I'm reproducing from scratch the results in Section 4.2.1 of
Marginal Likelihood from the Gibbs Output
Siddhartha Chib
Journal of the American Statistical Association, Vol. 90, No. 432. (Dec., 1995), pp. 1313-1321.
It's a mixture of normals model with known number $k\geq 1$ of components. $$ f(x\mid w,\mu,\sigma^2) =\prod_{i=1}^n\sum_{j=1}^k \mathrm{N}(x_i\mid\mu_j,\sigma_j^2) \, . \qquad (*) $$
The Gibbs sampler for this model is implemented using the data augmentation technique of Tanner and Wong. A set of allocation variables $z=(z_1,\dots,z_n)$ assuming the values $1,\dots,k$ is introduced, and we specify that $\Pr(z_i=j\mid w)=w_j$ and $f(x_i\mid z,\mu,\sigma^2)=\mathrm{N}(x_i\mid\mu_{z_i},\sigma^2_{z_i})$. It follows that integration over the $z_i$'s gives the original likelihood $(*)$.
The dataset is formed by velocities of $82$ galaxies from the Corona Borealis constellation.
set.seed(1701)
x <- c( 9.172, 9.350, 9.483, 9.558, 9.775, 10.227, 10.406, 16.084, 16.170, 18.419, 18.552, 18.600, 18.927,
19.052, 19.070, 19.330, 19.343, 19.349, 19.440, 19.473, 19.529, 19.541, 19.547, 19.663, 19.846, 19.856,
19.863, 19.914, 19.918, 19.973, 19.989, 20.166, 20.175, 20.179, 20.196, 20.215, 20.221, 20.415, 20.629,
20.795, 20.821, 20.846, 20.875, 20.986, 21.137, 21.492, 21.701, 21.814, 21.921, 21.960, 22.185, 22.209,
22.242, 22.249, 22.314, 22.374, 22.495, 22.746, 22.747, 22.888, 22.914, 23.206, 23.241, 23.263, 23.484,
23.538, 23.542, 23.666, 23.706, 23.711, 24.129, 24.285, 24.289, 24.366, 24.717, 24.990, 25.633, 26.960,
26.995, 32.065, 32.789, 34.279 )
nn <- length(x)
We assume that $w$, the $\mu_j$'s, and the $\sigma^2_j$'s are independent a priori with $$ (w_1,\dots,w_k) \sim \mathrm{Dir}(a_1,\dots,a_k) \, , \quad \mu_j \sim \mathrm{N}(\mu_0,\sigma_0^2) \, , \quad \sigma^2_j\sim\mathrm{IG}\!\left(\frac{\nu_0}{2},\frac{\delta_0}{2}\right) \, . $$
k <- 3
mu0 <- 20
va0 <- 100
nu0 <- 6
de0 <- 40
a <- rep(1, k)
Using Bayes' Theorem, the full conditionals are $$ \begin{align*} w \mid \mu,\sigma^2,z,x &\sim \mathrm{Dir}(a_1+n_1,\dots,a_k+n_k) \\ \mu_j \mid w, \sigma^2,z,x &\sim \mathrm{N}\!\left( \frac{n_j m_j\sigma_0^2+\mu_0\sigma_j^2}{n_j\sigma^2_0+\sigma^2_j}, \frac{\sigma^2_0\sigma^2_j}{n_j\sigma^2_0+\sigma^2_j}\right) \\ \sigma_j^2 \mid w,\mu,z,x &\sim \mathrm{IG}\!\left( \frac{\nu_0+n_j}{2},\frac{\delta_0+\delta_j}{2}\right) \\ \Pr(z_i=j\mid w,\mu,\sigma^2,x) &\propto w_j \times \frac{1}{\sigma_j}e^{-(x_i-\mu_j)^2/2\sigma_j^2} \end{align*} $$ in which $$ n_j = |L_j| \, , \qquad m_j = \begin{cases}\frac{1}{n_j}\sum_{i\in L_j} x_i &\;\mathrm{if}\; n_j>0 \\ 0 &\;\mathrm{otherwise.} \end{cases}\, , \qquad \delta_j = \sum_{i\in L_j} (x_i-\mu_j)^2 \, , $$ with $L_j=\{i\in\{1,\dots,n\}:z_i=j\}$.
