Abstract:
Exact upper and lower bounds on the ratio
$\operatorname{\mathbf{E}}w(\mathbf{X}-\mathbf{v})/\operatorname{\mathbf{E}}w(\mathbf{X})$ for a centered
Gaussian random vector $\mathbf{X}$ in $\mathbf{R}^n$ are obtained, as well as bounds on
the rate of change of $\operatorname{\mathbf{E}}w(\mathbf{X}-t\mathbf{v})$ in $t$, where
$w\colon\mathbf{R}^n\to[0,\infty)$ is any even unimodal function and
$\mathbf{v}$ is any vector in $\mathbf{R}^n$. As a corollary of such results,
exact upper and lower bounds on the power function of statistical tests for
the mean of a multivariate normal distribution are given.
Keywords:Gaussian measures, multivariate normal distribution, shifts, unimodality, logconcavity, monotonicity, exact bounds, tests for the mean.