Bayesian games

As has been noted in other reviews, Operations Management has been slow to adopt GT. But because SCM is an ideal candidate for GT applications, we have recently witnessed an explosion of GT papers in SCM. As our survey indicates, most of these papers utilize only a few GT concepts, in particular the concepts related to non-cooperative static games. Some attention has been given to stochastic games but several other important areas need additional work cooperative, repeated, differential, signaling, screening and Bayesian games. 

As companies are rational and driven by profit maximization, it will be in their best interest to underestimate their level of risk to increase then-benefit. This behavior causes uncertainty about the payoffs of the game and information asymmetry between NDA and SLC s (Neuman Morgenstern 1944). Under these circumstances, a Bayesian game is induced where each company has some beliefs about the level of risk hold by the other companies by assigning a continuous probability distribution over the interval of the level of risk. This distribution is common knowledge. In this paper, we assume that the companies interval type is the same for both companies (low levels of risk high levels of risk 0). Each type profile induces a state of the game with different payoffs. Table 1. 

Bayesian procedures are important not only for estimating parameters and states, but also for decision making in various fields. Chapters 6 and 7 include applications to model discrimination and design of experiments further applications appear in Appendix C. The theorem also gives useful guidance in economic planning and in games of chance (Meeden, 1981). 

Harsanyi, J. C. (1967). Games with incomplete information played by Bayesian players. I. The basic model. Management ScL, 14 159-182. 

Companies will choose a strategy that maximizes their expected payoff in each state of the game. The solution to this game is a Bayesian Nash Equilibrium. 

By, the end of period 1, retailer i has observed his first-period sales x, and thus possesses a piece of private information. We consider two models that differ in the way that the private information is handled. We start with a Bayesian Updating (BU) model, described as a three-stage game ... 

Denote by G2 the subgame starting with the secondary market, and G the three-stage game given above. A Bayesian Updating (BU) equilibrium of the... 

---