The goal is to compute an estimate for the marginal likelihood of the model. Chib's method begins with a first run of the Gibbs sampler using the full conditionals.
burn_in <- 1000
run <- 15000
cat("First Gibbs run (full):\n")
N <- burn_in + run
w <- matrix(1, nrow = N, ncol = k)
mu <- matrix(0, nrow = N, ncol = k)
va <- matrix(1, nrow = N, ncol = k)
z <- matrix(1, nrow = N, ncol = nn)
n <- integer(k)
m <- numeric(k)
de <- numeric(k)
rdirichlet <- function(a) { y <- rgamma(length(a), a, 1); y / sum(y) }
pb <- txtProgressBar(min = 2, max = N, style = 3)
z[1,] <- sample.int(k, size = nn, replace = TRUE)
for (t in 2:N) {
n <- tabulate(z[t-1,], nbins = k)
w[t,] <- rdirichlet(a + n)
m <- sapply(1:k, function(j) sum(x[z[t-1,]==j]))
m[n > 0] <- m[n > 0] / n[n > 0]
mu[t,] <- rnorm(k, mean = (n*m*va0+mu0*va[t-1,])/(n*va0+va[t-1,]), sd = sqrt(va0*va[t-1,]/(n*va0+va[t-1,])))
de <- sapply(1:k, function(j) sum((x[z[t-1,]==j] - mu[t,j])^2))
va[t,] <- 1 / rgamma(k, shape = (nu0+n)/2, rate = (de0+de)/2)
z[t,] <- sapply(1:nn, function(i) sample.int(k, size = 1, prob = exp(log(w[t,]) + dnorm(x[i], mean = mu[t,], sd = sqrt(va[t,]), log = TRUE))))
setTxtProgressBar(pb, t)
}
close(pb)
From this first run we get an approximate point $(w^*,\mu^*,\sigma^{2*})$ of maximum likelihood. Since the likelihood is actually unbounded, what this procedure probably gives is an approximate local MAP.
w <- w[(burn_in+1):N,]
mu <- mu[(burn_in+1):N,]
va <- va[(burn_in+1):N,]
z <- z[(burn_in+1):N,]
N <- N - burn_in
log_L <- function(x, w, mu, va) sum(log(sapply(1:nn, function(i) sum(exp(log(w) + dnorm(x[i], mean = mu, sd = sqrt(va), log = TRUE))))))
ts <- which.max(sapply(1:N, function(t) log_L(x, w[t,], mu[t,], va[t,])))
ws <- w[ts,]
mus <- mu[ts,]
vas <- va[ts,]
Chib's log-estimate of the marginal likelihood is $$ \begin{align} \log \widehat{f(x)} &= \log L_x(w^*,\mu^*,\sigma^{2*}) + \log \pi(w^*,\mu^*,\sigma^{2*}) \\ &- \log \pi(\mu^*\mid x) - \log \pi(\sigma^{2*}\mid \mu^*,x) - \log \pi(w^*\mid \mu^*,\sigma^{2*},x) \, . \end{align} $$
We already have the first two terms.
log_prior <- function(w, mu, va) {
lgamma(sum(a)) - sum(lgamma(a)) + sum((a-1)*log(w))
+ sum(dnorm(mu, mean = mu0, sd = sqrt(va0), log = TRUE))
+ sum((nu0/2)*log(de0/2) - lgamma(nu0/2) - (nu0/2+1)*log(va) - de0/(2*va))
}
chib <- log_L(x, ws, mus, vas) + log_prior(ws, mus, vas)
The Rao-Blackwellized estimate of $\pi(\mu^*\mid x)$ is $$ \pi(\mu^*\mid x) = \int \prod_{j=1}^k \mathrm{N}\!\left(\mu_j^* \;\Bigg|\; \frac{n_j m_j\sigma_0^2+\mu_0\sigma_j^2}{n_j\sigma^2_0+\sigma^2_j}, \frac{\sigma^2_0\sigma^2_j}{n_j\sigma^2_0+\sigma^2_j}\right)\,p(\sigma^{2},z\mid x)\,d\sigma^2\,dz \, , $$ and is readily obtained from the first Gibbs run.
