We consider the minimax rate of testing (or estimation) of non-linear functionals defined on semiparametric models. Existing methods appear not capable of determining a lower bound on the minimax rate of testing (or estimation) for certain functionals of interest. In particular, if the semiparametric model is indexed by several infinite-dimensional parameters. To cover these examples we extend the approach of [1], which is based on comparing a "true distribution" to a convex mixture of perturbed distributions to a comparison of two convex mixtures. The first mixture is obtained by perturbing a first parameter of the model, and the second by perturbing in addition a second parameter. We apply the new result to two examples of semiparametric functionals:the estimation of a mean response when response data are missing at random, and the estimation of an expected conditional covariance functional.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5884174 | PMC |
| http://dx.doi.org/10.1214/09-EJS479 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A phase I study of temsirolimus in combination with metformin in patients with advanced or recurrent endometrial cancer.
Gynecol Oncol
January 2025
Department of Investigational Cancer Therapeutics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
Introduction: Molecular alterations in the PI3K/AKT and Ras/Raf/MEK/ERK pathways are frequently observed in patients with endometrial cancers. However, mTOR inhibitors, such as temsirolimus, have modest clinical benefits. In addition to inducing metabolic changes in cells, metformin activates AMPK, which in turn inhibits the mTOR pathway.
View Article and Find Full Text PDFCovariate-Assisted Bayesian Graph Learning for Heterogeneous Data.
J Am Stat Assoc
September 2023
Department of Statistics, Texas A&M University.
In a traditional Gaussian graphical model, data homogeneity is routinely assumed with no extra variables affecting the conditional independence. In modern genomic datasets, there is an abundance of auxiliary information, which often gets under-utilized in determining the joint dependency structure. In this article, we consider a Bayesian approach to model undirected graphs underlying heterogeneous multivariate observations with additional assistance from covariates.
View Article and Find Full Text PDFNeoadjuvant Chemotherapy with Concurrent Letrozole for Estrogen Receptor-Positive and HER2-Negative Breast Cancer: An Open-Label, Single-Center, Nonrandomized Phase II Study (NeoCHAI).
Cancers (Basel)
September 2024
Department of Internal Medicine, Center for Breast Cancer, Hospital, National Cancer Center, 323 Ilsanro, Goyang 10408, Republic of Korea.
Article Synopsis
- A phase II trial was conducted to evaluate the effectiveness of combining letrozole (an endocrine therapy) with traditional chemotherapy in women with untreated stage II or III HR-positive, HER2-negative breast cancer.
- Out of 53 patients, only 2 (4%) achieved a pathologic complete response (pCR), which was below the necessary threshold to continue the trial, though the overall response rate was high at 83%.
- The treatment was deemed safe, with a 3-year disease-free survival rate of 87% and no deaths during treatment, but it did not significantly improve pCR rates, indicating the need for further research on neoadjuvant therapies for this cancer type.
Neural Operator Variational Inference Based on Regularized Stein Discrepancy for Deep Gaussian Processes.
IEEE Trans Neural Netw Learn Syst
August 2024
Deep Gaussian process (DGP) models offer a powerful nonparametric approach for Bayesian inference, but exact inference is typically intractable, motivating the use of various approximations. However, existing approaches, such as mean-field Gaussian assumptions, limit the expressiveness and efficacy of DGP models, while stochastic approximation can be computationally expensive. To tackle these challenges, we introduce neural operator variational inference (NOVI) for DGPs.
View Article and Find Full Text PDFEstimation and Inference for High-Dimensional Generalized Linear Models with Knowledge Transfer.
J Am Stat Assoc
April 2023
Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104.
Transfer learning provides a powerful tool for incorporating data from related studies into a target study of interest. In epidemiology and medical studies, the classification of a target disease could borrow information across other related diseases and populations. In this work, we consider transfer learning for high-dimensional generalized linear models (GLMs).
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!