Obtain 5 years of data for any two stocks. Perform Monte Carlo simulations for a portfolio of two stocks with weights 0.3 and 0.7. Use Normal distribution with constant variance for the simulations. Find 99% VaR for $1,000,000 portfolio of two stocks.

Here is the R code that we need to use but J am unable to run it. So What is the result when we run the following R code in R studio ?

library(quantmod) # <=== load the package "quantmod"

library(timeSeries)

getSymbols("TSLA",from="2010-01-01",to="2018-08-13") # <== specify the data span

getSymbols("TGT",from="2010-01-01",to="2018-08-13") # <== specify the data span

TSLA=last(TSLA, "4 years") # select the last 4 years of data

TGT=last(TGT, "4 years") # select the last 4 years of data

ret_TSLA=diff(log(TSLA$TSLA.Adjusted))*100 # returns are in percentage

ret_TGT=diff(log(TGT$TGT.Adjusted))*100 # returns are in percentage

ret_TSLA=na.omit(ret_TSLA) # remove missing values NA

ret_TGT=na.omit(ret_TGT) # remove missing values NA

nsim=10000

w=c(0.6,0.4) #portfolio weights

# mean returns could be included or ignored

#mu=cbind( mean(ret_TSLA),mean(ret_TGT))

mu=c(0,0)

# daily covariance matrix

SIG=cov(cbind(ret_TSLA,ret_TGT)) # covariance between TSLA and TGT

SIG

# Correlation between TSLA and TGT

cor(cbind(ret_TSLA,ret_TGT))

plot(as.data.frame(cbind(ret_TSLA,ret_TGT))) #scatterplot

plot(cbind(ret_TSLA,ret_TGT)) #plot over time

library(MASS)

set.seed(12345) #set seed so that monte carlo simulations are the same each time you run the code

sim_returns=mvrnorm(nsim,mu,SIG) # generate nsim=10000 scenarios for two stocks

sim_portfolio= sim_returns%*%w #compute portfolio returns for nsim scenarios

# Find VaR for $1,000,000 portfolio

value=1000000

VaR=-quantile(sim_portfolio,p=0.01)/100*value # divide by 100 since returns are in percentage

VaR