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

Re: st: Model Selection and Choices

 From Syed Basher To "statalist@hsphsun2.harvard.edu" Subject Re: st: Model Selection and Choices Date Wed, 27 Apr 2011 23:58:29 -0700 (PDT)

```Hi Muhammad,

I still think before you apply any statistical methods to discriminate between linear and non-linear models, you should have a head start about it from the economic theory you're contemplating to test. But as always having some statistical output always make it  easier to decide. Good luck.

--
Syed Abul Basher
Qatar Central Bank
P.O. Box 1234
Doha, Qatar.
http://www.syedbasher.org/

----- Original Message -----
> From: Muhammad Anees <aneesmkhattak@gmail.com>
> To: statalist@hsphsun2.harvard.edu
> Cc:
> Sent: Thursday, April 28, 2011 9:46 AM
> Subject: Re: st: Model Selection and Choices
>
>T hanks Yafee and Basher!
>
> I was away for a few days due to the death of my family member. I
> would try to use the BDS test and will reply. Basher! I have already
> tested these variables I know well how to proceed to test for
> cointegration. My question is how I can I test if linear or non-linear
> modelling applies to data I have. I think Yafee suggestions would work
> but let me test it and show you my conclusion.
>
> On 27 April 2011 11:18, Syed Basher <syed.basher@yahoo.com> wrote:
>> Hi,
>> Here is a straight answer. I would first check for the unit root in the
> data. Depending on the results, select between stationary and nonstationary
> modeling. The case of non-lineariy should be dictated by economic theory. If,
> for example, unit root is present and the theory behind your economic model is
> non-linearity, you can then use nonlinear cointegration. The same logic applies
> for stationary variables. Hope this answers your question.
>>
>> --
>> Syed Abul Basher
>> Qatar Central Bank
>> P.O. Box 1234
>> Doha, Qatar.
>> http://www.syedbasher.org/
>>
>> From: Muhammad Anees <aneesmkhattak@gmail.com>
>>> To: statalist@hsphsun2.harvard.edu
>>> Sent: Wednesday, April 27, 2011 8:47 AM
>>> Subject: Re: st: Model Selection and Choices
>>>
>>> Hi All!
>>>
>>> I have a straight question on time series modelling. I have a 37 years
>>> annualized time series data on five variables. I want to check if
>>> linear or non linear modelling would be best in my case. Is there any
>>> way using stata to obtain results and to select model that best
>>> reflects my specific time series data.
>>>
>>> --
>>> MSc in Economics
>>> The University of Sheffield
>>> United Kingdom
>>> *
>>> *  For searches and help try:
>>> *  http://www.stata.com/help.cgi?search
>>> *  http://www.stata.com/support/statalist/faq
>>> *  http://www.ats.ucla.edu/stat/stata/
>>>
>>>
>>>
>>
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/statalist/faq
>> *   http://www.ats.ucla.edu/stat/stata/
>>
>
>
>
> --
> MSc in Economics
> The University of Sheffield
> United Kingdom
>
> *
> *  For searches and help try:
> *  http://www.stata.com/help.cgi?search
> *  http://www.stata.com/support/statalist/faq
> *  http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```