Deciding Between Competition and Collusion
May 2001 In many studies in empirical industrial organization, the economist needs to decide between several non-nested models of industry equilibrium. In this paper, we develop a new approach to the model selection problem that can be used when the economist must decide between models with bid-rigging and models without bid-rigging. We elicit from industry experts a prior distribution over markups across auctions. This induces a prior distribution over structural cost parameters. We then use Bayes Theorem to compute posterior probabilities for several non-nested models of industry equilibrium. In many settings, we believe that it is useful to formally incorporate the a prior beliefs of industry experts into estimation, especially in small samples where asymptotic approximations may be unreliable. We apply our methodology to a data set of bidding by construction firms in the Midwest. The techniques we propose are not computationally demanding, use flexible functional forms and can be programmed using most standard statistical packages. Working Papers Index
|Date of creation:||May 2001|
|Date of revision:|
|Contact details of provider:|| Postal: |
Web page: http://www-econ.stanford.edu/econ/workp/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:wop:stanec:01008. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Thomas Krichel)
If references are entirely missing, you can add them using this form.