pi.mu_va.z.x <- function(mu, va, z) {
n <- tabulate(z, nbins = k)
m <- sapply(1:k, function(j) sum(x[z==j]))
m[n > 0] <- m[n > 0] / n[n > 0]
exp(sum(dnorm(mu, mean = (n*m*va0+mu0*va)/(n*va0+va), sd = sqrt(va0*va/(n*va0+va)), log = TRUE)))
}
chib <- chib - log(mean(sapply(1:N, function(t) pi.mu_va.z.x(mus, va[t,], z[t,]))))
The Rao-Blackwellized estimate of $\pi(\sigma^{2*}\mid \mu^*,x)$ is $$ \pi(\sigma^{2*}\mid \mu^*,x) = \int \prod_{j=1}^k \mathrm{IG}\!\left( \sigma^{2*}_j \;\Bigg|\; \frac{\nu_0+n_j}{2},\frac{\delta_0+\delta_j}{2}\right) \, p(z\mid\mu^*,x)\,dz \, , $$ and is computed from a second reduced Gibbs run in which the $\mu_j$'s are not updated, but made equal to $\mu^*_j$ at each iteration step.
cat("Second Gibbs run (reduced):\n")
N <- burn_in + run
w <- matrix(1, nrow = N, ncol = k)
va <- matrix(1, nrow = N, ncol = k)
z <- matrix(1, nrow = N, ncol = nn)
pb <- txtProgressBar(min = 2, max = N, style = 3)
z[1,] <- sample.int(k, size = nn, replace = TRUE)
for (t in 2:N) {
n <- tabulate(z[t-1,], nbins = k)
w[t,] <- rdirichlet(a + n)
de <- sapply(1:k, function(j) sum((x[z[t-1,]==j] - mus[j])^2))
va[t,] <- 1 / rgamma(k, shape = (nu0+n)/2, rate = (de0+de)/2)
z[t,] <- sapply(1:nn, function(i) sample.int(k, size = 1, prob = exp(log(w[t,]) + dnorm(x[i], mean = mus, sd = sqrt(va[t,]), log = TRUE))))
setTxtProgressBar(pb, t)
}
close(pb)
w <- w[(burn_in+1):N,]
va <- va[(burn_in+1):N,]
z <- z[(burn_in+1):N,]
N <- N - burn_in
pi.va_mu.z.x <- function(va, mu, z) {
n <- tabulate(z, nbins = k)
de <- sapply(1:k, function(j) sum((x[z==j] - mu[j])^2))
exp(sum(((nu0+n)/2)*log((de0+de)/2) - lgamma((nu0+n)/2) - ((nu0+n)/2+1)*log(va) - (de0+de)/(2*va)))
}
chib <- chib - log(mean(sapply(1:N, function(t) pi.va_mu.z.x(vas, mus, z[t,]))))
In the same way, the Rao-Blackwellized estimate of $\pi(w^*\mid \mu^*,\sigma^{2*},x)$ is $$ \pi(w^*\mid \mu^*,\sigma^{2*},x) = \int \mathrm{Dir}(w^* \mid a_1+n_1,\dots,a_k+n_k) \, p(z\mid\mu^*,\sigma^{2*},x)\,dz \, , $$ and is computed from a third reduced Gibbs run in which the $\mu_j$'s and the $\sigma^2_j$'s are not updated, but made equal to $\mu^*_j$ and $\sigma^{2*}_j$ respectively at each iteration step.
