|
on Discrete Choice Models |
| By: | Danny Campbell (Queen’s University Belfast); W. George Hutchinson (Queen’s University Belfast); Riccardo Scarpa (University of Waikato) |
| Abstract: | : Data from a discrete choice experiment on improvements of rural landscape attributes are used to investigate the implications of discontinuous preferences on willingness to pay estimates. Using a multinomial error component logit model, we explore differences in scale and unexplained variance between respondents with discontinuous and continuous preferences and condition taste intensities on whether or not each attribute was considered by the respondent during the evaluation of alternatives. Results suggest that significant improvements in model performance can be achieved when discontinuous preferences are accommodated in the econometric specification, and that the magnitude and robustness of the willingness to pay estimates are sensitive to discontinuous preferences. |
| Keywords: | discontinuous preferences; heteroskedastic mixed logit; discrete choice experiments; multinomial error component logit model; rural landscape; willingness to pay; |
| JEL: | C13 C15 C25 C99 Q26 |
| Date: | 2007–09–20 |
| URL: | http://d.repec.org/n?u=RePEc:wai:econwp:07/18&r=dcm |
| By: | Ricardo Scarpa (University of Waikato); Mara Thiene (University of Padua); Francesco Marangon (University of Udine) |
| Abstract: | This paper investigates preferences for various environment-friendly production systems using 1949 choices from a sample of 240 respondents that chose amongst different types of carrots. The and multi-attribute stated-preference data collection was based on an experimental designed tailored to identify interaction effects between production methods and place of origin we estimate the effect of collective reputations for growers of an Alpine valley known to be completely dedicated to organic production. The implied WTP distributions are positve for organic and integrated pest management and provide evidence of recognition of a collective reputation for environmentally friendly production methods. Marginal utility of income is found to be systematically linked to socio-economic covariates, while unobserved heterogeneity is found for organic and bio-dynamic production methods and for place of origin, but not for integrated pest management. WTP for organic produce from Val di Gresta is found to be around 1-2 euro/kg depending on budget constraints, and not statistically significant for bio-dynamic production. The study confirms the existence of the growers' reputation for EFPMs and provides an empirical estimate of the premium the market awards to such a reputation. |
| Keywords: | Collective reputation; mixed logit; random utility parameters; sustainable agriculture; Choice modeling; Organic methods |
| JEL: | C15 C25 Q26 |
| Date: | 2007–09–07 |
| URL: | http://d.repec.org/n?u=RePEc:wai:econwp:07/11&r=dcm |
| By: | Andrew M. Jones; Stefanie Schurer |
| Abstract: | Individual heterogeneity plays a key role in explaining variation in self-reported well-being and, in particular, health satisfaction. It is hypothesised that the inuence of this heterogeneity varies over levels of health and increases over the life-cycle. These hypotheses are tested with data on health satisfaction from 22 waves of the German Socioeconomic Panel (GSOEP). Nonlinear xed eects methods that allow for unobserved heterogeneity are not readily available for categorical measures of well-being. One common solution is to revert to conditional xed eects methods, at the price of a high degree of information loss. Another common solution is to ignore the association between unobserved heterogeneity and socio-economic status by using pooled or random eects models, at the price of potential bias. We use a generalization of the conditional xed eects logit, that allows for individual-specic reporting bias, heterogeneity in health endowments, and heterogeneity in the impact of income on health satisfaction. Adjusting for unobserved heterogeneity accounts for the relationship between income and very good health, but not between income and poorer health states. The income gradient for older age-groups is more strongly aected by controlling for unobserved heterogeneity: revealing an increasing inuence of heterogeneity on health satisfaction over the life-span. |
| Keywords: | Panel data, generalized conditional xed eects logit, generalized ordered logit, health, GSOEP. |
| JEL: | I12 C23 |
| Date: | 2007–04 |
| URL: | http://d.repec.org/n?u=RePEc:yor:hectdg:07/05&r=dcm |
| By: | Jose Apesteguia; Miguel A. Ballester |
| Abstract: | We study the complexity of rationalizing choice behavior. We do so by analyzing two polar cases, and a number of intermediate ones. In our most structured case, that is where choice behavior is defined in universal choice domains and satisfies the "weak axiom of revealed preference," finding the complete preorder rationalizing choice behavior is a simple matter. In the polar case, where no restriction whatsoever is imposed, either on choice behavior or on choice domain, finding the complete preorders that rationalize behavior turns out to be intractable. We show that the task of finding the rationalizing complete preorders is equivalent to a graph problem. This allows the search for existing algorithms in the graph theory literature, for the rationalization of choice. |
| Keywords: | Rationalization, Computational complexity, NP-complete, Arbitrary Choice Domains |
| JEL: | D00 |
| Date: | 2007–09 |
| URL: | http://d.repec.org/n?u=RePEc:upf:upfgen:1048&r=dcm |
| By: | Montero Minerva; Guerra Valia |
| Abstract: | Montero et al. (2002) proposed a strategy to formulate multilevel models related to a contingency table sample. This methodology is based on the application of the general linear model to hierarchical categorical data. In this paper we applied the method to a multilevel logistic regression model using simulated data. We find that the estimates of the random parameters are inadmissible in some circumstances; large bias and negative estimates of the variance are expected for unbalanced data sets. In order to correct the estimates we propose to use a numerical technique based on the Truncated Singular Value Decomposition (TSVD) in the solution of the problem of generalized least squares associated to the estimation of the random parameters. Finally a simulation study is presented to shows the effectiveness of this technique for reducing the bias of the estimates. |
