a flexible and accurate model.
DEPENDENCE MODELING
(2022)
Article
Statistics & Probability
Gerda Claeskens, Emilie Devijver, Irene Gijbels
Summary: The paper introduces the use of a nonlinear mixed effects model in functional data to find the global mean pattern and capture individual curve differences in phase and amplitude. The study provides sufficient and necessary conditions for model identifiability, and validates the effectiveness of the proposed method through theoretical and simulation research.
ELECTRONIC JOURNAL OF STATISTICS
(2021)
Article
Statistics & Probability
Jing Zhou, Gerda Claeskens, Jelena Bradic
ELECTRONIC JOURNAL OF STATISTICS
(2020)
Article
Automation & Control Systems
Eugen Pircalabelu, Gerda Claeskens
JOURNAL OF MACHINE LEARNING RESEARCH
(2020)
Article
Statistics & Probability
Omidali Aghababaei Jazi
Summary: In this paper, a pseudo-partial likelihood estimation method is proposed to estimate parameters in the Cox proportional hazards model with right-censored and biased sampling data by adjusting sample risk sets. The asymptotic properties of the resulting estimator are studied, and a simulation study is conducted to illustrate the finite sample performance. The proposed method is also applied to analyze a set of HIV/AIDS data.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Liya Fu, Shuwen Hu, Jiaqi Li
Summary: Empirical likelihood (EL) is an effective nonparametric method that combines estimating equations flexibly and adaptively. A penalized EL method based on robust estimating functions is proposed for variable selection in a high-dimensional model, allowing the dimensions to grow exponentially with the sample size. The proposed method improves robustness and effectiveness in the presence of outliers or heavy-tailed data. Extensive simulation studies and a real data example demonstrate the enhanced variable selection accuracy when dealing with heavy-tailed data or outliers.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Yifan Sun, Ziyi Liu, Wu Wang
Summary: This paper extends the classical functional linear regression model to allow for heterogeneous coefficient functions among different subgroups of subjects. A penalization-based approach is proposed to simultaneously determine the number and structure of subgroups and coefficient functions within each subgroup. The paper provides an effective computational algorithm and establishes the oracle properties and estimation consistency of the model. Extensive numerical simulations demonstrate its superiority compared to competing methods, and an analysis of an air quality dataset leads to interesting findings and improved predictions.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Takemi Yanagimoto, Yoichi Miyata
Summary: A Bayesian estimator is proposed to improve the conditional maximum likelihood estimation by introducing a pair of priors. The conditional maximum likelihood estimation is explained using the posterior mode under a prior, and a promising estimator is defined using the posterior mean under a corresponding prior. The advantages of this approach include two different optimality properties of the induced estimator, the ease of various extensions, and the possible treatments for a finite sample size. The existing approaches are discussed and critiqued.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Sameera Hewage, Yongli Sang
Summary: This paper introduces a new method for measuring dependence, the categorical Gini correlation rho(g), and proposes a Jackknife empirical likelihood approach for constructing confidence intervals. Simulation studies and real data applications demonstrate competitive performance of the proposed method in terms of coverage accuracy and interval length.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Isadora Antoniano-Villalobos, Cristiano Villa, Stephen G. Walker
Summary: Constructing objective priors for multidimensional parameter spaces is challenging, and a common approach assumes independence and uses standard objective methods to obtain marginal distributions. In this paper, a novel objective prior is proposed by extending the objective method for one-dimensional case, allowing for a dependence structure in multidimensional parameter spaces.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Hui Li, Liuqing Yang, Kashinath Chatterjee, Min-Qian Liu
Summary: Supersaturated design (SSD) plays a crucial role in factor screening, and E(f(NOD)) criterion is one of the most widely used criteria for evaluating multi-level and mixed-level SSDs. This paper provides methods to construct multi-level E(f(NOD)) optimal SSDs with general run sizes, which can also be extended to mixed-level SSDs. The main idea of these methods is to combine two processed generalized Hadamard matrices with the expansive replacement method. These proposed methods are easy to implement, and the non-orthogonality between any two columns of the resulting SSDs is well controlled by that of the source designs.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Victoria L. Leaver, Robert G. Clark, Pavel N. Krivitsky, Carole L. Birrell
Summary: This article compares three likelihood approaches to estimation under informative sampling and examines their efficiency and asymptotic variance. The study shows that sample likelihood estimation approaches the efficiency of full maximum likelihood estimation when the sample size tends to infinity and the sampling fraction tends to zero. However, when the sample size tends to infinity and the sampling fraction is not negligible, maximum likelihood estimation is more efficient due to considering the possibility of duplicate samples. Pseudo-likelihood estimation can perform poorly in certain cases. For a special case where the superpopulation is exponential and the selection is probability proportional to size, the anticipated variance of pseudo-likelihood estimation is infinite.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Fadoua Balabdaoui, Harald Besdziek
Summary: The two-component mixture model with known background density, unknown signal density, and unknown mixing proportion has been studied in this paper. The log-concave MLE of the signal density is computed using the estimator of Patra & Sen (2016), and its consistency and convergence are shown. The performance of this method is evaluated through a simulation study.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
V. Girardin, R. Senoussi
Summary: This paper investigates different issues related to stationarity reduction in autoregressive models, including both continuous and discrete time cases. Necessary and sufficient conditions for autoregressive models to be weakly stationary are explored, with explicit formulas for the time changes. Furthermore, the issue of stationarity reduction for discrete sequences sampled from continuous time autoregressive processes is also considered.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Juan Jose Fernandez-Duran, Maria Mercedes Gregorio-Dominguez
Summary: This paper presents the application of nonnegative trigonometric sums (NNTS) models in circular data analysis. Regression models for circular-dependent variables are constructed by fitting great circles on the parameter hypersphere, enabling the identification of different regions along the circle. The transformation of the original circular variable into a linear variable allows for the application of common linear regression methods in circular data analysis.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Miao Han, Yuanyuan Lin, Wenxin Liu, Zhanfeng Wang
Summary: The article proposes a method based on maximum rank correlation and concave fusion to automatically determine the number of subgroups, identify subgroup structure, and estimate subgroup-specific covariate effects. The method can be used without prior grouping information and is applicable to handling censored data.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)
Article
Statistics & Probability
Qing He, Hsin-Hsiung Huang
Summary: This article introduces a method for spatiotemporal data analysis with massive zeros, which is widely used in epidemiology and public health. The method fits zero-inflated negative binomial models using a Bayesian framework and employs latent variables from Polya-Gamma distributions to improve computational efficiency.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2024)