Skip to contents

As morie_holt_winters_additive but with the season MULTIPLYING the level, which is the right choice when the seasonal swing grows in proportion to the level.

Usage

morie_holt_winters_mult(
  y,
  period = 4,
  alpha = 0.3,
  beta = 0.1,
  gamma = 0.1,
  horizon = NULL
)

Arguments

y

series.

period

seasonal period.

alpha, beta, gamma

smoothing parameters in \([0, 1]\).

horizon

steps ahead; defaults to one full period.

Details

The data must be strictly positive – a zero makes the seasonal ratio undefined, and the function refuses rather than dividing by a fudge factor and returning a number.

References

Winters, P. R. (1960). Forecasting sales by exponentially weighted moving averages. Management Science, 6(3), 324-342.

Examples

y <- rep(c(10, 20, 30, 20), 5) * (1 + seq_len(20) / 40)
round(morie_holt_winters_mult(y)$forecast, 1)
#> [1] 14.7 30.3 47.0 32.3