Cross Validated Asked by Indula on January 3, 2022
If $Delta Y_t$ can be described by a (stationary) $ARMA(p,q)$ process, then $Y_t$ can be described by an $ARIMA(p,1,q)$ process. Theoretically (concerns of usefulness aside), does this mean we can consider $Y_t$ as a (non-stationary) $ARMA(p+1,q)$ with a unit root in its autoregressive component?
I’m trying to get a sense of how autoregressive, moving average, and integrated orders of a unit root process are linked to each other in its $ARMA$ and $ARIMA$ representations. To my understanding, it’s purely an issue of notation. If it’s not, please let me know.
1 Asked on January 14, 2021 by doxav
multiarmed bandit optimization queueing real time time series
1 Asked on January 14, 2021
1 Asked on January 14, 2021 by user261225
1 Asked on January 13, 2021 by katy
0 Asked on January 13, 2021
2 Asked on January 13, 2021 by crazydriver
1 Asked on January 13, 2021 by vin
bayesian bayesian network conditional probability inference posterior
0 Asked on January 12, 2021 by g-s-luimstra
convolution filter gradient descent neural networks optimization
1 Asked on January 12, 2021 by somethingsomething
1 Asked on January 12, 2021 by user3136
1 Asked on January 11, 2021 by ad-van-der-ven
bernoulli distribution distributions exponential distribution probability
0 Asked on January 11, 2021 by jonas-palaionis
0 Asked on January 11, 2021 by sventon
2 Asked on January 11, 2021 by benjamin-phua
1 Asked on January 10, 2021 by confusedmathstudent
conditional expectation conditional probability expected value frequency severity
0 Asked on January 10, 2021
2 Asked on January 10, 2021 by stats_nerd
feature engineering feature selection machine learning regression
0 Asked on January 10, 2021 by anto_zoolander
2 Asked on January 10, 2021 by snoopy
Get help from others!
Recent Answers
Recent Questions
© 2023 AnswerBun.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP