Search results

In this article we propose a multivariate dynamic probit model. Our model can be viewed as a nonlinear VAR model for the latent variables associated with correlated binary time-series data. To estimate it, we implement an exact maximum likelihood approach, hence providing a solution to the problem generally encountered in the formulation of multivariate probit models. Our framework allows us to study the predictive relationships among the binary processes under analysis. Finally, an empirical study of three financial crises is conducted.

The purpose of this paper is to analyze the differential impact each of the dominant theoretical explanations has on innovation persistence. The authors hereby differentiate the degree of novelty, distinguishing between innovation based on invention (new products for the international market) and those based on imitation or adoption processes (new products for the company or new products in the national market).

Placing this study in the context of a developing country, the authors apply an ordered probit model inflated in zeros (ZIOP). This methodology enables one to not only provide results not biased by the excess of zeros but also take into account the unobserved heterogeneity with respect to the sources of zeros (that is those firms which do not innovate). The empirical analysis is based on three Colombian innovation surveys carried out between 2003 and 2008 by the Colombian National Statistics Department.

The results provide empirical evidence that two elements are essential for both types of innovation persistence: accessing external financial resources and learning through interaction. Furthermore, the sunk R&D cost approach and technological learning explain persistence in innovation of new products for the international market.

The limitations of this study are directly related to the methodological choice. The authors were unable to take into consideration two sources of heterogeneity: the one related to initial conditions and the one related to the source of the many non-innovators. They opted to focus on the latter due the research question and setting of this study. Additionally, macroeconomic instability did not allow to consider a long panel; instead the authors had to rely on a short panel.

The results provide important insights to managers. Continuous investments in innovation activities are important bot to become an innovative firm as well as to improve the odds of persistently innovating. Particularly, R&D investments are a pre-requisite for new-to-the-world innovations. Finally, it is not one specific set of capabilities which is a prerequisite for the generation of innovation; rather it is a strategic combination of various skills that increase the probability to (persistently) innovate.

With innovation persistence being especially relevant for long-run dynamics behind economic growth, the results of this study provide insights into potential public policies. Governments are in a position to at least lower barriers, which might enable more firms to persistently innovate. Continuous access – less than the actual amount – to financial resources aimed at innovation activities and learning through interaction with external agents is fundamental for both kinds of innovation persistence. Both are market characteristics where governments can – at least indirectly – intervene.

Despite the existence of various theoretical approaches, the bulk of empirical research focuses on the verification of true state innovation persistence. Thus, while innovation persistency has been widely confirmed to exist to a certain degree, knowledge regarding which theoretical approach is likely to drive a firm to persistently innovation is still scarce. Additionally, this study is placed in the context of a developing country, which by most empirical research has been overlooked but is characterized by one element which is decisive for the empirical methodology: many firms do not innovate, let alone persistently innovate.

El objetivo de este artículo es analizar el impacto diferencial que cada una de las explicaciones teóricas dominantes tiene sobre la persistencia de la innovación. Para esto, diferenciamos el grado de novedad, distinguiendo entre la innovación basada en la invención (nuevos productos para el mercado internacional) y aquellas basadas en procesos de imitación o adopción (nuevos productos para el mercado nacional).

Este estudio se lleva a cabo en el contexto de un país en desarrollo, en el cual la mayoría de empresas no innovan. Consecuentemente, aplicamos un modelo probit ordenado inflado en ceros (ZIOP). Esta metodología no sólo proporciona resultados no sesgados por el exceso de ceros, sino que también tiene en cuenta la heterogeneidad no observada con respecto a las fuentes de ceros (es decir, aquellas empresas que no innovan). El análisis empírico se basa en tres Encuestas de Innovación en Colombia realizadas entre 2003 y 2008 por el Departamento Nacional de Estadísticas de Colombia.

Nuestros resultados proporcionan evidencia empírica de que tanto el enfoque de éxito genera éxito con el de capacidades son importantes. Sin embargo, se encontró que todas las variables que se desprenden de estos enfoques teóricos no están relacionadas en forma significativa con los dos tipos de persistencia estudiados. Además, el enfoque de costos hundidos de I + D se relaciona en forma robusta con la persistencia en la innovación de nuevos productos para el mercado internacional.

Las limitaciones de este estudio están directamente relacionadas con la elección metodológica. No pudimos tomar en consideración simultáneamente dos fuentes de heterogeneidad: la relacionada con las condiciones iniciales y la relacionada con el exceso de empresas no innovadoras. Optamos por centrarnos en lo último debido a la pregunta de investigación y el contexto país en el que se desarrolla esta investigación. Adicionalmente, la inestabilidad macroeconómica no permitió considerar un panel largo; por el contrario, se usó un panel corto que cubre un periodo de tiempo de estabilidad económica.

