Search

This article considers a semiparametric threshold regression model with two threshold variables. The proposed model allows endogenous threshold variables and endogenous slope regressors. Under the diminishing threshold effects framework, we derive consistency and asymptotic results of our proposed estimator for weakly dependent data. We study the finite sample performance of our proposed estimator via small Monte Carlo simulations and apply our model to classify economic growth regimes based on both national public debt and national external debt.

Using U.S. state-level data for the period 1973–1994, this study models the relationship between emissions, output and pollution abatement by defining an emissions function, in a manner that is consistent with the residual (emissions) generation mechanism and firms' optimizing behavior. It thus accounts for factors that were previously unaccounted for or addressed only individually. Applications using this comprehensive setting can offer more informed insights for policy-making, something that is particularly useful for developing countries that face the environmental degradation that comes together with the benefits of economic growth. Using nonparametric econometric techniques as well as threshold regression, the empirical results show that there is a positive nonlinear relationship between emissions and output, rejecting an inverted-U type of relationship between the two (the Environmental Kuznets Curve, or EKC). In the absence of abatement the relationship turns around, verifying the arguments in the literature that abatement is one of the driving forces for an EKC to emerge.

In this paper, we examine the convergence hypothesis using a long memory framework that allows for structural breaks and does not rely on a benchmark country using both univariate and multivariate estimates of the long memory parameter d. Using per capita GDP gaps, we confirm the findings of non-stationarity and long memory behavior that have been found previously in the literature using univariate tests. However, the support for these findings is much weaker when using a multivariate framework, in which case we find more evidence of stationary behavior. Based on these results, we also investigate club formation, something that would suggest the presence of conditional convergence. We describe a club formation methodology using the sequential testing criteria that we have employed in our analysis as the basis for forming clusters or clubs of countries with similar convergence characteristics.

We employ a structural threshold regression methodology to investigate the heterogeneous effects of debt on growth using public debt as a threshold variable as well as several other plausible variables. Our methodology allows us to address parameter heterogeneity that characterizes cross-country growth data and at the same time account for endogeneity. We find strong evidence for threshold effects based on democracy, which implies that higher public debt results in lower growth for countries in the Low-Democracy regime. Our results are consistent with the presence of parameter heterogeneity in the cross-country growth process due to fundamental determinants of economic growth proposed by the new growth theories. © 2013 Elsevier Inc. 38 35 43 35-43

The annual Eurovision Song Contest provides a setting where Europeans can express their sentiments about other countries without regard to political incentives. Analysing voting data from the 25 contests between 1981 and 2005, we find strong evidence for the existence of clusters of countries that systematically exchange votes regardless of the quality of their entries. Cultural, geographic, economic and political factors are significant determinants of point exchanges. Factors such as order of appearance, language and gender are also important. There is also a substantial host country effect. We find some evidence of reciprocity but no evidence of strategic voting.

We conduct an update of the ranking of economic journals by Kalaitzidakis, Mamuneas and Stengos (2003). However, our present study differs methodologically from that earlier study in an important dimension. We use a rolling window of years between 2003 and 2008, for each year counting the number of citations of articles published in the previous ten years. This allows us to obtain a smoother longer view of the evolution of rankings in the period under consideration and avoid the inherent randomness that may exist at any particular year. Using this framework we proceed to examine the relative ranking of the Canadian Journal of Economics over time. We find the Canadian Journal managed not only to maintain its relative position, but to also improve it over time.

In this paper we compare the impact of hardware, software, and communication equipment, widely referred to as information and communication technologies (ICT), on economic growth among the advanced industrialized countries. We use nonparametric techniques that allow us to estimate the output elasticities of ICT and human capital directly for each country and time period in our sample. Our results indicate that countries with high levels of ICT capital have high output elasticities of human capital. In addition, countries with high levels of human capital have high output elasticities of ICT, a result suggesting complementarity between the two. © Cambridge University Press 2010. 15 595 615 595-615

