CODEWITHSUNDEEP
rfor-loop
Amanda
Amanda

Reputation: 63

Simulation in R, for loops

I got a piece of R code shown as below to find out the values of Y in the last row , each time I run it, R will give 100 values of Y because I set N= 100 as beginning of the simulation...

I am going to simulate it for 500 times to find 500 series of Y. Each simulation contains 100 Y values. As a result, I want to get something like a matrix with 500 rows of simulation, each row contains 100 Y values. I suppose a for loop will help but I did not figure out how to do it? Could anyone help please? Many thanks!!!!!!

N = 100
# set up initial values
alpha1 = 8.439e-02
beta1 = 8.352e-01
mu = 7.483e-03 
omega = 1.343e-04
X_0 = -3.092031e-02
sigma_0 = 0.03573968
eps = rt (N,7.433e+00)

# loops
Xn= numeric (N)
sigma= numeric (N)
sigma[1] = sigma_0
Xn[1] = X_0
for (t in 2:N){
  sigma[t] = sqrt (omega + alpha1 * (Xn[t-1])^2 + beta1* (sigma[t-1])^2)
  Xn[t] = sigma[t] * eps[t]
}
Y = mu + Xn
head(Y)

Upvotes: 1

Views: 747

Answers (1)

jogo
jogo

Reputation: 12559

Put all that in a function getY <- function(N) { ... } and use replicate(500, getY(100)). So you can do:

getY <- function(N) {
  # set up initial values
  alpha1 <- 8.439e-02
  beta1  <- 8.352e-01
  mu     <- 7.483e-03 
  omega  <- 1.343e-04
  X_0    <- -3.092031e-02
  sigma_0 <- 0.03573968
  eps     <- rt(N, 7.433e+00)

  # loops
  Xn    <- numeric (N)
  sigma <- numeric (N)
  sigma[1] <- sigma_0
  Xn[1]    <- X_0
  for (t in 2:N) {
    sigma[t] <- sqrt (omega + alpha1 * (Xn[t-1])^2 + beta1* sigma[t-1])^2)
    Xn[t]    <- sigma[t] * eps[t]
  }
  Y <- mu + Xn
}

X <- replicate(500, getY(100))

If you want, you can transpose the result with t(), i.e. 

X <- t(replicate(500, getY(100)))

Upvotes: 1

Related Questions