Nuestros resultados proporcionan información importante para los gerentes. Las inversiones continuas en actividades de innovación son importantes tanto para aumentar la probabilidad de convertirse en una empresa innovadora como para mejorar las posibilidades de innovación persistente. En particular, las inversiones en I + D son un requisito para lograr innovaciones nuevas en el mundo. Finalmente, no se identificaron un conjunto único de capacidades necesarias para la generación de cualquier tipo de innovación; más bien se debe adoptar un enfoque estratégico diferenciado.

Dado que la persistencia de la innovación es especialmente relevante para las dinámicas de crecimiento económico de largo plazo, los resultados de nuestro estudio proporcionan información útil para el diseño de políticas públicas. Los gobiernos están en posición de al menos reducir las barreras que impiden que las empresas innoven persistentemente. El acceso continuo a los recursos financieros destinados a actividades de innovación y el aprendizaje a través de la interacción con agentes externos son fundamentales para ambos tipos de persistencia de innovación. Ambas son condiciones del mercado que pueden ser intervenidas, al menos indirectamente, por el gobierno.

A pesar de la existencia de tres enfoques principales sobre la persistencia en la innovación, la mayor parte de las investigaciones se han centrado en la verificación de la existencia de verdadera persistencia en innovación. Por lo tanto, aunque se ha confirmado ampliamente que la persistencia de la innovación existe hasta cierto punto, el conocimiento sobre qué enfoque teórico es probable que impulse a una empresa a innovar de manera persistente es aún escaso. Además, este estudio se ubica en el contexto de un país en desarrollo, contexto que ha sido pasado por alto en la mayoría de las investigaciones empíricas, aspecto que decisivo para la selección de la metodología empírica: muchas empresas no innovan, y mucho menos innovan persistentemente.

O objetivo deste artigo é analisar o impacto diferencial que têm sobre a persistência da inovação cada uma das explicações teóricas dominantes. Para isso diferenciamos o grau de novidade, distinguindo entre inovação baseada em invenção (novos produtos para o mercado internacional) e aqueles baseados em processos de imitação ou adoção (novos produtos para o mercado nacional).

Esta pesquisa ocorre no contexto de um país em desenvolvimento, no qual a maioria das empresas não inovam. Assim sendo, temos aplicado o modelo Probit ordenado inflado-zero (ZIOP). Essa metodologia permite não só que os resultados da pesquisa não sejam influenciados por excesso de zeros, mas também a inclusão da heterogeneidade não observada em relação às fontes de zeros (isto é, aquelas empresas que não inovam). A análise empírica baseia-se em três pesquisas sobre Inovação na Colômbia realizadas entre 2003 e 2008 pelo Departamento Nacional de Estatísticas da Colômbia.

Nossos resultados fornecem evidências empíricas que indicam que tanto a abordagem de sucesso gera sucesso quanto a abordagem de capacidade é importante. No entanto, não se encontrou que todas as variáveis que emergiram dessas abordagens teóricas foram significativamente relacionadas aos dois tipos de persistência pesquisados. Além disso, a abordagem dos custos irrecuperáveis de P and D está relacionada de forma robusta à persistência na inovação de novos produtos para o mercado internacional.

As limitações desta pesquisa estão diretamente relacionadas à escolha metodológica. Não temos podido considerar duas fontes de heterogeneidade: a relacionada às condições iniciais e a relacionada ao excesso de empresas não inovadoras. Optou-se por centrar-se nesse último devido à questão de pesquisa e ao contexto do país em que foi realizada. Além disso, a instabilidade macroeconômica não permitiu um painel longo; pelo contrário, foi utilizado um painel curto que cobre um período de estabilidade econômica.

Nossos resultados provêem informação importante para os gerentes. Investimentos contínuos em atividades de inovação são importantes tanto para aumentar a probabilidade de se tornar numa empresa inovadora quanto para melhorar as possibilidades de inovação persistente. Em particular, os investimentos em P and D são um requisito para alcançar inovações no mundo. Finalmente, um conjunto único de capacidades necessárias para a geração de qualquer tipo de inovação não foi identificado; ao contrário, uma abordagem estratégica diferenciada deve ser adotada.

