tailieunhanh - Train_Discrete Choice Methods with Simulation - Chapter 11

11 Individual-Level Parameters Introduction Mixed logit and probit models allow random coefficients whose distribution in the population is estimated. Consider, for example, the model in Chapter 6, of anglers’ choice among fishing sites. | P1 GEM IKJ P2 GEM IKJ QC GEM ABE T1 GEM August 20 2002 14 13 Char Count 0 CB495-11Drv CB495 Train KEYBOARDED 11 Individual-Level Parameters Introduction Mixed logit and probit models allow random coefficients whose distribution in the population is estimated. Consider for example the model in Chapter 6 of anglers choice among fishing sites. The sites are differentiated on the basis of whether campgrounds are available at the site. Some anglers like having campgrounds at the fishing sites since they can use the grounds for overnight stays. Other anglers dislike the crowds and noise that are associated with campgrounds and prefer fishing at more isolated spots. To capture these differences in tastes a mixed logit model was specified that included random coefficients for the campground variable and other site attributes. The distribution of coefficients in the population was estimated. Figure gives the estimated distribution of the campground coefficient. The distribution was specified to be normal. The mean was estimated as and the standard deviation was estimated as . This distribution provides useful information about the population. For example the estimates imply that 47 percent of the population dislike having campgrounds at their fishing sites while the other 53 percent like having them. The question arises where in the distribution of tastes does a particular angler lie Is there a way to determine whether a given person tends to like or dislike having campgrounds at fishing sites A person s choices reveal something about his tastes which the researcher can in principle discover. If the researcher observes that a particular angler consistently chooses sites without campgrounds even when the cost of driving to these sites is higher then the researcher can reasonably infer that this angler dislikes campgrounds. There is a precise way for performing this type of inference given by Revelt and Train 2000 . We explain the procedure in the context