$\newcommand{\e}{\varepsilon}$$\newcommand{\one}{\mathbf 1}$Suppose I have collected data $X \in \mathbb R^{n\times p}$ ($n \geq p$ and $X$ is full column rank…
$\newcommand{\X}{\mathcal X}$$\newcommand{\dl}{\,\text d\lambda}$$\newcommand{\dx}{\,\text dx}$$\newcommand{\one}{\mathbf 1}$I’m going to take a look at functional linear regression, where I’ll find the best linear…
$\newcommand{\bern}{\text{Bern}}$$\newcommand{\vp}{\varphi}$$\newcommand{\e}{\varepsilon}$$\newcommand{\P}{\mathcal P}$$\newcommand{\Cov}{\text{Cov}}$$\newcommand{\E}{\text{E}}$$\newcommand{\one}{\mathbf 1}$$\newcommand{\s}{\mathbf s}$$\newcommand{\Disc}{\text{Disc}}$In this post I’m going to explore correlations between finitely-supported discrete variables. Bernoulli case I’ll begin with…