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: st: Specifying Regression model as an equation
From
Rijo John <[email protected]>
To
stata <[email protected]>
Subject
Re: st: Specifying Regression model as an equation
Date
Tue, 1 Apr 2014 19:57:00 +0530
Thanks Nick. I need to explore nl a bit further. I guess it will serve
my purpose.
Rijo.
On Mon, Mar 31, 2014 at 9:09 PM, Nick Cox <[email protected]> wrote:
> Yes; in the particular sense that you can specify such a model, with a
> different syntax, to -nl-, given that it is not linear in the
> parameters.
>
> No; in the sense that this is unlikely to correspond one-to-one in
> effect with anything in EViews [NB], but here I speculate. For
> example, how would EViews fit such a model?
>
> Nick
> [email protected]
>
> On 31 March 2014 16:18, Rijo John <[email protected]> wrote:
>
>> I am doing a regression analysis with time series data. I want to
>> know if it is possible to specify the regression model as an equation
>> in Stata like in Eviews?
>>
>> Example: Y=a*(1-b) + b*L.Y + c*X1 - b*c*L.X1 + d*X2 - b*d*L.X2
>>
>> Where L.* are lagged variables.
>> a, b, c, & d are the parameters to be estimated.
>> It is possible to specify the above equation as such in Eviews. Can we
>> do this in Stata?
> *
> * 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/
--
Rijo M John, PhD
Assistant Professor,
Indian Institute of Technology Jodhpur,
Rajasthan, India - 342011
Web: http://home.iitj.ac.in/~rmjohn
*
* 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/