Seasonal trend

Seasonal trend first subtracts the data seasonality estimated with STL (Seasonal and Trend decomposition using Loess). It then forecasts the deseasonalized data using an ETS model adjusted for trends.

Use default trend smoother length

Default length is the smallest odd integer greater than (1.5 * season length) / (1 - 1.5 / seasonal smoother length).

Use default low pass filter length

Default length is the smallest odd integer strictly greater than the season length.

Degree of seasonal LOESS

Try Constant Try Constant & trend

Degree of the LOESS smoothing polynomial for the seasonal component.

Degree of trend LOESS

Try Constant Try Constant & trend

Degree of the LOESS smoothing polynomial for the trend component.

Degree of low pass LOESS

Try Constant Try Constant & trend

Degree of the LOESS smoothing polynomial for the low pass component.