Thank you Austin, for your reply. However I'm not sure clogit or
asclogit is appropriate here, because each auction has different set
of bidders, so the alternatives are changing. I checked out clogit and
asclogit, and it seems that you need a pre-specified set of
alternatives, such as presidential candidates, or travel modes.
For instance, (this is a reverse auction, only one winning seller in
each auction)
Auctionid, buyerid, sellerIsChosen(Y),sellerid, sellercharacteristics
1,1,1,1,...,
1,1,0,2,...,
1,1,0,3,...,
1,1,0,4,...,
2,1,1,5,...,
2,1,0,6,...,
2,1,0,3,...,
3,2,1,4,...,
3,2,0,2,...;
3,2,0,6,...,
3,2,0,9,....,
3,2,0,12,...,
3,2,0,20,...,
Sorry I wasn't clearer in my initial post and thank you for any
suggestions you can provide.
Thank you!
On Tue, Sep 28, 2010 at 9:44 PM, Austin Nichols <austinnichols@gmail.com> wrote:
> C Engelbrecht <cngelbrecht@gmail.com>:
> See help clogit
> and help asclogit
> for starters.
>
> On Wed, Sep 29, 2010 at 12:07 AM, C Engelbrecht <cngelbrecht@gmail.com> wrote:
>> I'm not sure if Probit / Logit is the appropriate model here, and I
>> hope someone can give me some suggestions.
>>
>> Suppose we have a competitive auction process. A, B, C,... F all place
>> bids in an auction hosted by Z. Z can only pick one. Now I want to
>> study what drives that choice. Currently I am modeling it as a binary
>> choice, i.e. for each bid (A, ..., F) the outcome is either winning or
>> not winning. But this seems to disregard the fact that only one of
>> them can be winning. Is this an unnecessary concern? If not, how would
>> you suggest addressing it?
>>
>> Many thanks,
>>
>> Charlie
> *
> * 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/
