## Search found 191 matches

- Tue Dec 02, 2008 6:11 am
- Forum: Programming
- Topic: LogL: How to get the gradient other than at estimated value
- Replies:
**1** - Views:
**1859**

### LogL: How to get the gradient other than at estimated value

In fact, I like to find the Hessian for a likelihood object to compute the robust variance. It seems that EViews does not provide one. I try to compute the numerical derivative of gradient vector. Thus, the gradient at b+h (b is the estimated parameter and h is some step size) should be calculated f...

- Tue Dec 02, 2008 4:35 am
- Forum: Programming
- Topic: Logl: Order of Evaluation
- Replies:
**2** - Views:
**2211**

### Logl: Order of Evaluation

Dear all When evaluating by obs, check the following code 'create workfile !T = 100 wfcreate(page=OLS) u 1 !T 'genr the data rndseed(type=mt) 12357 genr x = rnd genr y = 5 +3*x +nrnd 'Logl obj logl L11 L11.append @logl L 'L11.append @byeqn L11.append e = y -c(1) -c(2)*x L11.append v = @sum(e^2)/!T L...

- Tue Dec 02, 2008 4:03 am
- Forum: Programming
- Topic: math functions for coef
- Replies:
**3** - Views:
**2682**

### math functions for coef

It seems that math functions do NOT support coefficient vector. For example

Code: Select all

`wfcreate u 4`

coef(3) c1 = 1

coef(3) c2 = 2

c2 = exp(c1) 'error

- Tue Nov 04, 2008 6:39 pm
- Forum: Programming
- Topic: "cov=" in panel GMM
- Replies:
**6** - Views:
**3675**

### Re: "cov=" in panel GMM

Thanks very much for your detail!

- Tue Nov 04, 2008 5:55 pm
- Forum: Programming
- Topic: "cov=" in panel GMM
- Replies:
**6** - Views:
**3675**

### Re: "cov=" in panel GMM

Code: Select all

`c = 0`

equation eq53.gmm(c=1e-6,iter=sim,gmm=persur,cov=perwhite,nodf) I C F @ C F K

produce smaller SE than eq52.

I think gmm= is for coef estimation, and cov= for covariance estimation, which are computed after the coefs are estimated.

- Tue Nov 04, 2008 5:06 pm
- Forum: Programming
- Topic: "cov=" in panel GMM
- Replies:
**6** - Views:
**3675**

### Re: "cov=" in panel GMM

When over-identified, the following also give the same "std err"

Code: Select all

`c = 0`

equation eq51.gmm(c=1e-6,iter=sim,gmm=persur) I C F @ C F K

c = 0

equation eq52.gmm(c=1e-6,iter=sim,gmm=persur,cov=persur,nodf) I C F @ C F K

- Tue Nov 04, 2008 6:06 am
- Forum: Programming
- Topic: "cov=" in panel GMM
- Replies:
**6** - Views:
**3675**

### "cov=" in panel GMM

If cov= is not set, then it use the same setting as gmm=, right? for example wfopen(t=txt) http://www.wiley.co.uk/wileychi/baltagi/supp/Grunfeld.fil names=(fn yr i f k) pagestruct fn @date(yr) equation eq01.gmm(gmm=persur) I C F K @ C F K equation eq02.gmm(gmm=persur,cov=persur,nodf) I C F K @ C F K...

- Fri Oct 17, 2008 7:26 pm
- Forum: Programming
- Topic: option "l=number" in GMM
- Replies:
**3** - Views:
**2452**

### Re: option "l=number" in GMM

thx What is the option "e" then? pageload cs 'cs.wf1 is an example workfile of EViews smpl @first 1995q1 equation eq01.tsls(n) log(cs) c log(gdp) @ c log(cs(-1)) log(gdp(-1)) equation eq02.gmm(e) log(cs) c log(gdp) @ c log(cs(-1)) log(gdp(-1)) In my opinion, the coefs and std errs should b...

- Thu Oct 16, 2008 7:11 pm
- Forum: Programming
- Topic: option "l=number" in GMM
- Replies:
**3** - Views:
**2452**

### option "l=number" in GMM

For the command gmm, the Command Reference says

l=number Set maximum number of iterations on the first-stage iteration to get the one-step weighting matrix.

What is it for? can not find the difference in equation object or system object gmm estimation.

l=number Set maximum number of iterations on the first-stage iteration to get the one-step weighting matrix.

What is it for? can not find the difference in equation object or system object gmm estimation.

- Thu Oct 16, 2008 4:02 am
- Forum: Bug Reports
- Topic: [DOC bugs] GMM HAC
- Replies:
**1** - Views:
**2366**

### [DOC bugs] GMM HAC

Consulting the original paper, the following equations may have typos User guide II (ver: Nov 13, 2007), P340-341 eq33.8, should be K(j,q)=1-j/(q+1), note that the denominator should be q+1 eq33.43, add square to the LHS, should be a(p)=(l'F(p)l/(l'F(0)l))^2 eq33.45, if the corresponding first lines...

- Fri Oct 10, 2008 7:51 pm
- Forum: Programming
- Topic: construct ARMA model
- Replies:
**2** - Views:
**4719**

### Re: construct ARMA model

May be u like

Code: Select all

`wfopen demo`

!L = 6

%ar = ""

%ma = ""

for !i=1 to !L

%ar = %ar +" ar(" +@str(!i) +")"

%ma = %ma +" ma(" +@str(!i) +")"

equation eq_{!i}.ls log(gdp) c {%ar} {%ma}

next