Time Series Prediction – A short introduction for pragmatists

Re:Time Series Prediction – A short introduction for pragmat... by ulucs on Sunday November 10, 2019 @05:44AM (#21497437)

I mostly feel these methods are quite overkill for most applications. As a purist, I'd recommend starting out with a simple linear regression and then moving on to adding methods to cover the letters of SARIMA by showing the need for each. It may not be as flashy, but linear regression is a stupidly powerful and very cheap tool for all kinds of situations.

[ Parent | on HN ]

Re:Time Series Prediction – A short introduction for pragmat... by mr_toad on Sunday November 10, 2019 @10:45PM (#21501962)

As a complete non-purist I’d suggest chucking the data into Auto.arima and seeing where that gets you. Not only will it save a lot of time, in my experience it tends to produce better models.

https://cran.r-project.org/web/packages/forecast/index.html

[ Parent | on HN ]

Re:Time Series Prediction – A short introduction for pragmat... by in9 on Monday November 11, 2019 @07:24AM (#21504244)

I saw an article which I can't remember that warned in which contexts auto.arima might not work. But in the majority of times auto.arima outperforms the old Box-Jenkins methodology.

[ Parent | on HN ]