Working papers

Estimation and testing of self-reporting heterogeneity in self-assessed health questions (with Emmanouil Mentzakis)

Abstract: We propose a new methodology for statistically testing for reporting heterogeneity in self-assessed health (SAH) questions. We contribute to the literature by: i) quantifying the effect of such heterogeneity in the probability distribution of SAH responses, ii) providing a correction to that distribution that allows us to obtain an unbiased distribution of SAH responses as a function of true health, iii) measuring the marginal effect of individuals’ characteristics on the probability distribution of SAH responses under self-reporting heterogeneity. Our econometric approach extends the typical ordered probit formulation found in the literature for describing SAH responses by incorporating a consistent estimate of individuals’ true health. True health is estimated as a latent variable from a database with information on an array of individuals’ objective health binary indicators. This additional equation relating unobserved true health and observable health characteristics allows us to disentangle the effect of true health and self-reporting heterogeneity on SAH responses. We show that each effect is consistently estimated under joint and two-stage maximum likelihood estimation procedures. The proposed methodology is applied to a cross-section from the Understanding Society dataset. We find strong evidence of self-reporting heterogeneity of different degrees depending on age and employment status. Failing to control for such heterogeneity masks the good health of individuals and exaggerates the occurrence of bad health states, while over(under)-states true health gradient of covariates.

Paying or being paid to be Green (with Rupali Vashisht and Hector Calvo-Pardo)

Abstract: After decades of debate about the nature of the relationship between corporate environmental performance (EP) and corporate financial performance (FP), this relationship stands ambiguous. In this study, firms in the S&P 500 index are divided into brown (heavily polluting) and green (less polluting) sectors to investigate separately the EP-FP relationship for each. Competing techniques namely, Generalised Simultaneous Equation Modeling (GSEM) & 3-Stage Least Squares (3SLS) have been employed to estimate the model and alternate measures of profitability have been used to validate the findings. The crucial conclusion of this analysis points out that the impact of contemporaneous FP on EP is positive and significant for brown firms i.e. more profitable brown firms invest more in enhancing their environmental performance. This is the only effect that remains stable across various model specifications, different techniques, and alternate measures of profitability.