This book is in Open Review. I want your feedback to make the book better for you and other readers. To add your annotation, select some text and then click the on the pop-up menu. To see the annotations of others, click the button in the upper right hand corner of the page

## 12.4 ETS + ARIMA

Coming back to the topic of ETS and ARIMA, we can now look at it from the SSOE state space point of view.

A pure additive ETS + ARIMA model can be formulated in the general form, which we have already discussed several times in this textbook: \begin{equation*} \begin{aligned} &{y}_{t} = \mathbf{w}' \mathbf{v}_{t-\boldsymbol{l}} + \epsilon_t \\ &\mathbf{v}_{t} = \mathbf{F} \mathbf{v}_{t-\boldsymbol{l}} + \mathbf{g} \epsilon_t \end{aligned}, \end{equation*} but now the matrices and vectors of the model contain ETS and ARIMA components, stacked one after another. For example, if we want to construct ETS(A,N,A)+ARIMA(2,0,0), we can formulate this model as: \begin{aligned} &{y}_{t} = l_{t-1} + s_{t-m} + v_{1,t-1} + v_{2,t-2} + \epsilon_t \\ &l_t = l_{t-1} + \alpha \epsilon_t \\ &s_t = s_{t-m} + \gamma \epsilon_t \\ &v_{1,t} = \phi_1 v_{1,t-1} + \phi_1 v_{2,t-2} + \phi_1 \epsilon_t \\ &v_{2,t} = \phi_1 v_{1,t-1} + \phi_2 v_{2,t-2} + \phi_2 \epsilon_t \end{aligned}, \tag{12.20} where $$\phi_1$$ is the parameter of the AR(1) part of the model. This model represented in the conventional additive SSOE state space model leads to the following matrices and vectors: \begin{aligned} \mathbf{w} = \begin{pmatrix} 1 \\ 1 \\ 1 \\ 1 \end{pmatrix}, & \mathbf{F} = \begin{pmatrix} 1 & 0 & 0 & 0 \\ 0 & 1 & 0 & 0 \\ 0 & 0 & \phi_1 & \phi_1 \\ 0 & 0 & \phi_2 & \phi_2 \end{pmatrix}, \\ \mathbf{g} = \begin{pmatrix} \alpha \\ \gamma \\ \phi_1 \\ \phi_2 \end{pmatrix}, & \mathbf{v}_{t} = \begin{pmatrix} l_t \\ s_t \\ v_{1,t-1} \\ v_{2,t-2} \end{pmatrix}, & \boldsymbol{l} = \begin{pmatrix} 1 \\ m \\ 1 \\ 2\end{pmatrix} \end{aligned}. \tag{12.21} So, in this formulation the states of ETS and ARIMA are independent and form a combination of models only in the measurement equation. In a way, this model becomes similar to fitting first ETS to the data and then ARIMA to the residuals, but estimating both elements at the same time.

ADAM introduces the flexibility necessary for fitting any ETS+ARIMA combination, but not all combinations make sense. For example, here how ETS(A,N,N)+ARIMA(0,1,1) would look like: \begin{aligned} &{y}_{t} = l_{t-1} + v_{1,t-1} + \epsilon_t \\ &l_t = l_{t-1} + \alpha \epsilon_t \\ &v_{1,t} = v_{1,t-1} + (1+\theta_1) \epsilon_t \end{aligned}. \tag{12.22} In the transition part of the model (12.22), the two equations duplicate each other, because they same exactly the same mechanism of update of states. In fact, as we know from a previous chapter, ETS(A,N,N) and ARIMA(0,1,1) are equivalent, when $$\alpha=1+\theta_1$$. If we estimate this model, then we are duplicating the state, in a way splitting it into two parts with some arbitrary weights. This can be seen if we insert the transition equations in the measurement one, obtaining: \begin{aligned} {y}_{t} = & l_{t-2} + \alpha \epsilon_{t-1} + v_{1,t-2} + (1+\theta_1) \epsilon_{t-1} + \epsilon_t =\\ & l_{t-2} + v_{1,t-2} + (1+\theta_1+\alpha) \epsilon_{t-1} + \epsilon_t \end{aligned}, \tag{12.23} which leads to an infinite combination of values of parameters $$\theta$$ and $$\alpha$$ that would produce exactly the same fit. So, the model (12.22) does not have unique parameters and thus is not identifiable.

In some other cases, some parts of models might be unidentifiable as well, so it makes sense to switch to a more complicated model. For example, if we have ETS(A,A,N)+ARIMA(0,2,3), then some parts of the models will be duplicated (because ETS(A,A,N) is equivalent to ARIMA(0,2,2)), so it would be more reasonable to switch to pure ARIMA(0,2,3) instead.

These examples show that, when using ETS+ARIMA, model building needs to be done with care, not to get an unreasonable model that cannot be identefied. As a general recommendation, keep the ETS and ARIMA connection in mind, when deciding, what to construct. And here is a short list of guidlines of what to do in some special cases:

1. For ETS(A,N,N)+ARIMA(0,1,q):
• use ARIMA(0,1,q) in case of with $$q >1$$,
• use ETS(A,N,N) in case of $$q\leq 1$$;
1. For ETS(A,A,N)+ARIMA(0,2,q):
• use ARIMA(0,2,q) in case of with $$q >2$$,
• use ETS(A,A,N) in case of $$q \leq 2$$;
• use ARIMA(p,1,q), when either $$p>1$$ or $$q>2$$,
• use ETS(A,Ad,N), when $$p \leq 1$$ and $$q \leq 2$$.

When it comes to seasonal models, the relation between ETS and ARIMA is mroe complex, and it is highly improbable to get to equivalent ARIMA models, so it makes sense to make sure that the three rules above hold for the non-seasonal part of the model.

### 12.4.2 Pure multiplicative models

When it comes to the multiplicative error and mixed ETS models, then the ETS+ARIMA might not have the same issues as the pure additive one. This is because the multiplicative ETS and multiplicative ARIMA are formulated differently. An example is an ETS(M,N,N)+logARIMA(0,1,1), which is formulated as: \begin{aligned} &{y}_{t} = l_{t-1} v_{1,t-1} (1 + \epsilon_t) \\ &l_t = l_{t-1}(1 + \alpha \epsilon_t) \\ &\log v_{1,t} = \log v_{1,t-1} + (1+\theta_1) \log (1 + \epsilon_t) \end{aligned}. \tag{12.24} The last equation in (12.24) can be rewritten as $$v_{1,t} = v_{1,t-1} (1 + \epsilon_t)^{(1+\theta_1)}$$, demonstrating the difference between the transition equation of ETS(M,N,N) and multiplicative ARIMA(0,1,1). Still, the two models will be similar in cases, when $$\alpha$$ is close to zero and (respectively) $$\theta$$ is close to -1. So this combination of models should be treated with care, along with other potentially similar combinations. The following combinations of the two models can be considered as potentially unidentifiable under some conditions:

1. ETS(M,N,N)+logARIMA(0,1,1);
2. ETS(M,M,N)+logARIMA(0,2,2);
3. ETS(M,Md,N)+logARIMA(1,1,1).

In additions, the recommendations discussed for the pure additive ETS+ARIMA can be applied here for the pure multiplicative ETS+ARIMA to guarantee that the resulting model is identifiable no matter what.

Finally, mixing additive ETS with multiplicative ARIMA or multiplicative ETS with additive ARIMA does not make sense and only complicates the model building process, so, we do not consider these exotic cases in the book.