We propose a consumer demand system approach to estimating the size of the black economy where alternative hypotheses affecting the empirical results can be tested in a nested framework. This approach allows for the estimation of the under-reporting of household income from various sources, dispensing with the need to use arbitrary criteria to classify households by their main source of income. It also avoids potential bias in black economy estimates arising from mistaking preference heterogeneity (substitution) as income effects. We illustrate these arguments by estimating the extent to which self-employment income in the UK is underreported using parametric and nonparametric techniques. The black economy, broadly defined as the economic activities that are hidden from public authorities to avoid taxation, has recently received increased attention in the literature due to arguments that the rising tax burden and state regulation is driving economic activity underground (Tanzi and Schuknecht, 1997; Enste and Schneider, 1998). The usefulness of attempts to estimate the size of the black economy, however, is a controversial issue. The sceptics emphasise the difficulties associated with the precise definition of black economy activities and point to the widely different estimates of the size of these activities resulting from alternative methods (Dixon, 1999; Tanzi, 1999; Thomas, 1999). Authors approaching the subject in an optimistic frame of mind emphasise positive aspects of estimating the size of the black economy such as the correct measurement of GDP and other macroeconomic variables (e.g. employment) and the design of policy and econometric models (Bhattacharyya, 1999; Giles, 1999). The controversy on estimation issues, however, does not subtract from the widespread concern about the undesired consequences of the black economy. Undeclared economic activities reduce the tax base, thereby undermining the financing of public goods and social protection. A country trying to curtail the loss of tax revenue by raising tax rates can create a vicious cycle, as this reinforces the incentive not to declare economic activities to the public authorities. High tax rates have a distorting effect resulting in inefficient allocation of resources due to unequal opportunities and willingness to evade in different sectors of the economy and can undermine the ability of the country to compete internationally. Distortions in the labour market can also arise because individuals working in the black economy may have difficulty in moving from one job to another. Furthermore, in countries where health, pension and other social security payments are not universal, individuals working in the black economy and their families are outside the

An additive partially linear regression model is used to estimate non-parametrically the effects of total expenditure and age in the context of Engel curves and to investigate the specification and welfare interpretation of the age effects in parametric models of consumer behaviour. Empirical analysis based on data drawn from the U.K. Family Expenditure Survey shows that modelling of the effects of age requires a more sophisticated approach than that generally adopted in parametric demand analysis. It also shows that failing to adequately capture these effects can have misleading welfare implications. JEL Classification: C14, D12 L’effet de l’âge sur la demande des consommateurs : un modele de regression additif partiellement lineaire. On utilise un modele de regression additif partiellement lineaire pour faire la calibration non parametrique des effets de la depense totale et de l’âge dans le contexte de courbes de Engel, et pour enqueter sur la specification des effets d’âge et leur interpretation en termes de bien-etre dans des modeles parametriques de comportements du consommateur. L’analyse empirique est construite sur des donnees de la U.K. Family Expenditures Survey et montre que la modelisation des effets de l’âge reclame une approche plus sophistiquee que celle qui est generalement utilisee dans l’analyse parametrique de la demande. On montre aussi que le manque a bien saisir ces effets peut conduire a des conclusions fausses pour ce qui est du niveau de bien-etre.

We explore the forces that shape the development of aspirations and the achievement of grades during high school and the role that these aspirations, grades, and other variables play in educational outcomes such as going to university and graduating. We find that parental expectations and peer effects have a significant impact on educational outcomes through grades, aspirations, and their interconnectedness, an issue explained in the context of a rich, longitudinal data set. Apart from this indirect path, parents and peers also influence educational outcomes directly. Policy measures that operate on parental influences may modify educational outcomes in desired directions.

The pollution-convergence hypothesis is formalized in a neoclassical growth model with optimal emissions reduction: pollution growth rates are positively correlated with output growth (scale effect) but negatively correlated with emission levels (defensive effect). This dynamic law is empirically tested for two major and regulated air pollutants - nitrogen oxides (NOX) and sulfur oxides (SOX) - with a panel of 25 European countries spanning over years 1980-2005. Traditional parametric models are rejected by the data. However, more flexible regression techniques - semiparametric additive specifications and fully nonparametric regressions with discrete and continuous factors - confirm the existence of the predicted positive and defensive effects. By analyzing the spatial distributions of per capita emissions, we also show that cross-country pollution gaps have decreased over the period for both pollutants and within the Eastern as well as the Western European areas. A Markov modeling approach predicts further cross-country absolute convergence, in particular for SOX. The latter results hold in the presence of spatial non-convergence in per capita income levels within both regions.

