rently there were two issues, the comparison between R and Stata
> > was one issue and the "optimum" solution another. As I understand it,
> > there was some question about R numerical gradient calculation. This would
> > suggest some features of the function may be of interest t
ds newuoa, and Nelder-Mead are improved by
> scaling, but not by the availability of exact gradients. I don't know what is
> wrong with bobyqa in this example.
>
> In short, even with scaling and exact gradients, this optimization problem is
> recalcitrant.
>
> Best,
> Ra
re ( I haven't used these myself to any
extent and just try to run some simple teaching examples, asking
for my own clarification as much as anything).
Thanks.
----
> From: rvarad...@jhmi.edu
> To: pda...@gmail.com; alex.ols...@gmail.com
> Date: Sat, 7 Ma
ation as much as anything).
Thanks.
> From: rvarad...@jhmi.edu
> To: pda...@gmail.com; alex.ols...@gmail.com
> Date: Sat, 7 May 2011 11:51:56 -0400
> CC: r-help@r-project.org
> Subject: Re: [R] maximum likelihood convergence reproducing Anderson Blundell
> 1982 Econometr
Alex Olssen wrote:
>
> Wow that is really interesting,
>
> Sorry I was asleep when you emailed these.
>
> And yes, of course, I had been trying to implement model 18, not 18s,
> that was a typo, sorry.
>
> I will have a look at the code you posted.
>
> Thanks,
>
> Alex
>
I have run nlm wit
ters - but since I called all the parameters theta anyway there
>> is no need for it. e1 and e2 are the residuals from the first and
>> second equations of the system. Sigma is a 2x2 matrix which is the
>> outer product of the two vectors of residuals.
>>
>> Kind regards
>
> Kind regards,
>
> Alex
>
>
>
> On 9 May 2011 23:12, Mike Marchywka wrote:
>>
>>
>>
>>
>>
>>
>>
>>> Date: Mon, 9 May 2011 22:06:38 +1200
>>> From: alex.ols...@g
On May 9, 2011, at 13:40 , Alex Olssen wrote:
> Hi Mike,
>
> Mike said
> "is this it, page 1559?"
>
> That is the front page yes, page 15*6*9 has the table, of which the
> model labelled 18s is the one I replicated.
>
However, the R code you posted will at best replicate model 18. For 18s, yo
> Date: Mon, 9 May 2011 22:06:38 +1200
> From: alex.ols...@gmail.com
> To: pda...@gmail.com
> CC: r-help@r-project.org; da...@otter-rsch.com
> Subject: Re: [R] maximum likelihood convergence reproducing Anderson Blundell
> 1982
ectors of residuals.
Kind regards,
Alex
On 9 May 2011 23:12, Mike Marchywka wrote:
>
>
>
>
>
>
>
>> Date: Mon, 9 May 2011 22:06:38 +1200
>> From: alex.ols...@gmail.com
>> To: pda...@gmail.com
>> CC: r-help@
Peter said
"Ahem! You might get us interested in your problem, but not to the
level that we are going to install Stata and Tsp and actually dig out
and study the scientific paper you are talking about. Please cite the
results and explain the differences."
Apologies Peter, will do,
The results wh
On May 9, 2011, at 06:07 , Alex Olssen wrote:
> Thank you all for your input.
>
> Unfortunately my problem is not yet resolved. Before I respond to
> individual comments I make a clarification:
>
> In Stata, using the same likelihood function as above, I can reproduce
> EXACTLY (to 3 decimal p
Thank you all for your input.
Unfortunately my problem is not yet resolved. Before I respond to
individual comments I make a clarification:
In Stata, using the same likelihood function as above, I can reproduce
EXACTLY (to 3 decimal places or more, which is exactly considering I
am using differe
On May 7, 2011, at 17:51 , Ravi Varadhan wrote:
> There is something strange in this problem. I think the log-likelihood is
> incorrect. See the results below from "optimx". You can get much larger
> log-likelihood values than for the exact solution that Peter provided.
>
> ## model 18
> ln
Olssen
Cc: r-help@r-project.org
Subject: Re: [R] maximum likelihood convergence reproducing Anderson
Blundell 1982 Econometrica R vs Stata
On May 6, 2011, at 14:29 , Alex Olssen wrote:
> Dear R-help,
>
> I am trying to reproduce some results presented in a paper by Anderson
> and Blun
On May 6, 2011, at 14:29 , Alex Olssen wrote:
> Dear R-help,
>
> I am trying to reproduce some results presented in a paper by Anderson
> and Blundell in 1982 in Econometrica using R.
> The estimation I want to reproduce concerns maximum likelihood
> estimation of a singular equation system.
> I
Dear R-help,
I am trying to reproduce some results presented in a paper by Anderson
and Blundell in 1982 in Econometrica using R.
The estimation I want to reproduce concerns maximum likelihood
estimation of a singular equation system.
I can estimate the static model successfully in Stata but for t
17 matches
Mail list logo
