TimeSeriesBook.pdf

# For the integrated process the forecast error can be

• 435

This preview shows pages 164–166. Sign up to view the full content.

For the integrated process the forecast error can be written as X t + h - e P t X t + h = Z t + h + (1 + ψ 1 ) Z t + h - 1 + . . . + (1 + ψ 1 + ψ 2 + . . . + ψ h - 1 ) Z t +1 . The forecast error variance therefore is E X t + h - e P t X t + h 2 = 1 + (1 + ψ 1 ) 2 + . . . + (1 + ψ 1 + . . . + ψ h - 1 ) 2 σ 2 . This expression increases with the length of the forecast horizon h , but is no longer bounded. It increases linearly in h to infinity. 2 The precision of the forecast therefore not only decreases with the forecasting horizon h as in the case of the trend-stationary model, but converges to zero. In the example above of the ARIMA(0,1,1) process the forecasting error variance is E ( X t + h - P t X t + h ) 2 = 1 + ( h - 1) (1 + θ ) 2 σ 2 . This expression clearly increases linearly with h . 7.1.3 Impulse Response Function The impulse response function (dynamic multiplier) is an important analyt- ical tool as it gives the response of the variable X t to the underlying shocks. In the case of the trend-stationary process the impulse response function is e P t X t + h ∂Z t = ψ h -→ 0 for h → ∞ . 2 Proof : By assumption { ψ j } is absolutely summable so that Ψ(1) converges. Moreover, as Ψ(1) 6 = 0, there exists ε > 0 and an integer m such that h j =0 ψ j > ε for all h > m . The squares are therefore bounded from below by ε 2 > 0 so that their infinite sum diverges to infinity.

This preview has intentionally blurred sections. Sign up to view the full version.

146 CHAPTER 7. INTEGRATED PROCESSES The effect of a shock thus declines with time and dies out. Shocks have there- fore only transitory or temporary effects. In the case of an ARMA process the effect even declines exponentially (see the considerations in Section 2.3). 3 In the case of integrated processes the impulse response function for ∆ X t implies : e P t X t + h ∂Z t = 1 + ψ 1 + ψ 2 + . . . + ψ h . For h going to infinity, this expression converges j =0 ψ j = Ψ(1) 6 = 0. This implies that a shock experienced in period t will have a long-run or permanent effect. This long-run effect is called persistence . If { X t } is an ARMA process then the persistence is given by the expression Ψ(1) = Θ(1) Φ(1) . Thus, for an ARIMA(0,1,1) the persistence is Ψ(1) = Θ(1) = 1 + θ . In the next section we will discuss some examples. 7.1.4 The Beveridge-Nelson Decomposition The Beveridge-Nelson decomposition represents an important tool for the un- derstanding of integrated processes. 4 It shows how an integrated time series of order one can be represented as the sum of a linear trend, a random walk, and a stationary series. It may therefore be used to extract the cyclical com- ponent (business cycle component) of a time series and can thus be viewed as an alternative to the HP-filter (see section 6.5.2) or to more elaborated so-called structural time series models (see sections 17.1 and 17.4.2). Assuming that { X t } is an integrated process of order one, there exists, according to Definition 7.1, a causal representation for { X t } : X t = δ + Ψ(L) Z t with Z t WN ( 0 , σ 2 ) with the property Ψ(1) 6 = 0 and j =0 j | ψ j | < . Before proceeding to the main theorem, we notice the following simple, but extremely useful polyno- 3 The use of the partial derivative is just for convenience. It does not mean that
This is the end of the preview. Sign up to access the rest of the document.
• Spring '17
• Raffaelle Giacomini

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern