Re: st: Breaks in ordered probit model

[Erik Berwart <eberwart@mac.com>]

Dear Maarten,

First of all thank you for your mail.

In my model the rating change of today depends on 12 explanatory variables.
I compare ratings changes of credit rating agency A with dummies that represent if there were previous credit rating changes for the same company from credit rating agency B.
The lags are months, and I use 6 months. I have 12 variables because I differentiate between upgrades and downgrades.
In summary a rating change of A depends in previous upgrades and downgrades of B.

I am new in econometrics, can you give me some advise of literature to read about your answer, the interaction with time and how to implement it?

Thank you in advance,

Erik Berwart


On 31 Jan 2011, at 21:19, Maarten buis wrote:

> --- On Mon, 31/1/11, Erik Berwart wrote:
>> I have a panel data of credit rating changes for almost 10 years.
>> because of the ordered nature of credit rating changes I
>> used an ordered probit model to regress the credit rating
>> changes.
>> I suspect that the coefficients of the regression changes
>> through time. I wonder if there is some test to be certain
>> of my intuition?
>> If it does exist, how can I perform that test?
> 
> That is just an interaction with time. The factor variable 
> notation is very convenient for that purpose.
> 
> Hope this helps,
> Maarten
> 
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
> 
> http://www.maartenbuis.nl
> --------------------------
> 
> 
> 
> 
> *
> *   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/