On the asymptotic of likelihood ratios for self-normalized large deviations

arXiv0709.1506MaRDI QIDQ6206752FDOQ6206752

Authors: Zhiyi Chi 

Publication date: 10 September 2007

Abstract: Motivated by multiple statistical hypothesis testing, we obtain the limit of likelihood ratio of large deviations for self-normalized random variables, specifically, the ratio of $$ to $$, as $noi$, where $$ and $V$ are the sample mean and standard deviation of iid $X_1,\mathrm{...},X_n$, respectively, $d>0$ is a constant and $x_{n}oi$. We show that the limit can have a simple form $e^{d/z_0}$, where $z_0$ is the unique maximizer of $zf(x)$ with $f$ the density of $X_i$. The result is applied to derive the minimum sample size per test in order to control the error rate of multiple testing at a target level, when real signals are different from noise signals only by a small shift.

Mathematics Subject Classification ID

Large deviations (60F10) Hypothesis testing in multivariate analysis (62H15)

This page was built for publication: On the asymptotic of likelihood ratios for self-normalized large deviations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6206752)