Zum Hauptinhalt springen

Cookies bei Macro by Mark.Wir verwenden notwendige Cookies für Anmeldung, Sprache und Sicherheit. Mit Ihrer Einwilligung verwenden wir außerdem optionale Cookies für Präferenzen, für Analysen und für Werbemessung mit dem Meta-(Facebook-)Pixel. Lesen Sie unsere Cookie-Richtlinie.

Macro by MarkMacro by Mark
  • Start
Wird geladen …
Wird geladen …
← Modelle
MacroKonzepteWirtschaftspolitikModelle

ETS (exponential smoothing) Model

Error / trend / seasonality state-space framework that decomposes a series into smoothed components and forecasts forward.

ÜberblickDiagrammMathematikQuellen

Understand the mathematics

Follow the same equations and assumptions one section at a time or in a continuous reading.

Hover or focus a symbol defined in this model to find its exact matches. Select it to keep the highlight; Escape clears the selection.

State-Space Formulation and the Ets Taxonomy

The ETS framework recasts every exponential smoothing method as a state-space model with a single source of error. The model is defined by three choices: the error type (A for additive, M for multiplicative), the trend type (N for none, A for additive, Ad for additive damped, M for multiplicative, Md for multiplicative damped), and the seasonal type (N for none, A for additive, M for multiplicative). These three choices create a grid of 5×3×2=305 \times 3 \times 2 = 305×3×2=30 candidate models, of which about 15 are commonly used.

The single-source-of-error assumption means that one innovation εt\varepsilon_tεt​ drives both the observation and all state updates simultaneously. This is not the most general state-space formulation - a multiple-source-of-error model would have separate disturbances for the observation and each state. But the single-source assumption gives each model a closed-form innovation representation, which means the likelihood can be evaluated without the Kalman filter for additive error models. This is what makes ETS computationally fast.

yt=lt−1+bt−1+st−s+εty_t = l_{t-1} + b_{t-1} + s_{t-s} + \varepsilon_tyt​=lt−1​+bt−1​+st−s​+εt​
εt\varepsilon_tεt​

Measurement equation for ETS(A,A,A)\text{ETS}(A,A,A)ETS(A,A,A): the observation is the sum of the previous level, trend, and seasonal factor, plus an additive innovation.

lt=lt−1+bt−1+α εtl_t = l_{t-1} + b_{t-1} + \alpha\,\varepsilon_tlt​=lt−1​+bt−1​+αεt​
ltl_tlt​α\alphaαεt\varepsilon_tεt​

Level transition: the level advances by the trend and absorbs a fraction α\alphaα of the innovation.

bt=bt−1+β∗ εtb_t = b_{t-1} + \beta^*\,\varepsilon_tbt​=bt−1​+β∗εt​
btb_tbt​β∗\beta^*β∗εt\varepsilon_tεt​

Trend transition: the trend persists and absorbs a fraction β∗\beta^*β∗ of the innovation.

st=st−s+γ εts_t = s_{t-s} + \gamma\,\varepsilon_tst​=st−s​+γεt​
sts_tst​γ\gammaγεt\varepsilon_tεt​

Seasonal transition: the seasonal factor for this period within the cycle is updated by a fraction γ\gammaγ of the innovation.

bt=ϕ bt−1+β∗ εt(damped trend variant)b_t = \phi\, b_{t-1} + \beta^*\,\varepsilon_t \quad (\text{damped trend variant})bt​=ϕbt−1​+β∗εt​(damped trend variant)
btb_tbt​ϕ\phiϕβ∗\beta^*β∗εt\varepsilon_tεt​

With damping: the trend shrinks by factor ϕ\phiϕ each period. For ϕ<1\phi < 1ϕ<1, the trend decays geometrically toward zero over the forecast horizon.

yt=(lt−1+bt−1) st−s (1+εt)y_t = (l_{t-1} + b_{t-1})\, s_{t-s}\,(1 + \varepsilon_t)yt​=(lt−1​+bt−1​)st−s​(1+εt​)
εt\varepsilon_tεt​

Measurement equation for ETS(M,A,M)\text{ETS}(M,A,M)ETS(M,A,M): multiplicative error and multiplicative seasonality. The seasonal factor scales the level+trend, and the error is a relative perturbation.

Notations

ltl_tlt​

Level state

btb_tbt​

Trend state

sts_tst​

Seasonal state

α\alphaα

Level smoothing

β∗\beta^*β∗

Trend smoothing

γ\gammaγ

Seasonal smoothing

ϕ\phiϕ

Damping parameter

εt\varepsilon_tεt​

Innovation

About these symbols

Level state:

Trend state:

Seasonal state:

Level smoothing: α∈(0,1)\alpha \in (0,1)α∈(0,1)

Trend smoothing: β∗∈(0,α)\beta^* \in (0, \alpha)β∗∈(0,α)

Seasonal smoothing: γ∈(0,1−α)\gamma \in (0, 1-\alpha)γ∈(0,1−α)

Damping parameter: ϕ∈(0,1]\phi \in (0, 1]ϕ∈(0,1]

Innovation: εt∼NID(0,σ2)\varepsilon_t \sim \text{NID}(0, \sigma^2)εt​∼NID(0,σ2)

    Transition checks

    Forecast origin
    y^T+h∣T=ET[yT+h],h=1,2,…\widehat{y}_{T+h|T}=\mathbb{E}_T[y_{T+h}],\qquad h=1,2,\ldotsy​T+h∣T​=ET​[yT+h​],h=1,2,…

    Conditioning on information at T separates the sample from the projection. The forecast can be smooth even when later realized data will not be.

    The bridge point is shared so the eye can see the handoff. After that point, the red line is a model forecast, not observed history.

    Do not score the forecast segment as realized data or read it as a policy promise.

    Uncertainty propagation
    Var⁡T(yT+h)=σ2∑j=0h−1ψj2\operatorname{Var}_T(y_{T+h})=\sigma^2\sum_{j=0}^{h-1}\psi_j^2VarT​(yT+h​)=σ2j=0∑h−1​ψj2​

    Each future innovation contributes through its impulse weight ψj\psi_jψj​. Unless the future is degenerate, longer horizons carry more conditional variance.

    The band widens when shocks accumulate through the model recursion.

    Do not treat the band edge as an alternative deterministic scenario.

    Variable timing

    Observed history

    yt∈ITy_t\in\mathcal{I}_Tyt​∈IT​

    The history segment is realized data available at the forecast origin.

    Conditional mean

    y^T+h∣T=E[yT+h∣IT]\widehat{y}_{T+h|T}=\mathbb{E}[y_{T+h}\mid\mathcal{I}_T]y​T+h∣T​=E[yT+h​∣IT​]

    The forecast path is a conditional expectation, so it can be smooth while future realizations remain volatile.

    Prediction band

    σh2=Var⁡(yT+h∣IT)\sigma_h^2=\operatorname{Var}(y_{T+h}\mid\mathcal{I}_T)σh2​=Var(yT+h​∣IT​)

    Band width is horizon-specific uncertainty, not a second deterministic transition.

    Keep going

    Read next

    Continue with a related concept, model, or example.

    Theory model

    IS-LM Model

    a well-connected theoretical model two steps from here

    New angle: theoretical model →
    Macro by Mark
    Hilfe
    DatenschutzerklärungNutzungsbedingungenEthik und Compliance

    © 2026 Mark Jayson Nation LLC