Asumsi Arima.docx

  • May 2020
  • PDF

This document was uploaded by user and they confirmed that they have the permission to share it. If you are author or own the copyright of this book, please report to us by using this DMCA report form. Report DMCA


Overview

Download & View Asumsi Arima.docx as PDF for free.

More details

  • Words: 171
  • Pages: 2
Model ARIMA yang akan dipilih harus memenuhi asumsi white noise. Pengujian asumsi white noise dapat dilakukan dengan menggunakan pengujian Ljung-Box Chi-square Statistics. Dengan hipotesis sebagai berikut. Hipotesis: H0 : model telah memenuhi asumsi white noise H1 : model tidak memenuhi asumsi white noise H0 dapat ditolak jika nilai P-value dari Ljung-Box chi-square Statistics tersebut kurang dari nilai α yang ditentukan sebelumnya. Contoh output pengujian Ljung-Box chi-square Statistics pada minitab:

> terasvirta.test(DA,lag=1,type=c("F"),scale = TRUE) Teraesvirta Neural Network Test data: DA F = 9.2995, df1 = 2, df2 = 727, p-value = 0.0001028 > terasvirta.test(DA,lag=2,type=c("F"),scale = TRUE) Teraesvirta Neural Network Test data: DA F = 4.5435, df1 = 7, df2 = 721, p-value = 5.637e-05

> summary(DA_tr.arima) Series: DA_tr ARIMA(1,1,2)

Coefficients: ar1

ma1

ma2

0.4770 -0.7272 -0.1217 s.e. 0.0862 0.0890 0.0589 sigma^2 estimated as 9.306: log likelihood=-1691.63 AIC=3391.26 AICc=3391.32 BIC=3409.27 Training set error measures: ME

RMSE

MAE

MPE

MAPE

MASE

ACF1

Training set 0.08282055 3.041383 2.003969 -0.8392854 7.532956 1.084666 0.0009996079 > shapiro.test(DA_tr.arima$residuals) Shapiro-Wilk normality test data: DA_tr.arima$residuals W = 0.9035, p-value < 2.2e-16

Related Documents

Asumsi
June 2020 19
Asumsi
May 2020 17
Asumsi Makro.pdf.docx
November 2019 18
Asumsi Baru.docx
December 2019 19
Asumsi Arima.docx
May 2020 7
03 Asumsi Dan Hipotesis
October 2019 16