cat("Third Gibbs run (reduced):\n")
N <- burn_in + run
w <- matrix(1, nrow = N, ncol = k)
z <- matrix(1, nrow = N, ncol = nn)
pb <- txtProgressBar(min = 2, max = N, style = 3)
z[1,] <- sample.int(k, size = nn, replace = TRUE)
for (t in 2:N) {
n <- tabulate(z[t-1,], nbins = k)
w[t,] <- rdirichlet(a + n)
z[t,] <- sapply(1:nn, function(i) sample.int(k, size = 1, prob = exp(log(w[t,]) + dnorm(x[i], mean = mus, sd = sqrt(vas), log = TRUE))))
setTxtProgressBar(pb, t)
}
close(pb)
w <- w[(burn_in+1):N,]
z <- z[(burn_in+1):N,]
N <- N - burn_in
pi.w_z.x <- function(w, z) {
n <- tabulate(z, nbins = k)
exp(lgamma(sum(a+n)) - sum(lgamma(a+n)) + sum((a+n-1)*log(w)))
}
chib <- chib - log(mean(sapply(1:N, function(t) pi.w_z.x(ws, z[t,]))))
After all this, we get a log-estimate $-217.9199$ which is bigger than the one reported by Chib: $-224.138$ with Monte Carlo error $.086$.
To check if I somehow messed up the Gibbs samplers, I reimplemented the whole thing using RJAGS. The following code gives the same results.
x <- c( 9.172, 9.350, 9.483, 9.558, 9.775, 10.227, 10.406, 16.084, 16.170, 18.419, 18.552, 18.600, 18.927, 19.052, 19.070, 19.330,
19.343, 19.349, 19.440, 19.473, 19.529, 19.541, 19.547, 19.663, 19.846, 19.856, 19.863, 19.914, 19.918, 19.973, 19.989, 20.166,
20.175, 20.179, 20.196, 20.215, 20.221, 20.415, 20.629, 20.795, 20.821, 20.846, 20.875, 20.986, 21.137, 21.492, 21.701, 21.814,
21.921, 21.960, 22.185, 22.209, 22.242, 22.249, 22.314, 22.374, 22.495, 22.746, 22.747, 22.888, 22.914, 23.206, 23.241, 23.263,
23.484, 23.538, 23.542, 23.666, 23.706, 23.711, 24.129, 24.285, 24.289, 24.366, 24.717, 24.990, 25.633, 26.960, 26.995, 32.065,
32.789, 34.279 )
library(rjags)
nn <- length(x)
k <- 3
mu0 <- 20
va0 <- 100
nu0 <- 6
de0 <- 40
a <- rep(1, k)
burn_in <- 10^3
N <- 10^4
full <- "
model {
for (i in 1:n) {
x[i] ~ dnorm(mu[z[i]], tau[z[i]])
z[i] ~ dcat(w[])
}
for (i in 1:k) {
mu[i] ~ dnorm(mu0, 1/va0)
tau[i] ~ dgamma(nu0/2, de0/2)
va[i] <- 1/tau[i]
}
w ~ ddirich(a)
}
"
data <- list(x = x, n = nn, k = k, mu0 = mu0, va0 = va0, nu0 = nu0, de0 = de0, a = a)
model <- jags.model(textConnection(full), data = data, n.chains = 1, n.adapt = 100)
update(model, n.iter = burn_in)
samples <- jags.samples(model, c("mu", "va", "w", "z"), n.iter = N)
mu <- matrix(samples$mu, nrow = N, byrow = TRUE)
va <- matrix(samples$va, nrow = N, byrow = TRUE)
w <- matrix(samples$w, nrow = N, byrow = TRUE)
z <- matrix(samples$z, nrow = N, byrow = TRUE)
log_L <- function(x, w, mu, va) sum(log(sapply(1:nn, function(i) sum(exp(log(w) + dnorm(x[i], mean = mu, sd = sqrt(va), log = TRUE))))))
ts <- which.max(sapply(1:N, function(t) log_L(x, w[t,], mu[t,], va[t,])))
