|
on Discrete Choice Models |
| By: | William J. McCausland; A.A.J. Marley |
| Abstract: | We complete the development of a testing ground for axioms of discrete stochastic choice. Our contribution here is to develop new posterior simulation methods for Bayesian inference, suitable for a class of prior distributions introduced by McCausland and Marley (2013). These prior distributions are joint distributions over various choice distributions over choice sets of different sizes. Since choice distributions over different choice sets can be mutually dependent, previous methods relying on conjugate prior distributions do not apply. We demonstrate by analyzing data from a previously reported experiment and report evidence for and against various axioms. |
| Keywords: | Random utility, discrete choice, Bayesian inference, MCMC |
| JEL: | C11 C35 C53 D01 |
| Date: | 2013 |
| URL: | http://d.repec.org/n?u=RePEc:mtl:montec:07-2013&r=dcm |
| By: | Rohlfs, Chris (Morgan Stanley); Sullivan, Ryan (Naval Postgraduate School); Kniesner, Thomas J. (Syracuse University) |
| Abstract: | This paper develops a generalized hedonic model in which an exogenous shock to a single product attribute can affect other attributes, the markets for the product's complements and substitutes, and aggregate quantity produced. These factors are shown to be empirically relevant and to cause bias in traditional approaches. Experimental and quasi-experimental estimators of attribute demand are introduced that address these biases, are transparent, and are straightforward to implement. One of these estimators is applied to measure the marginal military recruit's valuation of educational benefits, which is found to range across packages from -$0.024 to +$0.467 per dollar of benefits. |
| Keywords: | hedonic, discrete choice, identification, experiment, quasi-experiment, marginal willingness to pay, attribute demand, amenity, heterogeneous goods, generalized, endogenous attributes, complement, substitute |
| JEL: | D12 C35 C31 D61 C9 |
| Date: | 2013–08 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp7554&r=dcm |
| By: | Kessels, Roselinde; Jones, Bradley; Goos, Peter |
| Abstract: | Using maximum likelihood estimation for discrete choice modeling of small datasets causes two problems. The rst problem is that the data often exhibit separation, in which case the maximum likelihood estimates do not exist. Also, provided they exist, the maximum likelihood estimates are biased. In this paper, we show how to adapt Firth's bias-adjustment method for use in discrete choice modeling. This approach removes the rst-order bias of the estimates, and it also deals with the separation issue. An additional advantage of the bias adjustment is that it is usually accompanied by a reduction in the variance. Using a large-scale simulation study, we identify the situations where Firth's bias-adjustment method is most useful in avoiding the problem of separation as well as removing the bias and reducing the variance. As a special case, we apply the bias-adjustment approach to discrete choice data from individuals, making it possible to construct an empirical distribution of the respondents' preferences without imposing any a priori population distribution. For both research purposes, we base our ndings on data from a stated choice study on various forms of employee compensation. |
| Date: | 2013–08 |
| URL: | http://d.repec.org/n?u=RePEc:ant:wpaper:2013013&r=dcm |