Thanks Austin! That is helpful. I will try successive cross sectional regressions and a survival analysis.
Best Regards
Dirk
Dirk P. Libaers, PhD
Assistant Professor of Entrepreneurship and Innovation,
Institute for Entrepreneurship and Innovation,
H.W. Bloch School of Business and Public
Administration,
5110 Cherry Street
Kansas City, MO 64110-2499
University of Missouri - Kansas City
Office: Bloch 235
Phone: (816)235 2625
Email: [email protected]
-----Original Message-----
From: [email protected] on behalf of Austin Nichols
Sent: Wed 11/25/2009 10:19 AM
To: [email protected]
Subject: Re: st: how to estimate the impact of founding conditions in a panel of firms
Dirk P. <[email protected]>:
Reconceptualize your panel data as a cross-section of lives of firms.
You can describe subsequent trajectories, but you have a cross-section
of data on lifetime outcomes; firms are only founded once. A survival
regression is one analysis to consider; see -help st- and -findit
hshaz-.
On Wed, Nov 25, 2009 at 11:11 AM, Libaers, Dirk P. <[email protected]> wrote:
>
> Hi all,
>
>
> My first post.
>
> This may seem a basic question !
>
>
> I have a panel of firms 47 firms over a 10-year period. I am interested in examining attributes of the founding context of these firms and their short, medium, and long-term impact on various measures of firm performance. In essence I want to test the imprinting hypothesis that posits that elements in the founding contexts will leave long lasting imprints on various firm characteristics. The founding conditions I like to test are:
>
> 1.Organizational origin of the firm ( I deal with spinoffs from a university or established firm), this is a dummy variable; 2. Market growth at the time of firm founding; this is a continuous variable 3. International experience of founding team, a dummy variable. My dependent variables are continuous or count.
>
> How can I estimate the parameters of these initial variables that are entered in my panel in the first year ? I use STATA 10.
*
* 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/
<<winmail.dat>>
