about the definition of ArimaModel

Home 2015 Forums Numerical Method Statistics about the definition of ArimaModel

This topic contains 1 reply, has 2 voices, and was last updated by avatar Ryu 7 years, 9 months ago.

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
    Posts
  • #1849
    avatar
    alexcwyu
    Participant

    Hi, I am trying to use

    com.numericalmethod.suanshu.stats.timeseries.univariate.stationaryprocess.arima.ArimaModel

    the java doc says, for the parameters AR and MA: the AR coefficients (excluding the initial 1), what does
    it mean by ” excluding the initial 1″?

    #1995
    avatar
    Ryu
    Participant

    Let’s say you have an AR(1) model like this:
    [tex]y_t = 0.5 * y_{t-1} + epsilon_t[/tex]

    There is a 1.0 coefficient for [tex]y_t[/tex], but you don’t need to specify it.

    Your code would look something like this:

Viewing 2 posts - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.