| Date: | 2007–09–22 |
| URL: | http://d.repec.org/n?u=RePEc:col:000163:004065&r=dcm |
| By: | Anirban Basu; James J. Heckman; Salvador Navarro-Lozano; Sergio Urzua |
| Abstract: | Instrumental variables methods (IV) are widely used in the health economics literature to adjust for hidden selection biases in observational studies when estimating treatment effects. Less attention has been paid in the applied literature to the proper use of instrumental variables if treatment effects are heterogeneous across subjects and individuals select treatments based on expected idiosyncratic gains or losses from treatments. In this paper, we analyze the role of conventional instrumental variable analysis and alternative approaches using instrumental variables for estimating treatment effects for models with treatment heterogeneity and self-selection. Instead of interpreting IV estimates as the effect of treatment at an unknown margin of patients, we identify the marginal patients and we apply the method of local instrumental variables to estimate the Average Treatment Effect (ATE) and the Effect on the Treated (TT) on 5-year direct costs of breast conserving surgery and radiation therapy compared to mastectomy in breast cancer patients. We use a sample from the Outcomes and Preferences in Older Women, Nationwide Survey (OPTIONS) which is designed to be representative of all female Medicare beneficiaries (aged 67 or older) with newly diagnosed breast cancer between 1992 and 1994. Our results reveal some of the advantages and limitations of conventional and alternative IV methods in estimating mean treatment effect parameters. |
| Keywords: | Self-selection, essential heterogeneity, instrumental variables, breast cancer, local instrumental variable method. |
| JEL: | C01 C21 C31 |
| Date: | 2007–06 |
| URL: | http://d.repec.org/n?u=RePEc:yor:hectdg:07/07&r=dcm |
| By: | Cepeda Edilberto; Peláez José Manuel |
| Abstract: | This paper considers situations where regression models are proposed to model abilities on three parameter logistic models. After a summary of the classical approach to estimate the item parameters and the abilities, we provided an exposition of the maximum likelihood method to estimate the regression parameters. We analyze how good these estimations are, using a simulated study, and we include an application |
| Date: | 2007–09–22 |
| URL: | http://d.repec.org/n?u=RePEc:col:000163:004069&r=dcm |
| By: | Dimitra Petropoulou |
| Abstract: | This paper extends a well-established vertical product differentiation model to an international duopoly with two segmented countries, where firms compete in quality and price. The framework is used to analyse governments` incentives for unilateral minimum standard-setting as well as the scope and effects of cooperative agreements in minimum standards. Endogenous national standards result from a standard-setting game between governments whose objective function is to maximise national welfare. Cross-country externalities can be are either positive or negative, depending on the quality of traded goods. Four unregulated Nash equilibria in minimum standards are shown to exist, two symmetric and two asymmetric, which correspond to the four different combinations of externalities that may arise between the two countries: symmetric positive externalities, symmetric negative externalities, or asymmetric positive and negative externalities. Unilateral minimum standards can be inefficiently high or low relative to world optimum symmetric standards and operate as non-tariff barriers to trade. Harmonisation of minimum quality standards through cooperation is both feasible and mutually beneficial in the symmetric case, but the scope for mutually beneficial cooperation is significantly restricted when countries are asymmetric and lump-sum transfers are not possible. The resulting cooperative standards are asymmetric and do not maximise world welfare. |
| Keywords: | Vertical Product Differentiation, Quality Reversal, International Trade, Minimum Quality Standards |
| JEL: | F13 L13 L52 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:oxf:wpaper:352&r=dcm |
| By: | Ramb, Fred |
| Abstract: | This study is the first empirical analysis to investigate the relationship between the investment behaviour of firms resident in Germany and the empirically determined marginal tax rates developed by John R. Graham. It is based on the Bundesbank's corporate balance sheet statistics for the period 1971-2002. In an autoregressive distributed lag model, the marginal tax rate is shown to be significant, with an elasticity of between 0.1 and 0.2. An error correction model does not produce any plausible results for the marginal tax rate. Graham's marginal tax rates are a complement to the methods typically used to determine the effective marginal tax rates and effective average tax rates. |
| Keywords: | Corporate marginal tax rate, tax loss carryforward, investment behaviour |
| JEL: | D21 H25 |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:bubdp1:6142&r=dcm |
| By: | Ian Babetskii; Nauro F. Campos |
| Abstract: | Why are socially beneficial reforms not implemented? One simple answer to this question (which has received little attention in the literature) is that this may be caused by generalised uncertainty about the effectiveness of reforms. If agents are unsure about whether a proposed reform will work, it will be less likely to be adopted. Despite the numerous benefits economists assign to structural reforms, the empirical literature has thus far failed to establish a positive and significant effect of reforms on economic performance. We collect data from 43 econometric studies (for more than 300 coefficients on the effects of reform on growth) and show that approximately one third of these coefficients is positive and significant, another third is negative and significant, and the final third is not statistically significant different from zero. In trying to understand this remarkable variation, we find that the measurement of reform and controlling for institutions and initial conditions are main factors in decreasing the probability of reporting a significant and positive effect of reform on growth. |
| Keywords: | Meta-regression analysis, reform, growth. |
| JEL: | O11 P21 C49 |
| Date: | 2007–03 |
| URL: | http://d.repec.org/n?u=RePEc:cer:papers:wp322&r=dcm |