Suchergebnisse

Logit- und Probitregression werden als multivariate Analyseverfahren zur Analyse von dichotomen abhängigen Variablen in den Sozialwissenschaften routinemäßig eingesetzt. Beide Verfahren können so interpretiert werden, dass sich aus einer linearen Modellierung einer unbeobachteten Variabley* eine nichtlineare Modellierung der Wahrscheinlichkeiten füry = 1 ergibt. Wir zeigen erstens, dass diese Nichtlinearität im Vergleich zu linearen Regressionsverfahren zu Problemen bei der Interpretation der Modellergebnisse führt. Insbesondere die in der logistischen Regression häufig verwendeten odds ratios (exponierte Logit-Koeffizienten) sind unseres Erachtens problematisch. Stattdessen empfehlen wir neben graphischen Interpretationshilfen die Verwendung von (korrigierten) durchschnittlich marginalen Effekten (AME). Zweitens zeigen wir anhand einer Serie von Monte-Carlo-Simulationen, dass die üblichen Regressionskoeffizienten bei Logit- und Probitanalysen nicht zwischen verschachtelten Modellen verglichen werden können. Da in den Sozialwissenschaften bei der Modellbildung jedoch häufig schrittweise vorgegangen wird, wäre ein Verfahren, das einen validen Vergleich von Effektstärken zwischen den Modellen erlaubt, sehr nützlich. Wie wir anhand unserer Simulationsstudie zeigen, führen durchschnittlich marginale Effekte und Koeffizienten, die nach dem Vorschlag von Karlson et al. (Sociological Methodology 42, 2012) korrigiert wurden, in sehr verschiedenen Situationen zu gültigen Ergebnissen.y*-standardisierte Koeffizienten sind für einen Modellvergleich hingegen weniger geeignet und Koeffizienten eines linearen Wahrscheinlichkeitsmodells sollten ausschließlich bei normalverteilten Variablen verwendet werden.

Abstract This paper employs the random-effects negative binomial regression model (RENBM) to test the relationship between macroeconomic factors and the birth of new firms. The test is across countries and uses count data. We consider a sample of 135 panel-data observations, taken from 27 countries in the European Union (EU) during the period 2004 to 2008. We found that the birth of new firms is positively related to the growth of gross domestic product (GDP), inflation and openness, and is negatively related to unemployment. This result is in accordance with macroeconomic theory. The results also show that expenditure on research and development (R&D) has a significant positive effect on the number of new firms. This result further supports the hypothesis of new economic growth theory. Moreover, the empirical evidence shows a positive correlation between the number of new businesses and ethnic heterogeneity.

While there has been several job satisfaction studies, very few of them are about the university teachers or academics in general. The present work examines not only how satisfied UK academics are with their primary tasks of teaching and research, but also their satisfaction with their pay. Using a binomial logit analysis on a survey data, the study found a strong positive relationship between pay satisfaction and gender, indicating that women academics are more satisfied than the men counterparts. The study also found that research and teaching satisfaction are negatively affected with increasing age and length of service in higher education respectively. Unsurprisingly, research and pay satisfaction are positively associated with rank. It was found that the engineering staff members are dissatisfied with their research but more significantly, their teaching. The implications of these findings are explored.

Abstract
In this article, we develop a bankruptcy prediction model for Korean firms that utilize logit regression. We find that not only financial accounting ratios but equity market inputs and macro-economic variables are also important predictors of bankruptcy. However, unlike the findings of Campbell et al. (2008), using market value of equity in computing total assets did not improve the model. We compare the model with a Merton-type structural model and find that our model demonstrates a higher prediction power in distinguishing distressed firms from healthy firms. Though our model proves to perform better, we are careful to make a conclusion and rather suggest using several models for the purpose of risk management to reduce model risk.

