We prove conditional asymptotic normality of a class of quadratic U-statistics that are dominated by their degenerate second order part and have kernels that change with the number of observations. These statistics arise in the construction of estimators in high-dimensional semi- and non-parametric models, and in the construction of nonparametric confidence sets. This is illustrated by estimation of the integral of a square of a density or regression function, and estimation of the mean response with missing data. We show that estimators are asymptotically normal even in the case that the rate is slower than the square root of the observations.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5232897 | PMC |
| http://dx.doi.org/10.1016/j.spa.2016.04.005 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Growth modeling of the European grayling (Thymallus thymallus L.) in a large alpine river based on age-at-length, mark-recapture, and length-frequency data.
J Fish Biol
January 2025
Aquatic Systems Biology Unit, TUM School of Life Sciences, Technical University of Munich, Freising, Germany.
Animal growth is a fundamental component of population dynamics, which is closely tied to mortality, fecundity, and maturation. As a result, estimating growth often serves as the basis of population assessments. In fish, analysing growth typically involves fitting a growth model to age-at-length data derived from counting growth rings in calcified structures.
View Article and Find Full Text PDFA global kernel estimator for partially linear varying coefficient additive hazards models.
Lifetime Data Anal
January 2025
Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China.
We study kernel-based estimation methods for partially linear varying coefficient additive hazards models, where the effects of one type of covariates can be modified by another. Existing kernel estimation methods for varying coefficient models often use a "local" approach, where only a small local neighborhood of subjects are used for estimating the varying coefficient functions. Such a local approach, however, is generally inefficient as information about some non-varying nuisance parameter from subjects outside the neighborhood is discarded.
View Article and Find Full Text PDFIdentifying genetic susceptibility loci associated with human coronary artery disease.
PLoS One
January 2025
Division of Life Science, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, China.
Coronary artery disease (CAD) is a multigenic condition influenced by both nature and nurture (60% to 40%). Prognosis of CAD is based on familial patterns. This study examined and analyzed the susceptibility of CAD to genetic variants in various Pakistani families.
View Article and Find Full Text PDFTesting measurement invariance in a conditional likelihood framework by considering multiple covariates simultaneously.
Behav Res Methods
January 2025
Paris Lodron University Salzburg, Kapitelgasse 4-6, 5020, Salzburg, Austria.
This article addresses the problem of measurement invariance in psychometrics. In particular, its focus is on the invariance assumption of item parameters in a class of models known as Rasch models. It suggests a mixed-effects or random intercept model for binary data together with a conditional likelihood approach of both estimating and testing the effects of multiple covariates simultaneously.
View Article and Find Full Text PDFWeighted Q-learning for optimal dynamic treatment regimes with nonignorable missing covariates.
Biometrics
January 2025
MRC Biostatistics Unit, School of Clinical Medicine, University of Cambridge, Cambridge, CB2 0SR, United Kingdom.
Dynamic treatment regimes (DTRs) formalize medical decision-making as a sequence of rules for different stages, mapping patient-level information to recommended treatments. In practice, estimating an optimal DTR using observational data from electronic medical record (EMR) databases can be complicated by nonignorable missing covariates resulting from informative monitoring of patients. Since complete case analysis can provide consistent estimation of outcome model parameters under the assumption of outcome-independent missingness, Q-learning is a natural approach to accommodating nonignorable missing covariates.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!