Dado que a persistência da inovação é especialmente relevante para as dinâmicas de longo prazo por trás do crescimento econômico, os resultados obtidos provêem informação útil para o desenho de políticas públicas. Os governos estão em posição de, pelo menos, reduzir as barreiras que impedem as empresas de inovar persistentemente. O acesso contínuo a recursos financeiros para atividades de inovação e a aprendizagem por meio da interação com agentes externos são fundamentais para os dois tipos de persistência de inovação. Ambas são condições do mercado que podem ser intervencionadas, pelo menos indiretamente, pelo governo.

Embora da existência de três abordagens principais sobre persistência na inovação, a maior parte das pesquisas concentraram-se em verificar a existência de verdadeira persistência na inovação. Portanto, ainda quando tem sido amplamente confirmado que a persistência da inovação existe até certo ponto, o conhecimento sobre qual abordagem teórico provavelmente alavanca uma empresa a inovar persistentemente ainda é escasso. Além disso, esta pesquisa está localizada num contexto de um país em desenvolvimento, que tem sido negligenciado na maioria das pesquisas empíricas, aspecto decisivo para a seleção da metodologia empírica: muitas empresas não inovam e muito menos inovam persistentemente.

The author proposes analyzing the dynamics of income positions using dynamic panel ordered probit models. The author disentangles, simultaneously, the roles of state dependence and heterogeneity (observed and non-observed) in explaining income position persistence, such as poverty persistence and affluence persistence. The author applies the approach to Chile exploiting longitudinal data from the P-CASEN 2006–2009. First, the author finds that income position mobility at the bottom and the top of the income distribution is much higher than expected, showing signs that income mobility in the case of Chile might be connected to economic insecurity. Second, the observable individual characteristics have a much stronger impact than true state dependence to explain individuals’ current income position in the income distribution extremes.

We analyse the dynamics of social assistance benefit (SA) receipt among working-age adults in Britain between 1991 and 2005. The decline in the annual SA receipt rate was driven by a decline in the SA entry rate rather than by the SA exit rate (which also declined). We examine the determinants of these trends using a multivariate dynamic random effects probit model of SA receipt probabilities applied to British Household Panel Survey data. We show how the model may be used to derive year-by-year predictions of aggregate SA entry, exit and receipt rates. The analysis highlights the importance of the decline in the unemployment rate over the period and other changes in the socio-economic environment including two reforms to the income maintenance system in the 1990s and also illustrates the effects of self-selection (‘creaming’) on observed and unobserved characteristics.

We propose a generic algorithm for numerically accurate likelihood evaluation of a broad class of spatial models characterized by a high-dimensional latent Gaussian process and non-Gaussian response variables. The class of models under consideration includes specifications for discrete choices, event counts and limited-dependent variables (truncation, censoring, and sample selection) among others. Our algorithm relies upon a novel implementation of efficient importance sampling (EIS) specifically designed to exploit typical sparsity of high-dimensional spatial precision (or covariance) matrices. It is numerically very accurate and computationally feasible even for very high-dimensional latent processes. Thus, maximum likelihood (ML) estimation of high-dimensional non-Gaussian spatial models, hitherto considered to be computationally prohibitive, becomes feasible. We illustrate our approach with ML estimation of a spatial probit for US presidential voting decisions and spatial count data models (Poisson and Negbin) for firm location choices.

This study aims to examine whether a switching decision between a family CEO and a non-family professional CEO has a different effect on firm performance and what determines such a decision by family firms.

This study uses multiple regressions, Probit and univariate analyses, based the sample of family-controlled Chaebol firms in Korea for the 11-year period from 2001 to 2011.

Evidence found was consistent with the family entrenchment hypothesis: firms experiencing declining Q value are more likely to replace family CEOs with non-family CEOs, and that these firms, having switched to non-family CEOs, exhibit an improvement in firm performance as measured by the change in Q value. On the other hand, for those firms that replace non-family CEOs with family member CEOs, no evidence was found that the switching decision either decreases or increases firm performance. The results of Probit and univariate analyses suggest that firms switching to family CEOs tend to be larger, stock-exchange listed and more “central”, with more cash flow rights held by the controlling families and with relatively more equity holdings in the other affiliated firms of the same Chaebol group. In contrast, firms switching to non-family CEOs tend to be smaller, unlisted and less “central”, with less equity holdings in the other affiliated firms of the same Chaebol group.

This study sheds light on the different value implications and determinants of a decision between “family CEO” and “non-family CEO”.

