Search

In this article, we suggest simple moment-based estimators to deal with unobserved heterogeneity in a special class of nonlinear regression models that includes as main particular cases exponential models for nonnegative responses and logit and complementary loglog models for fractional responses. The proposed estimators: (i) treat observed and omitted covariates in a similar manner; (ii) can deal with boundary outcomes; (iii) accommodate endogenous explanatory variables without requiring knowledge on the reduced form model, although such information may be easily incorporated in the estimation process; (iv) do not require distributional assumptions on the unobservables, a conditional mean assumption being enough for consistent estimation of the structural parameters; and (v) under the additional assumption that the dependence between observables and unobservables is restricted to the conditional mean, produce consistent estimators of partial effects conditional only on observables. [ABSTRACT FROM AUTHOR]

This paper analyses the effect of the implementation process of the Single Euro Payments Area (SEPA) project on credit transfer payments in euro area countries during the period between 2008 and 2013. Using both univariate and multivariate fractional regression models, we found that, when controlling for socio-demographic, economic, technological and institutional factors, the progress in the migration to SEPA formats had a relevant positive impact on the share of payments made with credit transfers. Our results provide for the first time empirical evidence of the direct effect of the implementation of SEPA on payment habits and set the basis for the discussion of some of the possible implications of payments digitalization from both economical and societal perspectives. [ABSTRACT FROM AUTHOR]

New fixed-effects estimators are proposed for logit and complementary loglog fractional regression models. The standard specifications of these models are transformed into a form of exponential regression with multiplicative individual effects and time-variant heterogeneity, from which four alternative estimators that do not require assumptions on the distribution of the unobservables are proposed. All new estimators are robust to both time-variant and time-invariant heterogeneity and can accommodate fractional responses with observations at the boundary value of zero. Additionally, some of these estimators can be applied to dynamic panel data models and can accommodate endogenous explanatory variables without requiring the specification of a reduced form model. A Monte Carlo study and an application to firm capital structure choices illustrate the usefulness of the suggested estimators. [ABSTRACT FROM AUTHOR]