状態空間時系列分析入門 第7章 (1/3)

{rstan} で 「状態空間時系列分析入門」 を再現したい。やっていること / 数式はテキストを参照。

リポジトリ: https://github.com/sinhrks/stan-statespace

必要パッケージのインストール/読み込み

library(devtools)
# devtools::install_github('hoxo-m/pforeach')
# devtools::install_github('sinhrks/ggfortify')

library(rstan)
library(pforeach)
library(ggplot2)
ggplot2::theme_set(theme_bw(base_family="HiraKakuProN-W3"))
library(ggfortify)

関数定義

# モデルが収束しているか確認
is.converged <- function(stanfit) {
  summarized <- summary(stanfit)  
  all(summarized$summary[, 'Rhat'] < 1.1)
}

# 値がだいたい近いか確認
is.almost.fitted <- function(result, expected, tolerance = 0.001) {
  if (abs(result - expected) > tolerance) {
    print(paste('Result is ', result))
    return(FALSE)
  } else {
    return(TRUE)
  }
}

データの読み込み

ukdrivers <- read.table('../data/UKdriversKSI.txt', skip = 1)
ukdrivers <- ts(ukdrivers[[1]], start = c(1969, 1), frequency = 12)
ukdrivers <- log(ukdrivers)

ukpetrol <- read.table('../data/logUKpetrolprice.txt', skip = 1)
ukpetrol <- ts(ukpetrol, start = start(ukdrivers), frequency = frequency(ukdrivers))

ukseats <- c(rep(0, (1982 - 1968) * 12 + 1), rep(1, (1984 - 1982) * 12 - 1))
ukseats <- ts(ukseats, start = start(ukdrivers), frequency = frequency(ukdrivers))

モデル定義

model_file <- '../models/fig07_01.stan'
cat(paste(readLines(model_file)), sep = '\n')

data {
  int<lower=1> n;
  vector[n] y;
  vector[n] x;
  vector[n] w;
}
parameters {
  # 確定的レベル
  real mu;
  # 確定的季節項
  vector[11] seas;
  # 確定的回帰係数
  real beta;
  # 確定的係数
  real lambda;
  # 観測撹乱項
  real<lower=0> sigma_irreg;
}
transformed parameters {
  vector[n] seasonal;
  vector[n] yhat;
  for(t in 1:11) {
    seasonal[t] <- seas[t];
  }
  for(t in 12:n) {
    seasonal[t] <- - seasonal[t-11] - seasonal[t-10] - seasonal[t-9] - seasonal[t-8] - seasonal[t-7] - seasonal[t-6] - seasonal[t-5] - seasonal[t-4] - seasonal[t-3] - seasonal[t-2] - seasonal[t-1];
  }
  for(t in 1:n) {
    yhat[t] <- mu + beta * x[t] + lambda * w[t];
  }
}
model {
  # 式 7.1
  for(t in 1:n)
    y[t] ~ normal(yhat[t] + seasonal[t], sigma_irreg);
}

y <- ukdrivers
x <- ukpetrol
w <- ukseats

standata <- within(list(), {
  y <- as.vector(y)
  x <- as.vector(x)
  w <- as.vector(w)
  n <- length(y)
})

stan_fit <- stan(file = model_file, chains = 0)

## 
## TRANSLATING MODEL 'fig07_01' FROM Stan CODE TO C++ CODE NOW.
## COMPILING THE C++ CODE FOR MODEL 'fig07_01' NOW.

fit <- pforeach(i = 1:4, .final = sflist2stanfit)({
  stan(fit = stan_fit, data = standata, 
       iter = 2000, chains = 1, seed = i)
})
stopifnot(is.converged(fit))

yhat <- get_posterior_mean(fit, par = 'yhat')[, 'mean-all chains']
mu <- get_posterior_mean(fit, par = 'mu')[, 'mean-all chains']
beta <- get_posterior_mean(fit, par = 'beta')[, 'mean-all chains']
lambda <- get_posterior_mean(fit, par = 'lambda')[, 'mean-all chains']
sigma_irreg <- get_posterior_mean(fit, par = 'sigma_irreg')[, 'mean-all chains']

# stopifnot(is.almost.fitted(mu, 6.4016))
is.almost.fitted(mu, 6.4016)

## [1] "Result is  6.40441374702868"

## [1] FALSE

# stopifnot(is.almost.fitted(beta, -0.45213))
is.almost.fitted(beta, -0.45213)

## [1] "Result is  -0.450946707623521"

## [1] FALSE

stopifnot(is.almost.fitted(lambda, -0.19714))
stopifnot(is.almost.fitted(sigma_irreg^2, 0.00740223))

title <- paste('Figure 7.1. Deterministic level plus variables',
               'log petrol price and seat belt law.', sep = '\n')
title <- paste('図 7.1 確定的レベルプラス対数石油価格と',
               'シートベルト法', sep = '\n')

p <- autoplot(y)
yhat <- ts(yhat, start = start(y), frequency = frequency(y))
p <- autoplot(yhat, p = p, ts.colour = 'blue')
p + ggtitle(title)