X; - X-1 = (H + y;) – (Hi-1 + yt–1) (2.27) = 6 + W; + Yt - Yt-1. It is easy to show z; = yt – Yt-1 is stationary using Chap. 1.1. That is, because stationary, Yt is Yz(h) = cov(z;+h, Zt) = cov(yt+h - Yt+h-1» Yt – Yt-1) %3D %3D = 2y, (h) – Yy(h + 1) – y,(h – 1) is independent of time; we leave it as an exercise (Problem 2.7) to show that x, – X1-1 in (2.27) is stationary. One advantage of differencing over detrending to remove trend is that no param- eters are estimated in the differencing operation. One disadvantage, however, is that differencing does not yield an estimate of the stationary process y; as can be seen in (2.27). If an estimate of y, is essential, then detrending may be more appropriate. If the goal is to coerce the data to stationarity, then differencing may be more appropri- ate. Differencing is also a viable tool if the trend is fixed, as in Example 2.4. That is, e.g., if µ; = Bo + Bị t in the model (2.24), differencing the data produces stationarity (see Problem 2.6):

Calculus For The Life Sciences
2nd Edition
ISBN:9780321964038
Author:GREENWELL, Raymond N., RITCHEY, Nathan P., Lial, Margaret L.
Publisher:GREENWELL, Raymond N., RITCHEY, Nathan P., Lial, Margaret L.
Chapter14: Discrete Dynamical Systems
Section14.3: Determining Stability
Problem 13E: Repeat the instruction of Exercise 11 for the function. f(x)=x3+x For part d, use i. a1=0.1 ii...
icon
Related questions
Question

Show (2.27) x_t - x_t-1 is stationary 

X; - X1-1 = (H, + yt) – (H1-1 + yt-1)
(2.27)
= 6 + W; + yt – Yt-1·
It is easy to show z; = y; - Y;–1 is stationary using Chap. 1.1. That is, because y, is
stationary,
Yz(h) = cov(z+h, Z;) = cov(y;+h - Yt+h-1, Yt – Yt-1)
= 2y»(h) – Y»(h + 1) – y»(h – 1)
%3D
is independent of time; we leave it as an exercise (Problem 2.7) to show that x, – X-1
in (2.27) is stationary.
One advantage of differencing over detrending to remove trend is that no param-
eters are estimated in the differencing operation. One disadvantage, however, is that
differencing does not yield an estimate of the stationary process y, as can be seen
in (2.27). If an estimate of y; is essential, then detrending may be more appropriate. If
the goal is to coerce the data to stationarity, then differencing may be more appropri-
ate. Differencing is also a viable tool if the trend is fixed, as in Example 2.4. That is,
e.g., if µ, = Bo + Bị t in the model (2.24), differencing the data produces stationarity
(see Problem 2.6):
%3D
Transcribed Image Text:X; - X1-1 = (H, + yt) – (H1-1 + yt-1) (2.27) = 6 + W; + yt – Yt-1· It is easy to show z; = y; - Y;–1 is stationary using Chap. 1.1. That is, because y, is stationary, Yz(h) = cov(z+h, Z;) = cov(y;+h - Yt+h-1, Yt – Yt-1) = 2y»(h) – Y»(h + 1) – y»(h – 1) %3D is independent of time; we leave it as an exercise (Problem 2.7) to show that x, – X-1 in (2.27) is stationary. One advantage of differencing over detrending to remove trend is that no param- eters are estimated in the differencing operation. One disadvantage, however, is that differencing does not yield an estimate of the stationary process y, as can be seen in (2.27). If an estimate of y; is essential, then detrending may be more appropriate. If the goal is to coerce the data to stationarity, then differencing may be more appropri- ate. Differencing is also a viable tool if the trend is fixed, as in Example 2.4. That is, e.g., if µ, = Bo + Bị t in the model (2.24), differencing the data produces stationarity (see Problem 2.6): %3D
Expert Solution
trending now

Trending now

This is a popular solution!

steps

Step by step

Solved in 2 steps

Blurred answer