Contributions published at Statistics and Empirical Economic Research (Rainer Winkelmann)

This thesis sheds empirical light on three research questions which belong to the realm of applied labor economics: What is the effect of early retirement on retirees’ mortality? How does an employment quota affect firms’ demand for disabled workers? And why are fluctuations in workplace accidents pro-cyclical? Chapter 2 shows that, for some groups of workers, early retirement increases the probability of premature death. Moreover, the driving force seems to be changed in health-related behavior, such as excessive alcohol consumption and smoking. The results in chapter 3 suggest that an employment quota is favorable to firms’ demand for disabled workers. In addition, chapter 4 finds that a rise in the tax, to which firms that do not comply with the employment quota are subject, also boosts this demand. Chapter 5 provides evidence that the pro-cyclicality of workplace accidents is governed by workers’ reporting behavior. Zusammenfassung Diese Dissertation untersucht empirisch drei Forschungsfragen, welche in das Gebiet der angewandten Arbeitsmarktökonomik fallen: Was ist der Effekt von Frühpension auf die Sterblichkeit von Rentnern? Inwiefern beeinflusst eine Quotenregelung die Nachfrage von Firmen nach Menschen mit Behinderung? Und warum sind Fluktuationen in der Rate von Arbeitsunfällen prozyklisch? Kapitel 2 zeigt auf, dass Frühpension bei gewissen Individuen die Wahrscheinlichkeit eines frühzeitigen Todes erhöht. Darüber hinaus wird gezeigt, dass die Ursache dafür in gesundheitsbezogenen Verhaltensänderungen liegt, wie z.B. exzessiver Alkoholkonsum und Rauchen. Die Resultate in Kapitel 3 deuten darauf hin, dass eine Quotenregelung sich günstig auf die Nachfrage von Firmen nach behinderten Arbeitnehmern auswirkt. Weiter zeigt Kapitel 4, dass eine Erhöhung der Ausgleichstaxe im Zusammenhang mit einer Quotenregelung ebenfalls die Nachfrage von Firmen nach Menschen mit Behinderung steigert. Kapitel 5 zeigt Evidenz dafür, dass die Prozyklizität von Arbeitsunfällen durch das Meldeverhalten von Arbeitern bestimmt wird.

Recent work by Anderson and van Wincoop (2003) establishes an empirical modeling strategy which takes full account of the structural, non-(log-)linear impact of trade barriers on trade in new trade theory models. Structural new trade theory models have never been used to evaluate and quantify the role of endogenous preferential trade agreement (PTA) membership for trade in a way which is consistent with general equilibrium. Apart from this gap, the present paper aims at delivering an empirical model which takes into account both that preferential trade agreement membership is endogenous and that the world matrix of bilateral trade flows contains numerous zero entries. These features are treated in an encompassing way by means of (possibly two-part) Poisson pseudo-maximum likelihood estimation with endogenous binary indicator variables in the empirical model.

This paper studies the effect of income rank on satisfaction. We hypothesize that a person's satisfaction depends on a comparison of own rank and rank of one's parents. Estimates using data from the German Socio-Economic Panel support the relative rank hypothesis.

Recent work by Anderson and van Wincoop (2003) establishes an empirical modeling strategy which takes full account of the structural, non-(log-)linear impact of trade barriers on trade in new trade theory models. Structural new trade theory models have never been used to evaluate and quantify the role of endogenous preferential trade agreement (PTA) membership for trade in a way which is consistent with general equilibrium. Apart from this gap, the present paper aims at delivering an empirical model which takes into account both that preferential trade agreement membership is endogenous and that the world matrix of bilateral trade flows contains numerous zero entries. These features are treated in an encompassing way by means of (possibly two-part) Poisson pseudo-maximum likelihood estimation with endogenous binary indicator variables in the empirical model.

The paper provides estimates of the effect of economic inequality on middle class well being in Switzerland. Economic well being is proxied by a person's satisfaction with his/her income. Two inequality indicators are used, one standard (the Gini coefficient of the pre-tax income distribution) and one novel (the number of luxury car registrations per 1000 population). Identification is through cross-sectional variation of these indicators at various levels of spatial aggregation. Results using data from the Swiss Household Panel confirm the existence of a robust inverse relationship between inequality and satisfaction among the middle class.

In this paper, we empirically evaluate competing approaches for combining inflation density forecasts in terms of Kullback–Leibler divergence. In particular, we apply a similar suite of models to four different datasets and aim at identifying combination methods that perform well throughout different series and variations of the model suite. We pool individual densities using linear and logarithmic combination methods. The suite consists of linear forecasting models with moving estimation windows to account for structural change. We find that combining densities is a much better strategy than selecting a particular model ex ante. While combinations do not always perform better than the best individual model, combinations always yield accurate forecasts and, as we show analytically, provide insurance against selecting inappropriate models. Logarithmic combinations can be advantageous, in particular if symmetric densities are preferred.

In this paper, we empirically evaluate competing approaches for combining inflation density forecasts in terms of Kullback–Leibler divergence. In particular, we apply a similar suite of models to four different datasets and aim at identifying combination methods that perform well throughout different series and variations of the model suite. We pool individual densities using linear and logarithmic combination methods. The suite consists of linear forecasting models with moving estimation windows to account for structural change. We find that combining densities is a much better strategy than selecting a particular model ex ante. While combinations do not always perform better than the best individual model, combinations always yield accurate forecasts and, as we show analytically, provide insurance against selecting inappropriate models. Logarithmic combinations can be advantageous, in particular if symmetric densities are preferred.

