"ZHANG Yan" <[EMAIL PROTECTED]> wrote in avqvhr$ibkko$[EMAIL PROTECTED]:">news:avqvhr$ibkko$[EMAIL PROTECTED]:
> Hi, would you please give me an example for the following model > satisfying the following three requirement? > 1. the arrival process is correlated. is MMPP or (B)MAP process an > example? 2. the service process is correlated. I can not find one > example. 3. the arrival process and the arrival process are > correlated. > > Thanks and Regards. > -- > ZHANG Yan > > > How about the operation of a search-and-rescue service in the mountains (say, in a skiing area)? "Arrivals" are calls for help, "services" are rescue operations. The need for assistance is weather-related, so the conditional probability of bad weather is greater immediately after an arrival than in general; since bad weather triggers the need for aid, that implies that the likelihood of another arrival increases immediately after an arrival (correlated arrivals). Service time increases as weather deteriorates, so the probability of severe weather is greater after a long service than after a short one, and hence service times tend to be longer immediately after a long service (correlated service times). Finally, a burst of arrivals implies severe weather, which implies longer services, so arrival and service rates are correlated. The same logic might apply to an air-sea rescue service as well. -- Paul ************************************************************************* Paul A. Rubin Phone: (517) 432-3509 Department of Management Fax: (517) 432-1111 The Eli Broad Graduate School of Management E-mail: [EMAIL PROTECTED] Michigan State University http://www.msu.edu/~rubin/ East Lansing, MI 48824-1122 (USA) ************************************************************************* Mathematicians are like Frenchmen: whenever you say something to them, they translate it into their own language, and at once it is something entirely different. J. W. v. GOETHE . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
