|
on Discrete Choice Models |
By: | Kurkalova, Lyubov; Rabotyagov, Sergey |
Abstract: | We propose an econometric technique for estimating the parameters of a binary choice model when only aggregated data are available on the choices made. The method performs favorably in applications to both simulated and real world choice data. |
Date: | 2005–01–24 |
URL: | http://d.repec.org/n?u=RePEc:isu:genres:12234&r=dcm |
By: | Ruth Hancock (University of Essex); Monica Hernandez (University of Birmingham); Stephen Pudney (Institute for Social and Economic Research) |
Abstract: | We estimate a discrete choice model of welfare participation by British pensioners who may have entitlements under multiple welfare programmes (Income Support, Housing Benefit and Council Tax Benefit). The model allows for imperfect information and subjective claim costs and is estimated using data from five years of the Family Resources Survey. We use the model to estimate the distribution of claim costs using the compensating variation principle and assess the impact of claim costs and information search costs on poverty measurement. |
Date: | 2004–12 |
URL: | http://d.repec.org/n?u=RePEc:ese:iserwp:2004-15&r=dcm |
By: | Maria A. Davia (Insitute for Social and Economic Research) |
Abstract: | The general aim of this research is to study transitions from education into the labour market among youths under a simultaneous framework. Using a sub-sample of youths from the European Community Household Panel, the empirical strategy has consisted of a trivariate probit estimation; initial conditions are controlled for. Results show that expectations about future labour market outcomes do not always contribute to explain youths decisions regarding education, other factors (i.e., current unemployment, family background and institutional factors) being more important. Moreover, there is a strong state dependency in educational choices and the relevant transitions from school into employment and job search are shown to be clearly interdependent |
Date: | 2004–10 |
URL: | http://d.repec.org/n?u=RePEc:ese:iserwp:2004-22&r=dcm |
By: | Stephen P. Jenkins (Institute for Social and Economic Research); Lorenzo Cappellari (Universita Cattolica di Milano); Annette Jäckle (Institute for Social and Economic Research); Emanuela Sala (Institute for Social and Economic Research) |
Abstract: | We analyse consent patterns and consent bias in the context of a large general household survey, the ‘Improving survey measurement of income and employment’ (ISMIE) survey, also addressing issues that arise when there are multiple consent questions. Using a multivariate probit regression model for four binary outcomes with two incidental truncations, we show that there are biases in consent to data linkage with benefit and tax credit administrative records held by the Department for Work and Pensions, and with wage and employment data held by employers, and also in respondents’ willingness and ability to supply their National Insurance Number. The biases differ according to the question considered, however. We also show that modelling consent questions independently rather than jointly may lead to misleading inferences about consent bias. A positive correlation between unobservable individual factors affecting consent to DWP record linkage and consent to employer record linkage is suggestive of a latent individual consent propensity. |
Date: | 2004–12 |
URL: | http://d.repec.org/n?u=RePEc:ese:iserwp:2004-27&r=dcm |
By: | Luis G. Gonzalez |
Abstract: | The Nash Bargaining problem in the context of a random utility model yields a stochastic demand for each player, conditional on his or her beliefs regarding the other player's behavior. We derive a symmetric logit equilibrium under naive expectations that converges to the Nash axiomatic solution as noise in utility vanishes. A numerical approximation to the symmetric logit equilibrium under rational expectations (Quantal Response Equilibrium) solution is also computed. |
Date: | 2005–01 |
URL: | http://d.repec.org/n?u=RePEc:esi:discus:2005-01&r=dcm |