Make some adjust to the script but don't know does is there error

d1 d2 and d3 are different data series

Want regress d1 against d2 and d3 without const

The output would be a regress d1hat

Do a adf on d1 - d1hat

Use the bfgsmax to determine the coefficients of d2 and d3 maximising t from the adf of d1 - d11hat

function scalar adf_t (matrix *b, series y, series d2, series d3)

series d0 = y - (b[1]*d2 + b[2]*d3)

adf 0 d0 --c --quiet

scalar tau = $test

return tau

end function

Using the above script gives a error

The convergence criterion was not met

Error executing script: halting

Dec 23, 2011 11:21:41 PM, gretl-users@lists.wfu.edu wrote:

Send Gretl-users mailing list submissions to

gretl-users@lists.wfu.edu

To subscribe or unsubscribe via the World Wide Web, visit

http://lists.wfu.edu/mailman/listinfo/gretl-users

or, via email, send a message with subject or body 'help' to

gretl-users-request@lists.wfu.edu

You can reach the person managing the list at

gretl-users-owner@lists.wfu.edu

When replying, please edit your Subject line so it is more specific

than "Re: Contents of Gretl-users digest..."

Today's Topics:

1. Using BFGSmax (clarodina@lycos.com)

2. Using BFGSmax (clarodina@lycos.com)

3. Re: Using BFGSmax (Allin Cottrell)

4. Adding one variable for Autoregressive Conditional Duration

(Josephine Sudiman)

----------------------------------------------------------------------

Message: 1

Date: Fri, 23 Dec 2011 18:25:42 +0000 (GMT)

From: "clarodina@lycos.com" <clarodina@lycos.com>

Subject: [Gretl-users] Using BFGSmax

To: gretl-users@lists.wfu.edu

Message-ID: <1608802836.117946.1324664742112.JavaMail.mail@webmail18>

Content-Type: text/plain; charset=UTF-8

Allin Cottrell,

Tks for the reply

d1 is another data series and not the fit value from d1 = b[1] * d2 + b[2] * d3

Want to regress d1 against d2 and d3 and find a d1^hat approximating d1

Ols uses error minimization but want to use maximisation of t value from the adf of d1^hat

Using the script you provide, the original d1 data series is replace from the d1^hat

Clarodina

------------------------------

Message: 2

Date: Fri, 23 Dec 2011 18:32:21 +0000 (GMT)

From: "clarodina@lycos.com" <clarodina@lycos.com>

Subject: [Gretl-users] Using BFGSmax

To: gretl-users@lists.wfu.edu

Message-ID: <509732906.118095.1324665141085.JavaMail.mail@webmail18>

Content-Type: text/plain; charset="us-ascii"

An HTML attachment was scrubbed...

URL: http://lists.wfu.edu/pipermail/gretl-users/attachments/20111223/9e2b3d77/attachment-0001.html

------------------------------

Message: 3

Date: Fri, 23 Dec 2011 13:41:35 -0500 (EST)

From: Allin Cottrell <cottrell@wfu.edu>

Subject: Re: [Gretl-users] Using BFGSmax

To: Gretl list <gretl-users@lists.wfu.edu>

Message-ID: <alpine.LNX.2.00.1112231331270.519@waverley.dhcp.wfu.edu>

Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed

On Fri, 23 Dec 2011, clarodina@lycos.com wrote:

> d1 is another data series and not the fit value from d1 =

> b[1] * d2 + b[2] * d3

>

> Want to regress d1 against d2 and d3 and find a d1^hat

> approximating d1

>

> Ols uses error minimization but want to use maximisation of

> t value from the adf of d1^hat

>

> Using the script you provide, the original d1 data series is

> replace from the d1^hat

My script can be thought of as giving you a d1-hat that

satisfies your "maximum ADF t" criterion. Of course, it may

bear little relationship to the actual d1 data. If in addition

you want d1-hat to "resemble" d1 in some way, you'll have to

constrain the maximization of the ADF t -- e.g. provide a

criterion for maximization that's a weighted sum of SSR for d1

and the ADF t-ratio for d1-hat (with a negative sign on the

SSR). [SSR = sum of squared residuals]

But this seems very weird, and there's no telling what

statistical properties the resulting estimator would possess.

Allin Cottrell

------------------------------

Message: 4

Date: Fri, 23 Dec 2011 20:20:25 -0800 (PST)

From: Josephine Sudiman <jsudiman@yahoo.com>

Subject: [Gretl-users] Adding one variable for Autoregressive

Conditional Duration

To: "r.lucchetti@univpm.it" <r.lucchetti@univpm.it>

Cc: "gretl-users@lists.wfu.edu" <gretl-users@lists.wfu.edu>

Message-ID:

<1324700425.73808.YahooMailNeo@web121403.mail.ne1.yahoo.com>

Content-Type: text/plain; charset="iso-8859-1"

Dear Gretl Mailing List Users,?

?

My apologise to email you at this time of year. First of all, I wish that you will have a Merry Christmas which will come in less than 48 hours. I am honestly very grateful to join this mailing list, it is always very supportive.

Once I wrote an email in GRETL mailing list to ask?help on how to code for the Maximum Likelihood Estimation to estimate the ACD model on GRETL and?I have the great help from Prof.?Lucchetti in this issue.

Now, I am begging for assistance again. It is still?about the ACD model, but my specification is:

EP_DUR(t) = x0 + x1 P_DUR(t-1) + x2 EP_TIME(t-1) + x3 SPREAD (t-1)

where:

EPTIME is the expected duration

PTIME is the actual duration (i got the value of this series)

EPTIME is the expected duration at lag1

SPREAD is the spread at lag1; spread is difference between bid and ask (i got the value of this series)

I?intend to apply Weilbull WACD (1,1)?and?Exponential EACD (1,1) to obtain the estimation of X0, x1, x2 and x3.

May question is where should I add the variable (SPREAD) in this model. I attached?the previous GRETL program that Prof. Lucchetti wrote for me last time and my simple data in gdt. I am really sorry to disturb you all during this festive break. Many sincere thanks for any help and attention....

Kind regards,

Josephine

------------------------------------------------------------------------------------------------------------------------------------------

-------------- next part --------------

An HTML attachment was scrubbed...

URL: http://lists.wfu.edu/pipermail/gretl-users/attachments/20111223/6d2a7bff/attachment.html

-------------- next part --------------

A non-text attachment was scrubbed...

Name: example_dataplus.gdt

Type: application/octet-stream

Size: 9935 bytes

Desc: not available

Url : http://lists.wfu.edu/pipermail/gretl-users/attachments/20111223/6d2a7bff/attachment.obj

-------------- next part --------------

A non-text attachment was scrubbed...

Name: ACD_funcs.inp

Type: application/octet-stream

Size: 2465 bytes

Desc: not available

Url : http://lists.wfu.edu/pipermail/gretl-users/attachments/20111223/6d2a7bff/attachment-0001.obj

-------------- next part --------------

A non-text attachment was scrubbed...

Name: ACD.inp

Type: application/octet-stream

Size: 1916 bytes

Desc: not available

Url : http://lists.wfu.edu/pipermail/gretl-users/attachments/20111223/6d2a7bff/attachment-0002.obj

------------------------------

_______________________________________________

Gretl-users mailing list

Gretl-users@lists.wfu.edu

http://lists.wfu.edu/mailman/listinfo/gretl-users

End of Gretl-users Digest, Vol 59, Issue 29

*******************************************