Scribd
Upload
21 views17 pages

When Is An Autoregressive Model Dynamically Stable - v3.2

Uploaded by

Raghavan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
21 views17 pages

When Is An Autoregressive Model Dynamically Stable - v3.2

Uploaded by

Raghavan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 17

When is an Autoregressive Model Dynamically

Stable?

McGraw-Hill/Irwin Copyright © 2010 by The McGraw-Hill Companies, Inc. All rights reserved.
AR Model

 Autoregressive processes arise frequently in econometrics.


– For example, we might have a simple dynamic model of the form:
yt = β0 + β1yt-1 + εt ; εt ~ i.i.d.[0 ,σ2] (1)

8-2
Conditions needed to ensure
the stationarity of more general AR models

 First, what do we mean by a stochastic process that's "stationary"?

 There are several types of "stationarity"


– Weak stationarity (or Covariance stationarity).
 What this means is that the mean and variance of the process are
both finite and must not depend on time;
 and the covariances between pairs of random values from the
process can depend on how far apart the values are in time, but
not the value of time itself.

8-3
Stationarity in AR(1) Model

 let's go back to the model in (1) above, and see what we mean by "stationarity" in
this simple case.
yt = β0 + β1yt-1 + εt ; εt ~ i.i.d.[0 ,σ2] (1)
 Notice that if we lag the equation by one period, we get:

yt-1 = β0 + β1yt-2 + εt-1 ; εt-1 ~ i.i.d.[0 , σ2] . (3)

Now, use (3) to eliminate yt-1 from (1), yielding:

yt = β0 + β1 [ β0 + β1yt-2 + εt-1 ] + εt .

Now, keep doing this repeatedly, and we end up with:

8-4 yt = β0 [1 + β1 + β12 + β13 + .......] + [εt + β1 εt-1 + β12εt-2 + ....]


 or,

yt = β0Σ( β1i ) + Σ( β1iεt-i ), (4)

where the range of summation is from zero to infinity in


each case.

8-5
• Given what we assumed about the εt values in equation (1), we
see from (4) that:

E[ yt ] = β0Σ( β1i ) = μ ; say


var.[ yt ] = σ2 Σ( β12i)
cov.[ εt , εs ] = 0 ; for all t ≠ s .

8-6
 Now, we know that Σ( β1i ) converges to the finite limit,
if and only if |β1| < 1.
– That is, it converges if and only if β1 lies strictly inside the unit
interval.
– If this condition holds, then both E[ yt] and var [yt ] will be finite -
and you can see that neither they nor the covariances depend on
the value of 't'.

 This condition on the value of β1 ensures that the series, yt,


is covariance stationary.
8-7
 The case where β1 = 1 is termed the "unit root" case, for
reasons that will become even more apparent below; and if
| β1 | > 1, the yt series is "explosive".

8-8
 Let's see why this particular terminology is used.
– If the stationarity condition is not satisfied, then any "shock" to the
yt series will lead to a subsequent time-path that has an unbounded
mean and variance.

– On the other hand, if the process is stationary, then following such a


"shock", the time-path for yt will eventually settle down to what it
was previously.
 The shock will be "absorbed".

– For this reason we often say that non-stationary time-series have "long
8-9 memories".
Let's see some examples of this.

8-10
8-11
8-12
8-13
let's go out to t = 100:

8-14
 More generally, let's suppose that we have an AR(p) model, of the form:
yt = ф1 yt-1 + ф 2 yt-2 + .......... + ф p yt-p + εt ; εt ~ i.i.d.[0 , σ2]

 Then the condition that must be satisfied in order that this model is
dynamically stable is that all of the roots of the following so-called
"characteristic equation"
1 - ф 1 z - ф 2 z2 - ..... - ф p zp = 0 ,

lie strictly outside the unit circle

8-15
 Let's go back to the AR(1) model - that is, set p = 1.

 In that case, the characteristic equation is

1 - ф 1 z = 0.

Solving for z, we get z = 1 / ф 1, so the stationarity condition is that


|1 / ф 1| > 1; or, equivalently, |ф 1| < 1.

 This is exactly the condition that we saw above, now in our new notation.
8-16
 Next, let's think about a series that is second-order autoregressive, or AR(2).

 In this case, the conditions that need to be satisfied to ensure stationarity of the
series are more complicated.
– Suppose that our AR(2) model for Y is written as:
yt = ф 1 yt-1 + ф 2 yt-2 + εt ; εt ~ i.i.d.[0 , σ2] .

– This model will be stationary (i.e., dynamically stable) if the roots of the
characteristic equation,1 - ф 1z - ф 2z2 = 0 ,
all lie strictly outside the unit circle.

8-17

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy