January 2020
Beginner to intermediate
432 pages
11h 24m
English
Autocorrelation (also known as serial correlation) measures how similar is a given time series to the lagged version of itself, over successive time intervals.
To investigate whether there is significant autocorrelation in returns, we created the autocorrelation plot using plot_acf from the statsmodels library. We inspected 50 lags and used the default alpha=0.05, which means that we also plotted the 95% confidence interval. Values outside of this interval can be considered statistically significant.
Read now
Unlock full access