Uniformly consistent proportion estimation for composite hypotheses via integral equations
| Autor: | Chen, Xiongzhi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | We consider estimating the proportion of random variables for two types of composite null hypotheses: (i) the means or medians of the random variables belonging to a non-empty, bounded interval; (ii) the means or medians of the random variables belonging to an unbounded interval that is not the whole real line. For each type of composite null hypotheses, uniform consistent estimators of the proportion of false null hypotheses are constructed respectively for random variables whose distributions are members of a Type I location-shift family or are members of the Gamma family. Further, uniformly consistent estimators of certain functions of a bounded null on the means or medians are provided for the two types of random variables mentioned earlier. These functions are continuous and of bounded variation. The estimators are constructed via solutions to Lebesgue-Stieltjes integral equations and harmonic analysis, do not rely on a concept of p-value, can be used to construct adaptive false discovery rate procedures and adaptive false nondiscovery rate procedures for multiple hypothesis testing, can be used in Bayesian inference via mixture models, and may be used to estimate the sparsity level in high-dimensional Gaussian linear models. Comment: 69 pages in 1.5-line spacing; 3 figures; added a section to illustrate the methods; extended simulations to include estimators based on randomized p-values; added contents on constructing Type I location-shift family; other minor edits |
| Databáze: | arXiv |
| Externí odkaz: |
|