Chapter 7 Further ADAM ETS topics
- ANN; AAN; AAdN; ANA; AAA; AAdA;
- MNN; MAN; MAdN; MNA; MAA; MAdA;
- MNM; MAM; MAdM;
- MMN; MMdN; MMM; MMdM;
- ANM; AAM; AAdM; MMA; MMdA; AMN; AMdN; AMA; AMdA; AMM; AMdM
ets() model from
forecast package supports only the Classes 1 - 4. The Class 5 models are not included in the function mainly because they have infinite variances, specifically on long horizons and when the data has low values. Indeed, when the level in one of these models becomes close to zero, there is an increased chance of breaking the model due to the appearance of negative values (think of ETS(A,A,M) model, which might have a negative trend, leading to negative values, which are then multiplied by the positive seasonal indices). That is why in practice these models should only be used, when the level of the series is high. Furthermore, some of the models from the Class 5 are very difficult to estimate and are very sensitive to the smoothing parameters values. All of this gives a rationale for restricting the pool of models to the 19 from classes 1 - 4.
Hyndman et al. (2008) demonstrate that models from the class 2 have closed forms of conditional expectation and variance, with the former corresponding to the point forecasts. However, the conditional distribution from these models is not Gaussian, so there are no formulae for the prediction intervals from these models. Yes, in some cases Normal distribution might be a fine approximation for the real one, but in general simulations should be preferred.
Class 3 models suffer from similar issues, but the situation worsens: there are no analytical solutions for the conditional mean and variance, and there are only approximations to these statistics.
Class 4 models have been discussed in the previous section.
To be fair, any mixed model can potentially break, when the level of series is close to zero. For example, ETS(M,A,N) can have the negative trend, which might lead to the negative level and as a result to the multiplication of pure positive error term by the negative components. Estimating such a model on real data becomes a non-trivial task. In addition, as discussed above, simulations are typically needed in order to get adequate estimates of prediction interval for models of classes 2 - 5 and conditional mean and variance for models fo classes 4 - 5. All of this in my opinion means that the more useful classification of ETS models is the following:
- Pure additive models: ANN; AAN; AAdN; ANA; AAA; AAdA;
- Pure multiplicative models: MNN; MMN; MMdN; MNM; MMM; MMdM;
- Mixed models with non-multiplicative trend: MAN; MAdN; MNA; MAA; MAdA; MAM; MAdM; ANM; AAM; AAdM;
- Mixed models with multiplicative trend: MMA; MMdA; AMN; AMdN; AMA; AMdA; AMM; AMdM;
The main idea behind the split to (3) and (4) is because the presence of multiplicative trend makes it almost impossible to derive the formulae for the conditional moments of distribution. So this class of models can be considered as the most challenging.
adam() function supports all 30 ETS models, but you should keep in mind the limitations of some of them discussed in this section.