|
on Discrete Choice Models |
By: | Yingying Dong (California State University, Irvine); Arthur Lewbel (Boston College); Thomas Tao Yang (Boston College) |
Abstract: | We discuss the relative advantages and disadvantages of four types of convenient estimators of binary choice models when regressors may be endogenous or mismeasured, or when errors are likely to be heteroskedastic. For example, such models arise when treatment is not randomly assigned and outcomes are binary. The estimators we compare are the two stage least squares linear probability model, maximum likelihood estimation, control function estimators, and special regressor methods. We specifically focus on models and associated estimators that are easy to implement. Also, for calculating choice probabilities and regressor marginal effects, we propose the average index function (AIF), which, unlike the average structural function (ASF), is always easy to estimate. |
Keywords: | Binary choice, Binomial Response, Endogeneity, Measurement Error, Heteroskedasticity, discrete endogenous, censored, random coefficients, Identification, Latent Variable Model. |
JEL: | C25 C26 |
Date: | 2012–02–15 |
URL: | http://d.repec.org/n?u=RePEc:boc:bocoec:789&r=dcm |
By: | M. Du Preez; M.C. Sale |
Abstract: | This paper presents an application of the conditional logit model to a small, Nelson Mandela Bay neighbourhood housing data set, with the objective of determining the impact of proximity to a low-cost housing development on nearby property prices. The results of this pilot study show that the average household in the neighbourhood of Walmer is willing to pay between R27 262 and R195 564 to be located 86m further away from an existing low—cost housing development. In addition to this, the probability of choosing a specific house increases if the house has a swimming pool, an electric fence, the lower its price and the closer it is to the nearest school. |
Date: | 2012 |
URL: | http://d.repec.org/n?u=RePEc:rza:wpaper:265&r=dcm |
By: | Barla, Philippe; Lapierre, Nathanael; Alvarez Daziano, Ricardo; Herrmann, Markus |
Abstract: | In this paper, we evaluate the potential impacts of travel demand management strategies to reduce the commuting mode share of automobiles using stated preference data. The analysis is carried out on members of Université Laval in Quebec City (Canada). We measure the impact of travel time and cost as well as attitudes toward automobile, public transit and the environment. We find elasticities with respect to time and cost parameters that are low implying that large changes are required to have a noticeable impact. We find however that combining several policy interventions is more effective. Policies aiming at reducing automobile dependency by changing attitudes do not appear to be particularly effective. |
Keywords: | Mode choice, stated preferences, travel demand management, Community/Rural/Urban Development, Resource /Energy Economics and Policy, R41, R48, Q58, |
Date: | 2012–02 |
URL: | http://d.repec.org/n?u=RePEc:ags:ulavwp:121311&r=dcm |
By: | Christoph Kuzmics (Institute of Mathematical Economics, Bielefeld University) |
Abstract: | If a decision maker, in a world of uncertainty a la Anscombe and Aumann (1963), can choose acts according to some objective probability distribution (by throwing dice for instance) from any given set of acts, then there is no set of acts that allows an experimenter to test more than the Axiom of EUOL (that the DM evaluates objective lotteries with an expected utility function). In fact there is no (common) experimental design that allows an experimenter to test more than EUOL. For any decision problem (or set of decision problems), for any preference relation that satisfies the Axiom EUOL, and for any optimal choice (or collection of choices) given this preference relation, there is another preference relation that satisfies EUOL plus the Savage axioms, for which this choice is also optimal. |
Keywords: | ambiguity, decision theory, Knightian uncertainty, experiments |
JEL: | C72 C81 C90 D01 D03 D81 |
Date: | 2012–03 |
URL: | http://d.repec.org/n?u=RePEc:bie:wpaper:462&r=dcm |
By: | Hanming Fang; Edward Kung |
Abstract: | Previous research has shown that the reasons for lapsation have important implications regarding the effects of the emerging life settlement market on consumer welfare. We present and empirically implement a dynamic discrete choice model of life insurance decisions to assess the importance of various factors in explaining life insurance lapsations. In order to explain some key features in the data, our model incorporates serially correlated unobservable state variables which we deal with using posterior distributions of the unobservables simulated from Sequential Monte Carlo (SMC) method. We estimate the model using the life insurance holding information from the Health and Retirement Study (HRS) data. Counterfactual simulations using the estimates of our model suggest that a large fraction of life insurance lapsations are driven by i.i.d choice specific shocks, particularly when policyholders are relatively young. But as the remaining policyholders get older, the role of such i.i.d. shocks gets smaller, and more of their lapsations are driven either by income, health or bequest motive shocks. Income and health shocks are relatively more important than bequest motive shocks in explaining lapsations when policyholders are young, but as they age, the bequest motive shocks play a more important role. We also suggest the implications of these findings regarding the effects of the emerging life settlement market on consumer welfare. |
JEL: | G22 H31 L11 |
Date: | 2012–03 |
URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:17899&r=dcm |