I study state dependence in social assistance receipt in Germany using annual survey data from the German Socio-Economic Panel for the years 1995–2011. There is considerable observed state dependence, with an average persistence rate in benefits of 68 per cent comparing to an average entry rate of just above 3 per cent. To identify a possible structural component, I estimate a series of dynamic random-effects probit models that control for observed and unobserved heterogeneity and endogeneity of initial conditions. I find evidence of substantial structural state dependence in benefit receipt. Estimates suggest that benefit receipt one year ago is associated with an increase in the likelihood of benefit receipt today by a factor of 3.4. This corresponds to an average partial effect of 13 percentage points. Average predicted entry and persistence rates and the absolute level of structural state dependence are higher in Eastern Germany than in Western Germany. I find only little evidence for time variation in state dependence around the years of the Hartz reforms.

A semiparametric stochastic frontier model is proposed for panel data, incorporating several flexible features. First, a constant elasticity of substitution (CES) production frontier is considered without log-transformation to prevent induced non-negligible estimation bias. Second, the model flexibility is improved via semiparameterization, where the technology is an unknown function of a set of environment variables. The technology function accounts for latent heterogeneity across individual units, which can be freely correlated with inputs, environment variables, and/or inefficiency determinants. Furthermore, the technology function incorporates a single-index structure to circumvent the curse of dimensionality. Third, distributional assumptions are eschewed on both stochastic noise and inefficiency for model identification. Instead, only the conditional mean of the inefficiency is assumed, which depends on related determinants with a wide range of choice, via a positive parametric function. As a result, technical efficiency is constructed without relying on an assumed distribution on composite error. The model provides flexible structures on both the production frontier and inefficiency, thereby alleviating the risk of model misspecification in production and efficiency analysis. The estimator involves a series based nonlinear least squares estimation for the unknown parameters and a kernel based local estimation for the technology function. Promising finite-sample performance is demonstrated through simulations, and the model is applied to investigate productive efficiency among OECD countries from 1970–2019.

International empirical evidence suggests that immigrants have a significantly higher risk than their native counterparts of being on welfare due to their observed characteristics. Nevertheless, it remains unclear if immigrants are also more prone to take-up benefits, conditional on being eligible. The authors explicitly focus on this potential explanation for higher welfare take-up rates. Therefore, the purpose of this paper is to analyze the take-up of social assistance in Germany by immigrants and natives, conditional on being eligible, and hence focus on take-up behavior rather than on determinants of eligibility.

To simulate welfare entitlements, the authors employ a Tax-Transfer Microsimulation Model. It is a static microsimulation model that consists of a detailed implementation of the German tax and transfer system as well as an econometrically estimated labor supply model. After the simulation of welfare entitlements, the authors analyze take-up behavior within a discrete choice framework. The authors estimate probit models of observed welfare benefit take-up for the sample of eligible households taking into account unobserved heterogeneity.

The estimation results do not reveal a significant effect of being a migrant on the probability of taking-up entitlements. The authors found a significant negative effect for citizens from European countries on the take-up probability, which disappeared after controlling for unobserved heterogeneity.

The authors find that it is worthwhile to focus on different groups of immigrants. Although not statistically significant, the rates of non-take-up of welfare benefits differ between different immigrant groups. The analysis further shows that controlling for unobserved heterogeneity is important when analyzing welfare differences between immigrants and natives.

The higher welfare rates of immigrants are explained mainly by their higher risk of welfare dependence. Thus, given that reducing the welfare dependence of immigrants is a political goal, social policy measures to improve welfare recipients’ labor market prospects are contested. However, restricting eligibility rules to reduce entitlements does not seem to be the appropriate measure, because the take-up probability does not differ between immigrants and natives after controlling for individual characteristics.

The authors build on Castronova et al. (2001) and analyze the take-up behavior of individuals who are entitled to basic means-tested welfare benefits for employable persons in Germany. The analysis differs from Castronova et al. (2001) in four points. First, the authors provide first evidence of immigrant-native differences in welfare benefit take-up under the new welfare system in Germany after its reorganization in 2005. Second, the authors apply a microsimulation model of the comlete tax and transfer system in Germany to determine welfare eligibility. Third, the authors extend the analysis to a panel framework and take into account individual unobserved heterogeneity. Fourth, the authors distinguish between different groups of immigrants.

This paper formulates and analyzes Bayesian model variants for the analysis of systems of spatial panel data with binary-dependent variables. The paper focuses on cases where latent variables of cross-sectional units in an equation of the system contemporaneously depend on the values of the same and, eventually, other latent variables of other cross-sectional units. Moreover, the paper discusses cases where time-invariant effects are exogenous versus endogenous. Such models may have numerous applications in industrial economics, public economics, or international economics. The paper illustrates that the performance of Bayesian estimation methods for such models is supportive of their use with even relatively small panel data sets.