AR(m) model

1 2 |

`x` |
time series |

`m, d, steps` |
embedding dimension, time delay, forecasting steps |

`series` |
time series name (optional) |

`include` |
Type of deterministic regressors to include |

`type` |
Whether the variable is taken is level, difference or a mix (diff y= y-1, diff lags) as in the ADF test |

AR(m) model:

*
x[t+steps] = phi[0] + phi[1] x[t] + phi[2] x[t-d] + … + phi[m]
x[t - (m-1)d] + eps[t+steps]*

A `nlar`

object, `linear`

subclass.

Antonio, Fabio Di Narzo

`nlar`

for fitting this and other models to time series data

1 2 3 4 |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.