Volatility Analysis of Exchange Rate with Correlated Errors: A Sliding Data Matrix Approach

Pseudocode 1

R codes for simulated data.

R Codes

RW <- function(N, x0, mu, variance) {

   z<-cumsum(rnorm(n=N, mean=0,

sd=sqrt(variance)))

   t<-1:N

   x<-x0+tmu+z

   return(x)

  }

P<-RW(4801,2,0,0.004)

  Q<-c(rep(NA,4800))

  for (i in 1:4800){

   Q[i]<- P[i+1]-P[i]

  }

 M<-matrix(c(rep(NA,4800)), nrow =240, ncol =20)

 for (i in 1:240) {

   A<-1+(20(i-1))

   B<-20i

   M[i,]<- Q[A:B]

 }

##### For sliding data matrix ####

 D<-c(rep(NA,227))

 W<-c(rep(NA,227))

 for (i in 1:227) {

   ma<-M[(i):(12+i),]

   as.matrix(ma)

   cc<-matrix(c(rep(NA,400)),nrow =20, ncol =20)

   cc<-cov(ma)

   D[i]<-sqrt(sum(diag(cc)))

   vvvvvW[i]<-sqrt(20)sd(ma[12+i,])

 }

 t.test(D,W,paired=TRUE,conf.level=0.95)

##### For cumulative data matrix, ma becomes #####

ma<-M[(1):(12+i),]