Generating ARMA data
In this exercise you will generate 100 days worth of AR/MA/ARMA data. Remember that in the real world applications, this data could be changes in Google stock prices, the energy requirements of New York City, or the number of cases of flu.
You can use the arma_generate_sample()
function available in your workspace to generate time series using different AR and MA coefficients.
Remember for any model ARMA(p,q):
- The list
ar_coefs
has the form[1, -a_1, -a_2, ..., -a_p]
. - The list
ma_coefs
has the form[1, m_1, m_2, ..., m_q]
,
where a_i
are the lag-i AR coefficients and m_j
are the lag-j MA coefficients.
This exercise is part of the course
ARIMA Models in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Import data generation function and set random seed
from statsmodels.tsa.arima_process import arma_generate_sample
np.random.seed(1)
# Set coefficients
ar_coefs = [____]
ma_coefs = [____]
# Generate data
y = arma_generate_sample(____, ____, nsample=____, scale=0.5)
plt.plot(y)
plt.ylabel(r'$y_t$')
plt.xlabel(r'$t$')
plt.show()