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]
st: RE: Re: st: Re: st: Re: st: RE: Truncated sample or Heckman selection
From
"Millimet, Daniel" <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: RE: Re: st: Re: st: Re: st: RE: Truncated sample or Heckman selection
Date
Thu, 4 Oct 2012 22:18:38 +0000
Censoring models typically assume the OBSERVED variable has a natural boundary, but this is just a mapping from an underlying latent variable that takes on values on the entire real number line. Like the common labor supply example.
****************************************************
Daniel L. Millimet, Professor
Department of Economics
Box 0496
SMU
Dallas, TX 75275-0496
phone: 214.768.3269
fax: 214.768.1821
web: http://faculty.smu.edu/millimet
****************************************************
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Joerg Luedicke
Sent: Thursday, October 04, 2012 5:10 PM
To: [email protected]
Subject: st: Re: st: Re: st: Re: st: RE: Truncated sample or Heckman selection
If innovation success is defined as novelty sales divided by total sales then, by definition, innovation success cannot be smaller than 0 and not be larger than 1. That means that if a firm is exclusively selling old stuff, their innovation success is just zero. But why do you think this measure is _censored_ at zero? Censoring means that your values would be unbounded in principle, but you just do not observe them below or above a certain value (or within an interval). A classical example would be top coded income. In your case, if you fit a Tobit model with a censoring point at zero, you would essentially assume that this 0 actually means _0 or less_. But this makes no sense as your values cannot be less than 0, by definition.
Joerg
On Thu, Oct 4, 2012 at 4:53 PM, Ebru Ozturk <[email protected]> wrote:
> Innovation success is heavily left-censored - many firms do not have any market novelties and thus no sales from this type of innovation (Grimpe & Kaiser, 2010).
>
> Is that wrong then?
>
> I'm really confused now.
>
> Ebru
>
> ----------------------------------------
>> Date: Thu, 4 Oct 2012 16:45:59 -0500
>> Subject: st: Re: st: Re: st: RE: Truncated sample or Heckman
>> selection
>> From: [email protected]
>> To: [email protected]
>>
>> On Thu, Oct 4, 2012 at 4:34 PM, Ebru Ozturk <[email protected]> wrote:
>> > For Tobit regression, the dependent variable is the percent of total firm sales revenues that derived from the sales of new products. Therefore, it is censored as sales of new products can only be zero or positive.
>> >
>> This just isn't a censoring problem. Consider having a look at:
>>
>> http://en.wikipedia.org/wiki/Censoring_%28statistics%29
>>
>> Joerg
>> *
>> * 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/
> *
> * 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/
*
* 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/
*
* 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/