Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Box-Cox Tobit


From   Mekhola Chatterjee <mchatterjee07@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Box-Cox Tobit
Date   Wed, 29 Feb 2012 14:20:17 -0600

Thanks Anees, I appreciate.

Regards,

MC

On Mon, Feb 27, 2012 at 12:29 AM, Muhammad Anees <anees@aneconomist.com> wrote:
> Hello,
>
> What I guess from the -btobit- and issues related to the specification
> of -tobit-, the abstract from
>
> http://ideas.repec.org/c/boc/bocode/s457163.html
>
> is here for your reference:
>
> bctobit computes the LM-statistic for testing the tobit specification,
> against the alternative of a model that is non-linear in the
> regressors and contains an error term that can be heteroskedastic and
> non-normally distributed. The test is carried out by taking a Box-Cox
> transformation of the dependent variable [y^(lambda)-1]/lambda and
> testing whether the parameter lambda=1. A rejection of the null
> suggests that the Tobit specification is unsuitable, as an alternative
> value for lambda would be required to return the linearity,
> homoskedasticity and normality assumptions that are necessary for
> consistent estimation. Critical values are obtained via the parametric
> bootstrap, where the regressors are assumed to be stochastic.
>
> What this implies, and what I understand is that if the Lambda is not
> equal to 1 then as an alternative value for lambda would be required
> to return the linearity, homoskedasticity and normality assumptions.
>
> Hope this is of help
>
> Best,
> Anees
>
> On Mon, Feb 27, 2012 at 10:14 AM, Mekhola Chatterjee
> <mchatterjee07@gmail.com> wrote:
>> Hello Anees,
>>
>> Thank you so much for your reply. I have already come across the
>> -bctobit- command and the Box-Cox Double Hurdle model. But I am
>> specifically interested in knowing about the Box-Cox Tobit model. I am
>> just not sure whether after doing the Box-Cox transformation of the
>> dependent variable, I can straight away use the tobit estimation
>> command (-tobit-) and do my analysis? Will that help accounting for
>> the non-normality problem? Or, after the Box-Cox transformation the
>> likelihood itself will change and I have to write my own program?
>>
>> Any help would be much appreciated.
>>
>> Thank you so much.
>>
>> Regards,
>>
>> Mekhola
>>
>> On Sun, Feb 26, 2012 at 10:56 PM, Muhammad Anees <anees@aneconomist.com> wrote:
>>> And the Stata ado named -btobit- works better in your case.
>>>
>>> If not already installed, you can install it from -ssc install btobit-
>>> and then read the help file for discussion from -help btobit-.
>>>
>>> Hope this helps this time
>>>
>>> Best,
>>> Anees
>>>
>>> On Mon, Feb 27, 2012 at 9:50 AM, Muhammad Anees <anees@aneconomist.com> wrote:
>>>> Only a starting comment, the search results from the Statalist
>>>> archives gives a related discussion. It is from
>>>>
>>>> http://www.stata.com/statalist/archive/2009-08/msg00861.html
>>>>
>>>> Hope this suits your need too.
>>>>
>>>> Best,
>>>> Anees
>>>>
>>>> On Mon, Feb 27, 2012 at 9:37 AM, Mekhola Chatterjee
>>>> <mchatterjee07@gmail.com> wrote:
>>>>> Dear All,
>>>>>
>>>>> Can you please help me by letting me know how to do Box-Cox Tobit in
>>>>> STATA. Can I make a box-cox transformation of my dependent variable
>>>>> (which is skewed) and use the general Tobit (-tobit- command) model
>>>>> for estimation? Or, there is any need to change the likelihood
>>>>> function itself and then do the estimation? Could you please cite any
>>>>> references?
>>>>>
>>>>> Please help.
>>>>>
>>>>> Thank you for your time.
>>>>>
>>>>> Regards,
>>>>>
>>>>> M. Chatterjee
>>>>> *
>>>>> *   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/
>>>>
>>>>
>>>>
>>>> --
>>>>
>>>> Best
>>>> ---------------------------
>>>> Muhammad Anees
>>>> Assistant Professor/Programme Coordinator
>>>> COMSATS Institute of Information Technology
>>>> Attock 43600, Pakistan
>>>> http://www.aneconomist.com
>>>
>>>
>>>
>>> --
>>>
>>> Best
>>> ---------------------------
>>> Muhammad Anees
>>> Assistant Professor/Programme Coordinator
>>> COMSATS Institute of Information Technology
>>> Attock 43600, Pakistan
>>> http://www.aneconomist.com
>>>
>>> *
>>> *   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/
>
>
>
> --
>
> Best
> ---------------------------
> Muhammad Anees
> Assistant Professor/Programme Coordinator
> COMSATS Institute of Information Technology
> Attock 43600, Pakistan
> http://www.aneconomist.com
>
> *
> *   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index