#clear
rm(list=ls())

#set directory
getwd()
setwd("C:/Users/Isariya/Desktop")

##############################################################
#ARMA-GARCH MODELING
##############################################################

library(xlsx)
library(fGarch)

# import data
temp <- tempfile()
download.file("http://freakonometrics.free.fr/oil.xls",temp)
oil=read.xlsx(temp,sheetName="DATA",dec=",")

# plot the first few lines of data
head(oil)

# set time variable and plot
Time=as.Date(oil$Date,"%Y-%m-%d")
plot(oil[,2])

# ARIMA model fitting
fit2_101=arima(x=oil[,2],order=c(1,0,1))
fit2_111=arima(x=oil[,2],order=c(1,1,1))
fit2_112=arima(x=oil[,2],order=c(1,1,2))

m_res <- apply(dat_res, 2, mean)
v_res <- apply(dat_res, 2, var)
dat_res_std =cbind((dat_res[,1]-m_res[1])/sqrt(v_res[1]),(dat_res[,2]-m_res[2])/sqrt(v_res[2]),(dat_res[,3]-m_res[3])/sqrt(v_res[3])

# ARMA-GARCH model fitting

fit1 = garchFit(formula = ~ arma(2,1)+garch(1, 1),data=oil[,2],cond.dist ="std")
fit2 = garchFit(formula = ~ arma(1,1)+garch(1, 1),data=oil[,3],cond.dist ="std")
fit3 = garchFit(formula = ~ arma(1,1)+garch(1, 1),data=oil[,4],cond.dist ="std")
dat_res = cbind(residuals(fit1),residuals(fit2),residuals(fit3))
m_res <- apply(dat_res, 2, mean)
v_res <- apply(dat_res, 2, var)
dat_res_std =cbind((dat_res[,1]-m_res[1])/sqrt(v_res[1]),(dat_res[,2]-m_res[2])/sqrt(v_res[2]),(dat_res[,3]-m_res[3])/sqrt(v_res[3]))

# DCC-GARCH (Multiple GARCH series + Dynamic Correlation)

library(MTS)

?dccFit

m2=dccFit(dat_res_std,type="TseTsui")
m2

m3=dccFit(dat_res_std,type="Engle")
m3

R2=m2$rho.t
R3=m3$rho.t

#Mulivariate t-Copula Volatility Model

m4=mtCopula(dat_res_std, 0.5, 0.2)
m4