Partial autocorrelation in time series data
Like autocorrelation, the partial autocorrelation function (PACF) measures the correlation coefficient between a time-series and lagged versions of itself. However, it extends upon this idea by also removing the effect of previous time points. For example, a partial autocorrelation function of order 3
returns the correlation between our time series (t_1
, t_2
, t_3
, …) and its own values lagged by 3 time points (t_4
, t_5
, t_6
, …), but only after removing all effects attributable to lags 1 and 2.
The plot_pacf()
function in the statsmodels
library can be used to measure and plot the partial autocorrelation of a time series.
This is a part of the course
“Visualizing Time Series Data in Python”
Exercise instructions
- Import
tsaplots
fromstatsmodels.graphics
. - Use the
plot_pacf()
function fromtsaplots
to plot the partial autocorrelation of the'co2'
column inco2_levels
. - Specify a maximum lag of 24.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Import required libraries
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
____
# Display the partial autocorrelation plot of your time series
fig = ____(co2_levels[____], lags=____)
# Show plot
plt.show()