The strategies expected to mitigate poverty tend to identify factors that are closely related to poverty and that could have influenced the policy implications. A household level data was collected to examine the poverty status and factors affecting poverty in Southern Punjab. A logistic regression technique was employed for the present analyses. The findings show that age and education of the household head, own house, spouse participation, remittances, number of earners in the household and physical assets reduces the probability of being poor in Southern Punjab. However, large household size, occupation in the primary sector, high dependency ratio and mental disability are associated with an increased probability of being poor in Southern Punjab. Government should adopt effective policy measures to generate employment and encourage the attainment of education for the poor households for the mitigation of poverty in this region.

Residential satisfaction is not only an important component of individuals' quality of life but also determines the way they respond to residential environment. An understanding of the factors that facilitate a satisfied or dissatisfied response can play a critical part in making successful housing policies. This study reinvestigates the effects of housing, neighborhood, and household characteristics on individuals' satisfaction with both dwelling and neighborhood, in order to reconcile the inconsistencies in the previous research. The empirical analysis uses data drawn from the American Housing Survey (AHS) and ordered logit models (OLM). OLM is more appropriate than the widely‐used regression technique in such analysis due to the ordinal nature of the dependent variables representing satisfaction. The results show that residential satisfaction is a complex construct, affected by a variety of environmental and socio‐demographic variables. While the actual effects of the variables by and large confirm earlier findings in the literature, significant differences between the results from the OLM and regression models were found. This indicates that regression models should be used with caution and their results accepted with a grain of salt.

The paper specifies a model of the first-past-the-post (FPTP) electoral system in which political parties themselves float independent candidates to gain electoral advantage, leading to a Prisoners' Dilemma type game where each party tries to out-maneuver one another. Imposing some intuitively appealing assumptions on this game, we show that the total number of independent candidates across constituencies would follow a Negative Binomial distribution. Empirical results for the 2004 parliamentary election in India reveal a good fit of the Negative Binomial model to data. Results also help to identify a few major determinants of the spatial distribution of independent candidates in India. Results point out that the number of independent candidates across constituencies in a State in India is strongly influenced by political fractionalization in that State, with metropolitan and urban constituencies on an average having more independent candidates. We also find that elite politicians and their family members, ceteris paribus, face more independent candidates. Finally, results establish that number of independent candidates is typically less in reserved constituencies due to reduced number of potential candidates. Our results suggest that FPTP electoral systems as in India need to put appropriate institutional constraints that increase transaction costs of electoral participation for independent candidates.

The paper specifies a model of the first-past-the-post (FPTP) electoral system in which political parties themselves float independent candidates to gain electoral advantage, leading to a Prisoners' Dilemma type game where each party tries to out-maneuver one another. Imposing some intuitively appealing assumptions on this game, we show that the total number of independent candidates across constituencies would follow a Negative Binomial distribution. Empirical results for the 2004 parliamentary election in India reveal a good fit of the Negative Binomial model to data. Results also help to identify a few major determinants of the spatial distribution of independent candidates in India. Results point out that the number of independent candidates across constituencies in a State in India is strongly influenced by political fractionalization in that State, with metropolitan and urban constituencies on an average having more independent candidates. We also find that elite politicians and their family members, ceteris paribus, face more independent candidates. Finally, results establish that number of independent candidates is typically less in reserved constituencies due to reduced number of potential candidates. Our results suggest that FPTP electoral systems as in India need to put appropriate institutional constraints that increase transaction costs of electoral participation for independent candidates.

This paper employs the random-effects negative binomial regression model (RENBM) to test the relationship between macroeconomic factors and the birth of new firms. The test is across countries and uses count data. We consider a sample of 135 panel-data observations, taken from 27 countries in the European Union (EU) during the period 2004 to 2008. We found that the birth of new firms is positively related to the growth of gross domestic product (GDP), inflation and openness, and is negatively related to unemployment. This result is in accordance with macroeconomic theory. The results also show that expenditure on research and development (R&D) has a significant positive effect on the number of new firms. This result further supports the hypothesis of new economic growth theory. Moreover, the empirical evidence shows a positive correlation between the number of new businesses and ethnic heterogeneity.