price = read.csv('index.csv')
y=diff(log(price$Index)) # calculate returns
plot(y) # plot returns
price = csvread('index.csv', 1, 0);
y=diff(log(price)); % calculate returns
plot(y) % plot returns
library(moments)
library(tseries)
mean(y)
sd(y)
min(y)
max(y)
skewness(y)
kurtosis(y)
acf(y,1)
acf(y^2,1)
jarque.bera.test(y)
Box.test(y, lag = 20, type = c("Ljung-Box"))
Box.test(y^2, lag = 20, type = c("Ljung-Box"))
%% the function sacf uses Kevin Sheppard's MFE toolbox
%% download at https://www.kevinsheppard.com/MFE_Toolbox
mean(y)
std(y)
min(y)
max(y)
skewness(y)
kurtosis(y)
sacf(y,1,[],0)
sacf(y.^2,1,[],0)
[h,pValue,stat]=jbtest(y);
[h,pValue,stat]=lbqtest(y,'lags',20);
[h,pValue,stat]=lbqtest(y.^2,'lags',20);
%% NOTE: in MATLAB 2018a, some functions require name-value pairs
%% e.g. MATLAB 2016a: [h,pValue,stat] = lbqtest(y,20)
library(MASS)
library(stats)
par(mfrow=c(1,2), pty="s")
q = acf(y,20)
q1 = acf(y^2,20)
%% subplots here are just for ease of visualization
subplot(1,2,1)
autocorr(y, 20)
subplot(1,2,2)
autocorr(y.^2, 20)
library(car)
par(mfrow=c(1,2), pty="s")
qqPlot(y)
qqPlot(y,distribution="t",df=5)
%% subplots here are just for ease of visualization
subplot(1,2,1)
qqplot(y)
subplot(1,2,2)
qqplot(y, fitdist(y,'tLocationScale'))
p = read.csv('stocks.csv')
y=apply(log(p),2,diff)
print(cor(y)) # correlation matrix
price = csvread('stocks.csv', 1, 0);
y=diff(log(price));
corr(y) % correlation matrix