This paper introduces the structural threshold regression (STR) model that allows for an endogenous threshold variable as well as for endogenous regressors. This model provides a parsimonious way of modeling nonlinearities and has many potential applications in economics and finance. Our framework can be viewed as a generalization of the simple threshold regression framework of Hansen (2000, Econometrica 68, 575–603) and Caner and Hansen (2004, Econometric Theory 20, 813–843) to allow for the endogeneity of the threshold variable and regime-specific heteroskedasticity. Our estimation of the threshold parameter is based on a two-stage concentrated least squares method that involves an inverse Mills ratio bias correction term in each regime. We derive its asymptotic distribution and propose a method to construct confidence intervals. We also provide inference for the slope parameters based on a generalized method of moments. Finally, we investigate the performance of the asymptotic approximations using a Monte Carlo simulation, which shows the applicability of the method in finite samples.

Using nonparametric estimation techniques we find that, in contrast to recent research, the finance-growth relationship is linear when the previously documented nonlinearity between initial per capital income, human capital and economic growth is taken into account. 15 1 12 1-12

The purpose of this paper is to examine the Information and Communication Technology (ICT) capital-economic growth nexus, taking into consideration the previously documented nonlinear relationship between initial income and human capital on the one hand and economic growth on the other. We apply nonparametric techniques for a number of OECD countries for the period 1980-2004. Specification tests provide evidence in favor of the semiparametric specification in which initial income, human capital and ICT capital enter nonlinearly. © 2007 Elsevier Inc. All rights reserved. 29 555 568 555-568

In this paper we study the relationship between human capital accumulation and economic growth using various measures of human capital frequently employed by researchers. We use semiparametric estimation techniques to uncover any nonlinearities that may exist. Using mean years of schooling measures of human capital we find a nonlinear effect on economic growth. There seem to be important differences in the growth effect of educational attainment by gender and level of education. Enrollment rates do not yield a nonlinear effect. 6 229 254 229-254

3 70 75 70-75

We propose a specification test of parametrically specified nonlinear model against a weakly specified non-nested alternative. We estiamte the alternative model by using nonparametric regression (nearest righbours). The test is based on the t-statistic of an artificial regression. Monte-Carlo simulations suggest that the test has good power and size characteristic. Publicado

We consider the non-nested testing prqblem of non-parametric regressions. We show that, when the regression functions are unknown under both the null and the alternative hypotheses, an extension of the J-test procedure of Davidson and Mackinnon (1981) will lead to a test statistic with well defined asymptotic properties. The derivation of the test statistic involves double kernel estimation. Monte Carlo simulations suggest that the test has good size and power characteristics.

We propose a specification test of a parametrically specified model against a weakly specified alternative. The latter is estimated using K nonparametric nearest neighbors (K-NN) in the context of an artificial regression. We derived the asymptotic distribution under the null hypothesis and under a series of local alternatives. Monte Carlo simulations suggest that the test is quite powerful although it has a tendency to over-reject under the null hypothesis.

The package performs estimation and prediction in the context of time-series or cross-section nonparametric models. It is menu-driven and very easy to operate. The manual reads well. This version has some limitations, which can easily be corrected. Nevertheless it provides a useful pedagogical and research tool, even for people not familiar with nonparametric analysis. Publicado

This article examines the effect of preference heterogeneity on nonparametric and parametric tests of the rank of demand systems. Using samples of households drawn from the U.K. Family Expenditure Survey, we find that preference heterogeneity increases the rank of demand systems. When the effects of household characteristics on demand are removed by semiparametric techniques, a rank-3 demand system appears to be an adequate empirical specification for all samples. © 1999 Taylor & Francis Group, LLC. 17 248 252 248-252

Cross sectional dependence may lead to inconsistent and inefficient estimators and as such misleading inferences when standard panel data techniques such as fixed/random effects are employed. Pesaran (2006) suggests incorporating cross sectional averages in panel data models as approximates of unobserved common factor(s) to deal with cross sectional dependence. In the context of a standard panel growth model we investigate whether these unobserved common factors can be identified and we find that institutional variables and life expectancy are able to adequately identify them. (C) 2018 Elsevier B.V. All rights reserved.