statsmodels.tsa.holtwinters.Holt

class statsmodels.tsa.holtwinters.Holt(endog, exponential=False, damped_trend=False, initialization_method=None, initial_level=None, initial_trend=None)[source]

Holt’s Exponential Smoothing

Parameters
endogarray_like

The time series to model.

exponentialbool, optional

Type of trend component.

damped_trendbool, optional

Should the trend component be damped.

initialization_methodstr, optional

Method for initialize the recursions. One of:

  • None

  • ‘estimated’

  • ‘heuristic’

  • ‘legacy-heuristic’

  • ‘known’

None defaults to the pre-0.12 behavior where initial values are passed as part of fit. If any of the other values are passed, then the initial values must also be set when constructing the model. If ‘known’ initialization is used, then initial_level must be passed, as well as initial_trend and initial_seasonal if applicable. Default is ‘estimated’. “legacy-heuristic” uses the same values that were used in statsmodels 0.11 and earlier.

initial_levelfloat, optional

The initial level component. Required if estimation method is “known”. If set using either “estimated” or “heuristic” this value is used. This allows one or more of the initial values to be set while deferring to the heuristic for others or estimating the unset parameters.

initial_trendfloat, optional

The initial trend component. Required if estimation method is “known”. If set using either “estimated” or “heuristic” this value is used. This allows one or more of the initial values to be set while deferring to the heuristic for others or estimating the unset parameters.

See also

ExponentialSmoothing

Exponential smoothing with trend and seasonal components.

SimpleExpSmoothing

Basic exponential smoothing with only a level component.

Notes

This is a full implementation of the Holt’s exponential smoothing as per [1]. Holt is a restricted version of ExponentialSmoothing.

References

1

Hyndman, Rob J., and George Athanasopoulos. Forecasting: principles and practice. OTexts, 2014.

Attributes
endog_names

Names of endogenous variables.

exog_names

The names of the exogenous variables.

Methods

fit([smoothing_level, smoothing_trend, …])

Fit the model

fix_params(values)

Temporarily fix parameters for estimation.

from_formula(formula, data[, subset, drop_cols])

Create a Model from a formula and dataframe.

hessian(params)

The Hessian matrix of the model.

information(params)

Fisher information matrix of model.

initial_values([initial_level, …])

Compute initial values used in the exponential smoothing recursions.

initialize()

Initialize (possibly re-initialize) a Model instance.

loglike(params)

Log-likelihood of model.

predict(params[, start, end])

In-sample and out-of-sample prediction.

score(params)

Score vector of model.

Methods

fit([smoothing_level, smoothing_trend, …])

Fit the model

fix_params(values)

Temporarily fix parameters for estimation.

from_formula(formula, data[, subset, drop_cols])

Create a Model from a formula and dataframe.

hessian(params)

The Hessian matrix of the model.

information(params)

Fisher information matrix of model.

initial_values([initial_level, …])

Compute initial values used in the exponential smoothing recursions.

initialize()

Initialize (possibly re-initialize) a Model instance.

loglike(params)

Log-likelihood of model.

predict(params[, start, end])

In-sample and out-of-sample prediction.

score(params)

Score vector of model.

Properties

endog_names

Names of endogenous variables.

exog_names

The names of the exogenous variables.