Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Re: st: Question on estimation procedure


From   Nick Cox <[email protected]>
To   [email protected]
Subject   Re: Re: st: Question on estimation procedure
Date   Tue, 13 Nov 2012 17:08:38 +0000

This looks like the same question in essence, even though your model
changes from post to post.

If you disagree with Kit's analysis, please explain why he is wrong.

Otherwise if something is impossible in principle, you can't do it in
Stata [NB].

Nick

On Tue, Nov 13, 2012 at 4:56 PM, Elena Quercioli
<[email protected]> wrote:

> My question was meant to get at STATA (estimation) capabilities and
> not identifiability; here, in essence, is what I want to know. I want
> to simultaneously estimate the common base and other coefficients of
> this geometric function:
>
>  Y = c_0 + c_1[X_1+a^d2 X_2 + a^d3 X_3]
>
> any ideas?

On Mon, Nov 12, 2012 at 9:15 PM, Christopher Baum <[email protected]> wrote:

>> Elena said
>>
>> Oops, my bad. I omitted to state that d1=0.
>>
>> Would you have any suggestions on how to estimate the non-linear model
>> I illustrated?
>>
>>
>>
>> No, the model
>>  Y = c_0 + c_1  X1 + c_2 a^d2 X2
>> is still underidentified, even with the restriction that removes the alpha^0 term. Consider
>>
>> sysuse auto, clear
>>
>> forv c2 = 0.75(0.05)1.2 {
>>         nl (price = {c0} + {c1} * mpg + `c2' * {alpha}^2 * weight)
>>         nlcom `c2' * ([alpha]_cons )^2
>> }
>>
>> As you can see, there is a locus of c2 and alpha values that render the same product (c2 * alpha^2),
>> so the data cannot identify c0, c1, c2, alpha from three data vectors: iota, mpg, weight.
>>
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index