|
on Discrete Choice Models |
| By: | Yingying Dong (Department of Economics, University of California-Irvine); Arthur Lewbel (Department of Economics, Boston College) |
| Abstract: | This paper provides simple estimators for binary choice models with endogenous or mismeasured regressors. Unlike control function methods, which are generally only valid when endogenous regressors are continuous, the estimators proposed here can be used with limited, censored, continuous, or discrete endogenous regressors, and they also allow for latent errors having heteroskedasticity of unknown form, including random coefficients. The variants of special regressor based estimators we provide are numerically trivial to implement. We illustrate these methods with an empirical application estimating migration probabilities within the US. |
| Keywords: | Binary choice; Binomial response; Endogeneity; Measurement error; Heteroskedasticity; Discrete endogenous regressor; Censored regressor; Random coefficients; Identification; Latent variable model |
| JEL: | C25 C26 |
| Date: | 2012–02 |
| URL: | http://d.repec.org/n?u=RePEc:irv:wpaper:111204&r=dcm |
| By: | Birol, Ekin; Asare-Marfo, Dorene; Karandikar,Bhushana; Roy, Devesh |
| Abstract: | This study explores farmer acceptance and valuation of a biofortified staple food crop in a developing country prior to its commercialization. We focus on the hypothetical introduction of a high-iron pearl millet variety in Maharashtra, India, where pearl millet is among the most important staple crops. A choice experiment is used to investigate farmer preferences for and trade-offs among various production and consumption attributes of pearl millet. The key pearl millet attributes studied included days it takes pearl millet to mature, color of the roti (flat bread) the grain produces, the presence of high-iron content (nutritional attribute), and the price of the pearl millet seed. Choice data come from 630 pearl millet-producing households randomly selected from 3 purposefully selected districts of Maharashtra. A latent class model is used to investigate the heterogeneity in farmers' preferences for pearl millet attributes and to profile farmers who are more or less likely to choose high-iron varieties of pearl millet. Our results reveal that there are three distinct segments in the sample, and there is significant heterogeneity in farmer preferences across these segments. High-iron pearl millet is valued the most by larger households that produce mainly for household consumption and currently have lower quality diets. Households that mainly produce for market sales, on the other hand, derive lower benefits from consumption characteristics such as color and nutrition. These results have implications for the design of targeted strategies to maximize adoption and consumption of high-iron pearl millet varieties. |
| Keywords: | Biofortification, Choice experiment, latent class model, preference heterogeneity, Pearl millet, |
| Date: | 2011 |
| URL: | http://d.repec.org/n?u=RePEc:fpr:harvwp:7&r=dcm |
| By: | Rong Zhang; Brett A. Inder; Xibin Zhang |
| Abstract: | We present a Bayesian sampling approach to parameter estimation in a discrete-response model with double rules of selectivity, where the dependent variables contain two layers of binary choices and one ordered response. Our investigation is motivated by an empirical study using such a double-selection rule for three labor-market outcomes, namely labor force participation, employment and occupational skill level. Full information maximum likelihood (FIML) estimation often encounters convergence problems in numerical optimization. The contribution of our investigation is to present a sampling algorithm through a new reparameterization strategy. We conduct Monte Carlo simulation studies and find that the numerical optimization of FIML fails for more than half of the simulated samples. Our Bayesian method performs as well as FIML for the simulated samples where FIML works. Moreover, for the simulated samples where FIML fails, Bayesian works as well as it does for the simulated samples where FIML works. We apply the proposed sampling algorithm to the double-selection model of labor-force participation, employment and occupational skill level. We derive the 95% Bayesian credible intervals for marginal effects of the explanatory variable on the three labor-force outcomes. In particular, the marginal effects of mental health factors on these three outcomes are discussed. |
| Keywords: | Bayesian sampling; conditional posterior; marginal effects; mental illness; reparameterization. |
| JEL: | C35 C11 |
| Date: | 2012–02 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2012-5&r=dcm |