com.github.signaflo.timeseries.model

Interface Model

All Known Subinterfaces:

Arima, TimeSeriesLinearRegression

All Known Implementing Classes:

MeanModel, RandomWalk

public interface Model

A representation of a time series model. A time series model is an attempt to capture the essential characteristics of the process or processes underlying the time series.

Method Summary

Modifier and Type	Method and Description
TimeSeries	fittedSeries() Get the model fitted values, which are in-sample one-step ahead forecasts.
default Forecast	forecast(int steps) Create a new forecast for the given number of steps ahead with a default α significance level of 0.05.
Forecast	forecast(int steps, double alpha) Produce a forecast from this model up to the given number of steps ahead.
TimeSeries	observations() Get the series of observations.
default TimeSeries	predictionErrors() Get the model prediction errors, the difference between the observed values and the model fitted values.

Method Detail

forecast

Forecast forecast(int steps,
                  double alpha)

Produce a forecast from this model up to the given number of steps ahead.

Parameters:

steps - the number of time periods ahead to forecast.

alpha - the significance level to use for the prediction interval.

Returns:

a forecast from this model up to the given number of steps ahead.

forecast

default Forecast forecast(int steps)

Create a new forecast for the given number of steps ahead with a default α significance level of 0.05.

Parameters:

steps - the number of time periods ahead to forecast.

Returns:

a new forecast for the given number of steps ahead with a default α significance level of 0.05.

observations

TimeSeries observations()

Get the series of observations.

Returns:

the series of observations.

fittedSeries

TimeSeries fittedSeries()

Get the model fitted values, which are in-sample one-step ahead forecasts.

Returns:

the model fitted values.

predictionErrors

default TimeSeries predictionErrors()

Get the model prediction errors, the difference between the observed values and the model fitted values.

Returns:

the model prediction errors.