|
on Discrete Choice Models |
| By: | Richard Williams (Dept of Sociology, University of Notre Dame) |
| Abstract: | When a binary or ordinal regression model incorrectly assumes that error variances are the same for all cases, the standard errors are wrong and (unlike OLS regression) the parameter estimates are biased. Heterogeneous choice/ location-scale models explicitly specify the determinants of heteroskedasticity in an attempt to correct for it. These models are also useful when the variability of underlying attitudes is itself of substantive interest. This paper illustrates how Williams’ user-written routine oglm (Ordinal Generalized Linear Models) can be used to estimate heterogeneous choice and related models. It further shows how two other models that have appeared in the literature – Allison’s (1999) model for comparing logit and probit coefficients across groups, and Hauser and Andrew’s (2006) logistic response model with partial proportionality constraints (LRPPC) – are special cases of the heterogenous choice model and/or algebraically equivalent to it, and can also be estimated with oglm. Other key features of oglm that are illustrated include support for linear constraints, the use of prefix commands such as svy and stepwise, and the computation of predicted probabilities and marginal effects. |
| Date: | 2007–10–31 |
| URL: | http://d.repec.org/n?u=RePEc:boc:wsug07:3&r=dcm |
| By: | Anat Bracha; Donald J Brown |
| Date: | 2007–11–15 |
| URL: | http://d.repec.org/n?u=RePEc:cla:levrem:122247000000001676&r=dcm |
| By: | Rinaldo Brau; Antonello E. Scorcu; Laura Vici |
| Abstract: | In this paper we assess the appeal of potential interventions on the tourism offer of Rimini, a popular Italian seaside holiday destination, by means of a choice modelling analysis. Tourism can be viewed as a composite good, its overall utility depending on the arrangement of the component characteristics. Our discrete choice experiments incorporate as attributes a number of possible changes to current tourist activities (the subject of public debate), including them in hypothetical alternative holiday packages. The conditional logit analysis indicates that tourists show lesser preference for interventions aimed at protecting the environmental integrity of the beach and greater preference for those, such as the creation of a pedestrianised seafront with late-night opening of amenities and facilities, that are likely to diminish the role of the traditional sea, sun and sand component of the overall holiday experience. |
| Keywords: | Destination planning; Tourism demand, Stated preference methods |
| JEL: | L83 C25 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:cns:cnscwp:200709&r=dcm |
| By: | Broberg, Thomas (Department of Economics, Umeå University) |
| Abstract: | This paper focuses on three important issues in estimating the relationship between WTP and income using contingent valuation: 1) the choice of income measure; 2) the modelling choice; and 3) the social context. Addressing the first two issues, a sensitivity analysis is performed. The results show that the estimated income-elasticity of WTP is fairly sensitive to different income measures and modelling assumptions and varies between 0.07 and 0.49 for the specific models estimated. The main conclusion drawn from the analysis is that inclusion of control variables for household characteristics is important for finding a significant income-effect, when the household income measure is used. No significant difference is found between gross or net income. The results further indicate that the relevant income measure may not only be the income level per se, but also the income level relative to others. The latter result is based on an experimental valuation question, conditioning the respondents on hypothetical changes in their absolute and relative income. The conclusion is that the social context read into the valuation situation influences the responses and, therefore, the estimated welfare measure. |
| Keywords: | contingent valuation; income-effect; income-elasticity of WTP; income measure; social context; relative income; multiple bounded; payment card. |
| JEL: | C81 Q20 Q26 Q28 |
| Date: | 2007–11–16 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:umnees:0723&r=dcm |
| By: | Martin Kahanec (IZA); Mariapia Mendola (University of Milan Bicocca) |
| Abstract: | The labor market outcomes of ethnic minorities in advanced societies and their dependence on social relationships and membership in social networks are important empirical issues with significant policy consequences. We use detailed micro-data on multiple-origin ethnic minorities in England and Wales and a discrete choice model to investigate these issues. We find that the core family structure and contacts with parents and children away (in Britain) increases the probability of self-employment. On the other hand, engagement in organizational social networks is more likely to channel the same people into paid employment. Finally, disaggregating different types of social networks along their compositional characteristics, we find that having ethnic friends is positively associated with the likelihood to be self-employed while integration in mixed or non-ethnic social networks facilitates paid employment among minority individuals. These findings hint at a positive role of social integration on employment opportunities of ethnic communities in host societies. |
| Keywords: | labor market, self-employment, ethnic minorities, social ties |
| JEL: | J7 J15 J21 |
| Date: | 2007–11 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp3146&r=dcm |
| By: | John D. Hey; Andrea Morone; Ulrich Schmidt |
| Abstract: | In the context of eliciting preferences for decision making under risk, we ask the question: “which might be the ‘best’ method for eliciting such preferences?”. It is well known that different methods differ in terms of the bias in the elicitation; it is rather less well-known that different methods differ in terms of their noisiness. The optimal trade-off depends upon the relative magnitudes of these two effects. We examine four different elicitation mechanisms (pairwise choice, willingness-to-pay, willingness-to-accept, and certainty equivalents) and estimate both effects. Our results suggest that economists might be better advised to use what appears to be a relatively inefficient elicitation technique (i.e. pairwise choice) in order to avoid the bias in better-known and more widely-used techniques. |
| Keywords: | pairwise choice, WTP, WTA, errors, noise, biases |
| JEL: | C91 C81 |
| Date: | 2007–11 |
| URL: | http://d.repec.org/n?u=RePEc:kie:kieliw:1386&r=dcm |
| By: | George R. Parsons (Graduate College of Marine Studies and Department of Economics,University of Delaware); Steven M. Thur (NOAA Office of Response and Restoration) |
| Abstract: | We estimated the economic value of changes in the quality of a coral reef ecosystem to SCUBA divers in the Caribbean using a stated preference mail survey. Our sampling frame was all divers with U.S. home addresses who purchased a tag required for diving in the Bonaire National Marine Park in 2001. Divers were asked how they might have altered their trip choice had the quality of the coral reef system been different from what they experienced. From these responses we inferred the value of three different levels of quality defined by visibility, species diversity, and percent coral cover. We used random utility theory and mixed logit to analyze the choice questions. Our sample size was 211, and our survey response rate is 75%. For modest changes in quality we estimate per person annual losses at $45. For larger losses the value is $192. |
| Keywords: | coral reef, marine protected area, non-market valuation |
| URL: | http://d.repec.org/n?u=RePEc:dlw:wpaper:07-18.&r=dcm |