Testing FX returns for normality
So far, the exercises in this chapter have examined the normality of equity index returns and individual equity returns.
To reinforce these ideas, you will apply similar ideas to exchange-rate log-returns. The dataset fx_d
contains daily log-returns of the EUR/USD, GBP/USD and JPY/USD exchange rates for the period 2001-2015, and the dataset fx_m
contains the corresponding monthly log-returns. Both are multivariate; they are loaded into your workspace.
Which of the monthly log-return series appears the most normal?
This exercise is part of the course
Quantitative Risk Management in R
Exercise instructions
- Plot the daily exchange-rate log-return series in
fx_d
with the appropriate plotting function. - Use
apply()
to conduct the Jarque-Bera test on each of the series infx_d
. - Plot the monthly log-return series in
fx_m
with the same plotting function and parametertype = "h"
. - Use
apply()
to conduct the Jarque-Bera test on each of series infx_m
. - Fill in
apply()
to fit a Student t distribution to each of the series infx_m
and obtain the parameter estimates.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Plot the daily log-return series in fx_d
___(___)
# Apply the Jarque-Bera test to each of the series in fx_d
___(___)
# Plot the monthly log-return series in fx_m
___(___)
# Apply the Jarque-Bera test to each of the series in fx_m
___(___)
# Fit a Student t distribution to each of the series in fx_m
apply(___, ___, function(v){fit.st(v)$par.ests})