Why do some people become entrepreneurs while others stay in paid employment? Searching for a distinctive set of entrepreneurial skills that matches the profile of the entrepreneurial task, Lazear introduced a theoretical model featuring skill variety for entrepreneurs. He argues that because entrepreneurs perform many different tasks, they should be multi-skilled in various areas. First, this dissertation provides the reader with an overview of previous relevant research results on skill variety with regard to entrepreneurship. The majority of the studies discussed focus on the effects of skill variety. Most studies come to the conclusion that skill variety mainly affects the decision to become self-employed. Skill variety also favors entrepreneurial intentions. Less clear are the results with regard to the influence of skill variety on the entrepreneurial success. Measured on the basis of income and survival of the company, a negative or U-shaped correlation is shown. Within the empirical part of this dissertation three research goals are tackled. First, this dissertation investigates whether a variety of early interests and activities in adolescence predicts subsequent variety in skills and knowledge. Second, the determinants of skill variety and variety of early interests and activities are investigated. Third, skill variety is tested as a mediator of the gender gap in entrepreneurial intentions. This dissertation employs structural equation modeling (SEM) using longitudinal data collected over ten years from Finnish secondary school students aged 16 to 26. As indicator for skill variety the number of functional areas in which the participant had prior educational or work experience is used. The results of the study suggest that a variety of early interests and activities lead to skill variety, which in turn leads to entrepreneurial intentions. Furthermore, the study shows that an early variety is predicted by openness and an entrepreneurial personality profile. Skill variety is also encouraged by an entrepreneurial personality profile. From a gender perspective, there is indeed a gap in entrepreneurial intentions. While a positive correlation has been found between the early variety of subjects and being female, there are negative correlations between the other two variables, education and work related Skill variety, and being female. The negative effect of work-related skill variety is the strongest. The results of this dissertation are relevant for research, politics, educational institutions and special entrepreneurship education programs. The results are also important for self-employed parents that plan the succession of the family business. Educational programs promoting entrepreneurship can be optimized on the basis of the results of this dissertation by making the transmission of a variety of skills a central goal. A focus on teenagers could also increase the success as well as a preselection based on the personality profile of the participants. Regarding the gender gap, state policies should aim to provide women with more incentives to acquire skill variety. For this purpose, education programs can be tailored specifically to women and self-employment can be presented as an attractive alternative to dependent employment.

Flexibility and spatial mobility of labour are central characteristics of modern societies which contribute not only to higher overall economic growth but also to a reduction of interregional employment disparities. For these reasons, there is the political will in many countries to expand labour market areas, resulting especially in an overall increase in commuting. The picture of the various, unintended long-term consequences of commuting on individuals is, however, relatively unclear. Therefore, in recent years, the journey to work has gained high attention especially in the study of health and well-being. Empirical analyses based on longitudinal as well as European data on how commuting may affect health and well-being are nevertheless rare. The principle aim of this thesis is, thus, to address this question with regard to Germany using data from the Socio-Economic Panel. Chapter 2 empirically investigates the causal impact of commuting on absence from work due to sickness-related reasons. Whereas an exogenous change in commuting distance does not affect the number of absence days of those individuals who commute short distances to work, it increases the number of absence days of those employees who commute middle (25 " 49 kilometres) or long distances (50 kilometres and more). Moreover, our results highlight that commuting may deteriorate an individual- health. However, this effect is not sufficient to explain the observed impact of commuting on absence from work. Chapter 3 explores the relationship between commuting distance and height-adjusted weight and sheds some light on the mechanisms through which commuting might affect individual body weight. We find no evidence that commuting leads to excess weight. Compensating health behaviour of commuters, especially healthy dietary habits, could explain the non-relationship of commuting and height-adjusted weight. In Chapter 4, a multivariate probit approach is used to estimate recursive systems of equations for commuting and health-related behaviours. Controlling for potential endogeneity of commuting, the results show that long distance commutes significantly decrease the propensity to engage in health-related activities. Furthermore, unobservable individual heterogeneity can influence both the decision to commute and healthy lifestyle choices. Chapter 5 investigates the relationship between commuting and several cognitive and affective components of subjective well-being. The results suggest that commuting is related to lower levels of satisfaction with family life and leisure time which can largely be ascribed to changes in daily time use patterns, influenced by the work commute.

This dissertation looked at both design-based and model-based estimation for rare and clustered populations using the idea of the ACS design. The ACS design (Thompson, 2012, p. 319) starts with an initial sample that is selected by a probability sampling method. If any of the selected units meets a pre-specified condition, its neighboring units are added to the sample and observed. If any of the added units meets the pre-specified condition, its neighboring units are further added to the sample and observed. The procedure continues until there are no more units that meet the pre-specified condition. In this dissertation, the pre-specified condition is the detection of at least one animal in a selected unit. In the design-based estimation, three estimators were proposed under three specific design setting. The first design was stratified strip ACS design that is suitable for aerial or ship surveys. This was a case study in estimating population totals of African elephants. In this case, units/quadrant were observed only once during an aerial survey. The Des Raj estimator (Raj, 1956) was modified to obtain an unbiased estimate of the population total. The design was evaluated using simulated data with different levels of rarity and clusteredness. The design was also evaluated on real data of African elephants that was obtained from an aerial census conducted in parts of Kenya and Tanzania in October (dry season) 2013. In this study, the order in which the samples were observed was maintained. Re-ordering the samples by making use of the Murthy's estimator (Murthy, 1957) can produce more efficient estimates. Hence a possible extension of this study. The computation cost resulting from the n! permutations in the Murthy's estimator however, needs to be put into consideration. The second setting was when there exists an auxiliary variable that is negatively correlated with the study variable. The Murthy's estimator (Murthy, 1964) was modified. Situations when the modified estimator is preferable was given both in theory and simulations using simulated and two real data sets. The study variable for the real data sets was the distribution and counts of oryx and wildbeest. This was obtained from an aerial census that was conducted in parts of Kenya and Tanzania in October (dry season) 2013. Temperature was the auxiliary variable for two study variables. Temperature data was obtained from R package raster. The modified estimator provided more efficient estimates with lower bias compared to the original Murthy's estimator (Murthy, 1964). The modified estimator was also more efficient compared to the modified HH and the modified HT estimators of (Thompson, 2012, p. 319). In this study, one auxiliary variable is considered. A fruitful area for future research would be to incorporate multi-auxiliary information at the estimation phase of an ACS design. This could, in principle, be done by using for instance a multivariate extension of the product estimator (Singh, 1967) or by using the generalized regression estimator (Särndal et al., 1992). The third case under design-based estimation, studied the conjoint use of the stopping rule (Gattone and Di Battista, 2011) and the use of the without replacement of clusters (Dryver and Thompson, 2007). Each of these two methods was proposed to reduce the sampling cost though the use of the stopping rule results in biased estimates. Despite this bias, the new estimator resulted in higher efficiency gain in comparison to the without replacement of cluster design. It was also more efficient compared to the stratified design which is known to reduce final sample size when networks are truncated at stratum boundaries. The above evaluation was based on simulated and real data. The real data was the distribution and counts of hartebeest, elephants and oryx obtained in the same census as above. The bias attributed by the stopping rule has not been evaluated analytically. This may not be direct since the truncated network formed depends on the initial unit sampled (Gattone et al., 2016a). This and the order of the bias however, deserves further investigation as it may help in understanding the effect of the increase in the initial sample size together with the population characteristics on the efficiency of the proposed estimator. Chapter four modeled data that was obtained using the stratified strip ACS (as described in sub-section (3.1)). This was an extension of the model of Rapley and Welsh (2008) by modeling data that was obtained from a different design, the introduction of an auxiliary variable and the use of the without replacement of clusters mechanism. Ideally, model-based estimation does not depend on the design or rather how the sample was obtained. This is however, not the case if the design is informative; such as the ACS design. In this case, the procedure that was used to obtain the sample was incorporated in the model. Both model-based and design-based simulations were conducted using artificial and real data. The study and the auxiliary variable for the real data was the distribution and counts of elephants collected during an aerial census in parts of Kenya and Tanzania in October (dry season) and April (wet season) 2013 respectively. Areas of possible future research include predicting the population total of African elephants in all parks in Kenya. This can be achieved in an economical and reliable way by using the theory of SAE. Chapter five compared the different proposed strategies using the elephant data. Again the study variable was the elephant data from October (dry season) 2013 and the auxiliary variable was the elephant data from April (wet season) 2013. The results show that the choice of particular strategy to use depends on the characteristic of the population under study and the level and the direction of the correlation between the study and the auxiliary variable (if present). One general area of the ACS design that is still behind, is the implementation of the design in the field especially on animal populations. This is partly attributed by the challenges associated with the field implementation, some of which were discussed in section 2.3. Green et al. (2010) however, provides new insights in undertaking the ACS design during an aerial survey such as how the aircraft should turn while surveying neighboring units. A key point throughout the dissertation is the reduction of cost during a survey which can be seen by the reduction in the number of units in the final sample (through the use of stopping rule, use of stratification and truncating networks at stratum boundaries) and ensuring that units are observed only once (by using the without replacement of cluster sampling technique). The cost of surveying an edge unit(s) is assumed to be low in which case the efficiency of the ACS design relative to the non-adaptive design is achieved (Thompson and Collins, 2002). This is however not the case in aerial surveys as the aircraft flies at constant speed and height (Norton-Griffiths, 1978). Hence the cost of surveying an edge unit is the same as the cost of surveying a unit that meets the condition of interest. The without replacement of cluster technique plays a greater role of reducing the cost of sampling in such surveys. Other key points that motivated the sections in the dissertation include gains in efficiency (in all sections) and practicability of the designs in the specific setting. Even though the dissertation focused on animal populations, the methods can as well be implemented in any population that is rare and clustered such as in the study of forestry, plants, pollution, minerals and so on.

Die korrekte Behandlung fehlender Daten in empirischen Untersuchungen spielt zunehmend eine wichtige Rolle in der anwendungsorientierten, quantitativen Forschung. Als zentrales flexibles Instrument wurde von Rubin (1987) die multiple Imputation entwickelt, welche unter regulären Bedingungen eine korrekte Inferenz der eigentlichen Schätzungen ermöglicht. Eine Reihe von Imputationsmethoden beruht im Wesentlichen auf der Normalverteilungsannahme. In der Empirie wird diese Annahme normalverteilter Daten zunehmend kritisiert. So erweisen sich Variablen auf Grund ihrer sehr schiefen Verteilungen für die Imputation als besonders problematisch. In dieser Arbeit steht die korrekte Behandlung fehlender Werte mit der Intention einer validen Inferenz der eigentlichen Schätzung im Vordergrund. Ein Instrument ist die Transformation schiefer Verteilungen, um mit Hilfe der transformierten und approximativ normalverteilten Daten Imputationen unter regulären Bedingungen durchzuführen. In der Arbeit wird ein multivariater Ansatz eingeführt. Anschließend wird im Rahmen mehrerer Monte-Carlo-Simulationsstudien gezeigt, dass der neue Ansatz bereits bekannte Verfahren dominiert und sich die Transformation positiv auf die Analyse mit imputierten Daten auswirkt.

Die vorliegende Meta-Analyse zeigt eindeutig, dass von Familienmitgliedern geführte Familienunternehmen eine schlechtere Performance aufweisen als Unternehmen, die von Managern geleitet werden, die der Inhaberfamilie nicht angehören. Basierend auf uni- und multivariaten Analysen von 270 wissenschaftlichen Publikationen aus 42 verschiedenen Ländern, wurde die Performance von Familienunternehmen im Vergleich zu Nicht-Familienunternehmen untersucht. Das erste robuste Ergebnis zeigt eindeutig, dass Familienunternehmen hinsichtlich der Performance Nicht-Familienunternehmen übertreffen. Dieses Ergebnis ist im Einklang mit den meisten Primärstudien und früheren Meta-Analysen. Das zweite Ergebnis dieser Arbeit kann dem "Finance"-Forschungszweig zugeordnet werden und basiert auf der Unterscheidung von Markt- und Accounting-Performance-Kennzahlen. Markt-Performance-Kennzahlen, welche durch Analysten errechnet werden, zeigen, dass Familienunternehmen Nicht-Familienunternehmen hinsichtlich der Performance unterlegen sind. Dieses Ergebnis steht im Gegensatz zu den Accounting-Performance-Kennzahlen, welche von den Familienunternehmen selbst in ihren von Wirtschaftsprüfern freigegebenen Bilanzen veröffentlicht wurden. Die dritte Forschungsfrage untersucht im Detail, ob die Zusammensetzung des Datensatzes in Primärstudien das Gesamtergebnis in eine bestimmte Richtung verzerrt. Das Ergebnis wird nicht durch Datensätzen mit Unternehmen, welche öffentlich gelistet, im produzieren Gewerbe tätig oder Technologie getriebene Unternehmen, sind getrieben. Kleine und Mittlere Unternehmen (KMU) veröffentlichen kleinere Kennzahlen und reduzieren somit die Höhe der abhängigen Variable. Das vierte Ergebnis gibt eine Übersicht über die Art und Weise der Beteiligung der Familie an der Aufsicht oder dem operativen Geschäft des Unternehmens. Dieses Ergebnis zeigt klar, dass Manager aus Familien einen signifikanten negativen Einfluss auf die Performance des Unternehmens haben. Dies kann auf die Erhaltung des Wohlstandes der Familienmitglieder zurückzuführen sein und somit spielen finanzielle Kennzahlen keine vordergründige Rolle. Die letzte Forschungsfrage untersucht, ob die Performance von Familienunternehmen im Vergleich zu Nicht-Familienunternehmen auch durch institutionelle Faktoren beeinflusst wird. In Europa zeigen die Familienunternehmen im Vergleich zu Nordamerika eine geringere Performance hinsichtlich der Kennzahlen. Das ist darauf zurückzuführen, dass europäische Unternehmen im Vergleich zu nordamerikanischen unterbewertet sind (Caldwell, 07.06.2014). Darüber hinaus zeigen Familienunternehmen im Vergleich zu Nicht-Familienunternehmen eine bessere Performance in eher maskulin geprägten Kulturen. Maskulinität, ist nach Hofstede, gekennzeichnet durch höhere Wettbewerbsorientierung, Selbstbewusstsein, Streben nach Wohlstand und klar differenzierte Geschlechterrollen. Rechtsregime hingegen (Common- oder Civil-Law) spielen im Performance-Zusammenhang von Familienunternehmen keine Rolle. Die Durchsetzbarkeit der Gesetze hat jedoch einen signifikanten positiven Einfluss auf die Performance von Familienunternehmen im Vergleich zu Nicht-Familienunternehmen. Dies ist damit zu begründen, dass die Kosten für Kredite in Länder mit einer sehr guten Durchsetzbarkeit von Gesetzen für Familienunternehmen geringer sind.