Optimal Inference with a Multidimensional Multiscale Statistic

Pratyay Datta, Bodhisattva Sen

We observe a stochastic process $Y$ on $[0,1{]}^d$ ($d\ge 1$) satisfying $dY(t)=n^{1/2}f(t)dt$ + $dW(t)$, $t\in [0,1{]}^d$, where $n\ge 1$ is a given scale parameter (`sample size'…