import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
plt.rcParams['font.family'] = 'Songti SC' # 显示中文标签
#from matplotlib.font_manager import FontProperties
#font =FontProperties(fname = '/Users/cloudwise/Documents/字体/simsun.ttf')
%matplotlib inline
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
from statsmodels.tsa.stattools import pacf, pacf_ols, pacf_yw
import statsmodels as sm
from scipy.linalg import toeplitz
from statsmodels.regression.linear_model import OLS, yule_walker
公式
statsmodels.tsa.stattools.pacf的计算方式
参考：https://www.statsmodels.org/stable/_modules/statsmodels/regression/linear_model.html#yule_walker
Y u l e − W a l k e r 方 程 ， 系 数 求 法 i n p u t 1 : t s i n p u t 2 : o r d e r n = l e n ( t s ) k ∈ [ 0 , 1 , 2 , 3 , . . . , o r d e r ] r k = t s 1 ∗ t s k + 1 + t s 2 ∗ t s k + 2 + t s 3 ∗ t s k + 3 + . . . + t s n − k ∗ t s n n − k Yule-Walker方程，系数求法 \\ input 1 : ts \\ input 2 : order \\ n = len(ts) \\ k \in [0,1,2,3,..., order] \\ r_{k} = \frac{ts_{1}*ts_{k+1} + ts_{2}*ts_{k+2} + ts_{3}*ts_{k+3} + ... +ts_{n-k}*ts_{n}}{n-k} Yule−Walker方程，系数求法input1:tsinput2:ordern=len(ts)k∈[0,1,2,3,...,order]rk=n−kts1∗tsk+1+ts2∗tsk+2+ts3∗tsk+3+...+tsn−k∗tsn
R = [ r 0 r 1 r 2 . . . r o r d e r − 1 r 1 r 0 r 1 . . . r o r d e r − 2 r 2 r 1 r 0 . . . r o r d e r − 3 . . . . . . . . . . . . r o r d e r − 1 r o r d e r − 2 r o r d e r − 3 . . . r 0 ] R= \left[ %左括号 \begin{array}{ccccc} %该矩阵一共3列，每一列都居中放置 r_{0} & r_{1} & r_{2} & ... & r_{order-1}\\ r_{1} & r_{0} & r_{1} & ... & r_{order-2}\\ r_{2} & r_{1} & r_{0} & ... & r_{order-3}\\ ... & & ... & ... & ...\\ r_{order-1} & r_{order-2} & r_{order-3} & ... & r_{0}\\ \end{array} \right] %右括号 R=⎣⎢⎢⎢⎢⎡r0r1r2...rorder−1r1r0r1rorder−2r2r
最低0.47元/天 解锁文章
5万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
