python中使用ARMA / ARIMA的線性回歸模型

Question

有人可以給我一個如何結合使用ARMA和線性回歸的基本示例嗎？ 我有一個自變量X，我想回歸到Y，但在X上使用AR。任何簡單的示例都將非常有用。

類似的問題

Answer 1

這是一個快速入門

from statsmodels.tsa.stattools import ARMA
import pandas as pd
import numpy as np

ts = pd.Series(np.random.randn(500), index=pd.date_range('2010-01-01', periods=500))

p, q = 1, 1

arma = ARMA(endog=ts, order=(p, q)).fit()

print arma.summary()

                              ARMA Model Results                              
==============================================================================
Dep. Variable:                      y   No. Observations:                  500
Model:                     ARMA(1, 1)   Log Likelihood                -678.805
Method:                       css-mle   S.D. of innovations              0.941
Date:                Tue, 17 May 2016   AIC                           1365.610
Time:                        00:01:52   BIC                           1382.469
Sample:                    01-01-2010   HQIC                          1372.225
                         - 05-15-2011                                         
==============================================================================
                 coef    std err          z      P>|z|      [95.0% Conf. Int.]
------------------------------------------------------------------------------
const          0.0624      0.048      1.311      0.191        -0.031     0.156
ar.L1.y        0.3090      0.311      0.992      0.322        -0.302     0.919
ma.L1.y       -0.2177      0.318     -0.684      0.494        -0.841     0.406
                                    Roots                                    
=============================================================================
                 Real           Imaginary           Modulus         Frequency
-----------------------------------------------------------------------------
AR.1            3.2367           +0.0000j            3.2367            0.0000
MA.1            4.5939           +0.0000j            4.5939            0.0000
-----------------------------------------------------------------------------