ws <- w[ts,]
mus <- mu[ts,]
vas <- va[ts,]
log_prior <- function(w, mu, va) {
lgamma(sum(a)) - sum(lgamma(a)) + sum((a-1)*log(w))
+ sum(dnorm(mu, mean = mu0, sd = sqrt(va0), log = TRUE))
+ sum((nu0/2)*log(de0/2) - lgamma(nu0/2) - (nu0/2+1)*log(va) - de0/(2*va))
}
chib <- log_L(x, ws, mus, vas) + log_prior(ws, mus, vas)
cat("log-likelihood + log-prior =", chib, "\n")
pi.mu_va.z.x <- function(mu, va, z, x) {
n <- sapply(1:k, function(j) sum(z==j))
m <- sapply(1:k, function(j) sum(x[z==j]))
m[n > 0] <- m[n > 0] / n[n > 0]
exp(sum(dnorm(mu, mean = (n*m*va0+mu0*va)/(n*va0+va), sd = sqrt(va0*va/(n*va0+va)), log = TRUE)))
}
chib <- chib - log(mean(sapply(1:N, function(t) pi.mu_va.z.x(mus, va[t,], z[t,], x))))
cat("log-likelihood + log-prior - log-pi.mu_ =", chib, "\n")
fixed.mu <- "
model {
for (i in 1:n) {
x[i] ~ dnorm(mus[z[i]], tau[z[i]])
z[i] ~ dcat(w[])
}
for (i in 1:k) {
tau[i] ~ dgamma(nu0/2, de0/2)
va[i] <- 1/tau[i]
}
w ~ ddirich(a)
}
"
data <- list(x = x, n = nn, k = k, nu0 = nu0, de0 = de0, a = a, mus = mus)
model <- jags.model(textConnection(fixed.mu), data = data, n.chains = 1, n.adapt = 100)
update(model, n.iter = burn_in)
samples <- jags.samples(model, c("va", "w", "z"), n.iter = N)
va <- matrix(samples$va, nrow = N, byrow = TRUE)
w <- matrix(samples$w, nrow = N, byrow = TRUE)
z <- matrix(samples$z, nrow = N, byrow = TRUE)
pi.va_mu.z.x <- function(va, mu, z, x) {
n <- sapply(1:k, function(j) sum(z==j))
de <- sapply(1:k, function(j) sum((x[z==j] - mu[j])^2))
exp(sum(((nu0+n)/2)*log((de0+de)/2) - lgamma((nu0+n)/2) - ((nu0+n)/2+1)*log(va) - (de0+de)/(2*va)))
}
chib <- chib - log(mean(sapply(1:N, function(t) pi.va_mu.z.x(vas, mus, z[t,], x))))
cat("log-likelihood + log-prior - log-pi.mu_ - log-pi.va_ =", chib, "\n")
fixed.mu.and.va <- "
model {
for (i in 1:n) {
x[i] ~ dnorm(mus[z[i]], 1/vas[z[i]])
z[i] ~ dcat(w[])
}
w ~ ddirich(a)
}
"
data <- list(x = x, n = nn, a = a, mus = mus, vas = vas)
model <- jags.model(textConnection(fixed.mu.and.va), data = data, n.chains = 1, n.adapt = 100)
update(model, n.iter = burn_in)
samples <- jags.samples(model, c("w", "z"), n.iter = N)
w <- matrix(samples$w, nrow = N, byrow = TRUE)
z <- matrix(samples$z, nrow = N, byrow = TRUE)
pi.w_z.x <- function(w, z, x) {
n <- sapply(1:k, function(j) sum(z==j))
exp(lgamma(sum(a)+nn) - sum(lgamma(a+n)) + sum((a+n-1)*log(w)))
}
chib <- chib - log(mean(sapply(1:N, function(t) pi.w_z.x(ws, z[t,], x))))
cat("log-likelihood + log-prior - log-pi.mu_ - log-pi.va_ - log-pi.w_ =", chib, "\n")
My question is if in the above description there are any misunderstandings of Chib's method or any mistakes in its implementation.