We discuss a class of copula-based ordered probit models with endogenous switching. Such models can be useful for the analysis of self-selection in subjective well-being equations in general, and job satisfaction in particular, where assignment of regressors may be endogenous rather than random, resulting from individual maximization of well-being. In an application to public and private sector job satisfaction, and using data on male workers from the German Socio-Economic Panel for 2004, and using two alternative copula functions for dependence, we find consistent evidence for endogenous sector selection.

Increasing evidence from the empirical economic and psychological literature suggests that positive and negative well-being are more than opposite ends of the same phenomenon. Two separate measures of the dependent variable may therefore be needed when analyzing the determinants of subjective well-being. We investigate asymmetries in the effect of income on subjective well-being with a single-item measure of general life satisfaction. Using data from the German Socio-Economic Panel 1984–2004, and a flexible multiple-index ordered probit panel data model with varying thresholds, we find that income has only a minor effect on high satisfaction but significantly reduces dissatisfaction.

This study investigates the prevalence and extent of altruism by examining the relationship between parents’ and their adult children’s subjective well-being in a data set extracted from the German Socio-Economic Panel. To segregate the share of parents with altruistic preferences from those who are selfish, we estimate a finite mixture regression model. We control for various sources of potential bias by taking advantage of the data’s panel structure. To validate our modeling approach, we show that predicted altruists indeed make higher average transfer payments.

This article investigates power and size of some tests for exogeneity of a binary explanatory variable in count models by conducting extensive Monte Carlo simulations. The tests under consideration are Hausman contrast tests as well as univariate Wald tests, including a new test of notably easy implementation. Performance of the tests is explored under misspecification of the underlying model and under different conditions regarding the instruments. The results indicate that often the tests that are simpler to estimate outperform tests that are more demanding. This is especially the case for the new test.

The bivariate probit model is frequently used for estimating the effect of an endogenous binary regressor on a binary outcome variable. This paper discusses simple modifications that maintain the probit assumption for the marginal distributions while introducing non-normal dependence among the two variables using copulas. Simulation results and evidence from two applications, one on the effect of insurance status on ambulatory expenditure and one on the effect of completing high school on subsequent unemployment, show that these modified bivariate probit models work well in practice, and that they provide a viable and simple alternative to the standard bivariate probit approach.

It has been shown in past research that unemployment has a large negative impact on subjective well-being of individuals. In this paper, I explore whether and to what extent people with more social capital are sheltered from the harmful effects of unemployment. Using data from the German Socio-Economic Panel 1984–2004, I find that social capital is an important predictor of well-being levels, but there is no evidence that it moderates the effect of unemployment on well-being. Possible reasons for these findings are discussed, and suggestions for future research given.

Can long-run identified structural vector autoregressions (SVARs) discriminate between competing models in practice? Several authors have suggested SVARs fail partly because they are finite-order approximations to infinite-order processes. We estimate vector autoregressive moving average (VARMA) and state space models, which are not misspecified, using simulated data and compare true with estimated impulse responses of hours worked to a technology shock. We find few gains from using VARMA models. However, state space algorithms can outperform SVARs. In particular, the CCA subspace method consistently yields lower mean squared errors, although even these estimates remain too imprecise for reliable inference. The qualitative differences for algorithms based on different representations are small. The comparison with estimation methods without specification error suggests that the main problem is not one of working with a VAR approximation. The properties of the processes used in the literature make identification via long-run restrictions difficult for any method.

The book provides a simple, intuitive introduction to regression models for qualitative and discrete dependent variables, to sample selection models, and to event history models, all in the context of maximum likelihood estimation. It presents a wide range of commonly used models. The book thereby enables the reader to become a critical consumer of current empirical social science research and to conduct own empirical analyses. The book includes numerous examples, illustrations, and exercises. It can be used as a textbook for an advanced undergraduate, a Master`s or a first-year Ph.D. course in microdata analysis, and as a reference for practitioners and researchers.

This paper investigates the relationship between income satisfaction of adult children and their relative economic status, using data from the German Socio-Economic Panel and income rank as an indicator of status. The results show that children appear to compare their actual economic status with that of their parents, deriving large satisfaction gains from an income rank that is higher than that of their parents. The effect is asymmetric with regard to parents, as these seem not to be ifluenced by their children's income rank.

Economics rests upon a set of presumptions about how human beings are affected by income. Yet causal evidence is scant. This paper reports a longitudinal study of randomly selected lottery winners. Remarkably, we show that it takes almost three years before they enjoy their money. We develop a model of dissonance and deservingness. We argue that, despite the tradition of economics, human beings may weight differently the different kinds of income that accrue to them. If so, it is not sufficient to describe utility by a function u(y), and it is not true that ‘a dollar is a dollar’.

Previous studies in positive psychology have indicated that work satisfaction is an important determinant of individual well-being. Research has suggested that people are most satisfied with their work when they are doing what they are drawn to naturally. We provide further evidence on this issue from a large representative data set, the German Socio-Economic Panel (SOEP). The 2005 wave of the SOEP contains a battery of personality questions as well as detailed information on personal life and work life. We extract the Big Five personality factors and one character strength: vitality. The main results are based on regression analysis. The analysis supports the hypothesis that certain personality clusters are more predominant in some occupations than in others. Furthermore, an alignment between personal profile and occupational profile tends to be related positively to satisfaction. These results indicate that ignoring mental aspects of work has its price in terms of well-being. They also highlight the importance of studying the way we structure work and harness personality and individual strengths within positive psychology.

This study investigates the prevalence and extent of altruism by examining the relationship between parents' and their adult children's subjective well-being in a data set extracted from the German Socio-Economic Panel. In order to segregate the share of parents with altruistic preferences from those who are selfish, we estimate a finite mixture regression model. We control for various sources of potential bias by taking advantage of the data's panel structure. To validate our modeling approach we show that predicted altruists indeed make higher average transfer payments.