Hi,
I have a logl function for an asymmetric garch estimation. One of the variables is like this
y = ......+ x * min(p,0) + .......
How do i enter this min(p,0) in the logl function? Tried using x*(@min(p,0)) but that i guess is wrong
how to do a minimum calculation
Moderators: EViews Gareth, EViews Moderator, EViews Jason, EViews Matt
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13604
- Joined: Tue Sep 16, 2008 5:38 pm
Re: how to do a minimum calculation
What is p?
Re: how to do a minimum calculation
p is the lag value of the residual from the mean equation calculated as
mgarch.append res1= (y1-cons(1) - mu(1)*y1(-1) - mu(2)*y2(-1) - mu(3)*y3(-1))
Which then feeds into a volatility equation as
var_y1=......+rho(1)*(min(res1,0)^2)
mgarch.append res1= (y1-cons(1) - mu(1)*y1(-1) - mu(2)*y2(-1) - mu(3)*y3(-1))
Which then feeds into a volatility equation as
var_y1=......+rho(1)*(min(res1,0)^2)
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13604
- Joined: Tue Sep 16, 2008 5:38 pm
Re: how to do a minimum calculation
I meant, what type of object is it? For that matter, what are X and Y?
Re: how to do a minimum calculation
Sorry if I am unable to clearly say but Y and X are both time series. X is the residual error and Y is the calculated variance. this is a bivariate mgarch model and I started by using the TV_garch.prg and modified the logl function.
-
EViews Gareth
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13604
- Joined: Tue Sep 16, 2008 5:38 pm
Re: how to do a minimum calculation
I'm going to assume they're series objects.
You can use the @recode function.
You can use the @recode function.
Who is online
Users browsing this forum: No registered users and 2 guests
