Question

In: Economics

show that GARCH(1,1) has time varying conditional variance

show that GARCH(1,1) has time varying conditional variance

Solutions

Expert Solution

How to calculate the conditional variance of a time series?

Intuition

Firstly we model the conditional mean process (using a ARMA,ARFIMA...) and subtract it from the original returns series to obtain the "return residuals" : rt−μt=ϵt=σtzt where zt is an i.i.d process with Et(zt)=0 and Vart(zt)=1. Note that the conditional variance of ϵt is equal to σ2t.

However since we know that the variance is time varying we also know that σ2t has a time dependent structure and exhibits autocorrelations (so do the squares returns residuals). We can model it using GARCH class of models which can (very roughly) be seen as ARMA models for the conditional variance process.

Example of a Garch(1,1) : σ2t=a+αϵ2t−1+βσ2t−1

Once we fit our conditional variance models we will be left with the conditional variance process σ2t.At this point we know the conditional variance process σ2t and ϵ2t. This allow us to obtain the final standardized residuals series zt which is i.i.d and equal to ϵt/σt=zt.

Estimation

How do we estimate it ?

The simplest way is to rely on the Maximum Likelihood Estimation (MLE) method. We need to assume a distribution for the zt (the final residuals). Since we know that these residuals are i.i.d it is easy to compute the log-likelihood for a given zt serie. (to be more precise the typical arguments for the likelihood function are ϵ2t and σ2t)

Example : If we assume a normal distribution for zt the log likelihood (assuming no constant) is given by : LogLik=−12∑T1[log(2π)+log(σ2t)+z2t](=−12∑T1[log(2π)+log(σ2t)+ϵ2tσ2t])

But how can we practically obtain zt ? A solution is to use what we called "filters" takings as input the returns series and, based on a particular specifications (ex: arma(1,1)-garch(1,1)), returning σ2t. By "filtering" we mean that we applied the autoregressive framework (recursive algorithm on both the mean and variance) on the input serie (the return serie) to obtain as output the zt .


Related Solutions

A) Why is the conditional variance a good measure of uncertainty? B) Outline the GARCH model...
A) Why is the conditional variance a good measure of uncertainty? B) Outline the GARCH model and GARCH-M model. C) Outline one of the extensions to the basic GARCH family of models
Define in 200 words:  Garch (1,1) model
Define in 200 words:  Garch (1,1) model
Conditional Probability Problem 1 Conditional probability In group of 200 university students, 140 are full time...
Conditional Probability Problem 1 Conditional probability In group of 200 university students, 140 are full time students (80 females and 60 males) and 60 no full time students (40 females and 20 males). Let    M=event a student is male    W=event a student is a female    F=event a student is full time    FC= event a student is not full time 1) Find the probability that a student is male and full time    2) Find the probability...
Show that g(x) = 1/2sin(x-1) has a unique fixed point on the interval [-1,1] Estimate the...
Show that g(x) = 1/2sin(x-1) has a unique fixed point on the interval [-1,1] Estimate the number of iterations required to achieve 10^-2 accuracy
At some time t the time-varying magnetic field component of an electromagnetic wave is pointed in...
At some time t the time-varying magnetic field component of an electromagnetic wave is pointed in the -xˆ direction. If the electromagnetic wave velocity is in the -zˆ direction, what is the direction of the time-varying electric field component of this wave at t? Please explain the reasoning behind the answer A. yˆ B. -yˆ C. -zˆ D. zˆ
Rods of varying length (± 10%) travel one at a time in the direction of their...
Rods of varying length (± 10%) travel one at a time in the direction of their longest axis on a conveyor belt. A mechanical arm pushes rods that are within specification (± 5%) off the belt to one side. A second arm pushes rods that are too long to the other side. Rods that are too short remain on the belt. Use three light barriers (light source + photocell) as sensors, and design the combinational circuits that activate the two...
show calculation and explanation solving Direct Labor Pricce Variance and efficiency variance and the total variance....
show calculation and explanation solving Direct Labor Pricce Variance and efficiency variance and the total variance. if they are favorable or unfavorable? AP x AQ= $350,000 SP x AQ= $315,000 SP x SQ= $450,000
Show how to compute the conditional probability of a straight flush given that the first two...
Show how to compute the conditional probability of a straight flush given that the first two cards you are dealt are the 9 and 10 of hearts.
(a) Show that B {[2, 3, 0,1],[1, 1, 1,1]} is a maximal linearly independent subset of...
(a) Show that B {[2, 3, 0,1],[1, 1, 1,1]} is a maximal linearly independent subset of S {[1, 4, 1,2],[1, 1, 1,1],[3, 2,1, 0],[2, 3, 0,1]}. (b) Calculate dim(span(S)). (c) Does span(S) R4? Why or why not?
1,Let v=(1,1)v=(1,1) be a vector in the xy-plane. Find a planar vector w which has length...
1,Let v=(1,1)v=(1,1) be a vector in the xy-plane. Find a planar vector w which has length 2√2, has a positive first component and is perpendicular to v. W=(,) 2, Find the points where the line l(t)=(1−t,1+t,t) intersects the plane z=x+y (Give the answer in the form of comma separated list of points like (*,*,*), (*,*,*)
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT