---
title: "The structure of the concentration and covariance matrix in a naive Bayes model"
author: "Mikkel Meyer Andersen and Søren Højsgaard"
date: "`r Sys.Date()`"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{The structure of the concentration and covariance matrix in a naive Bayes model}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r, message=FALSE}
library(Ryacas)
```

## Naive Bayes model

Consider this model: 
$$
x_i = a x_0 + e_i, \quad i=1, \dots, 4
$$ 
and $x_0=e_0$. All terms $e_0, \dots, e_3$ are independent and $N(0,1)$ distributed. 
Let $e=(e_0, \dots, e_3)$ and $x=(x_0, \dots x_3)$.
Isolating error terms gives that
$$
 e = L_1 x
$$
where $L_1$ has the form
```{r}
L1chr <- diag(4)
L1chr[2:4, 1] <- "-a"
L1 <- ysym(L1chr)
L1
```

If error terms have variance $1$ then $\mathbf{Var}(e)=L \mathbf{Var}(x) L'$ so the covariance matrix is $V1=\mathbf{Var}(x) = L^- (L^-)'$ while the concentration matrix (the inverse covariances matrix) is $K=L' L$.

```{r}
L1inv <- solve(L1)
K1 <- t(L1) %*% L1
V1 <- L1inv %*% t(L1inv)
```

```{r, results="asis"}
cat(
  "\\begin{align} 
    K_1 &= ", tex(K1), " \\\\ 
   V_1 &= ", tex(V1), " 
  \\end{align}", sep = "")
```

Slightly more elaborate:

```{r}
L2chr <- diag(4)
L2chr[2:4, 1] <- c("-a1", "-a2", "-a3")
L2 <- ysym(L2chr)
L2
Vechr <- diag(4)
Vechr[cbind(1:4, 1:4)] <- c("w1", "w2", "w2", "w2")
Ve <- ysym(Vechr)
Ve
```

```{r}
L2inv <- solve(L2)
K2 <- t(L2) %*% solve(Ve) %*% L2
V2 <- L2inv %*% Ve %*% t(L2inv)
```

```{r, results="asis"}
cat(
  "\\begin{align} 
    K_2 &= ", tex(K2), " \\\\ 
   V_2 &= ", tex(V2), " 
  \\end{align}", sep = "")
```