A Simple Derivation of r* for Curved Exponential Families

For curved exponential families we consider modified likelihood ratio statistics of the form r_L=r+ log( u/r)/r , where r is the signed root of the likelihood ratio statistic. We are testing a one-dimensional hypothesis, but in order to specify approximate ancillary statistics we consider the test as one in a series of tests. By requiring asymptotic independence and asymptotic normality of the test statistics in a large deviation region there is a particular choice of the statistic u which suggests itself. The derivation of this result is quite simple, only involving a standard saddlepoint approximation followed by a transformation. We give explicit formulas for the statistic u , and include a discussion of the case where some coordinates of the underlying variable are lattice.     

Paid Work and Unpaid Work: Diary Information Versus Questionnaire Information

Time-use information is preferably obtained from diaries, as this method is considered more reliable than information from questionnaires. Data from the Danish Time Use Survey 2001 thus indicate differences in the level of unpaid work, whereas only minor differences appear for paid work. That is: people reporting many hours of paid work tend to over-report the actual number of hours worked, while those reporting a small number of hours tend to underreport their contribution. For unpaid work, the same pattern appears. Moreover, men are found to be more unreliable than women in evaluating their amount of work on the labour market, while the opposite is the case for the unpaid/household work, with women underreporting their contribution more than men. The implication is that labour supplystudies based on questionnaire-information, i.e. Labour Force Surveys, are less accurate than studies based on diary-information.     

Managerial Risk‐taking in International Acquisitions in the Brewery Industry: Institutional and Ownership Influences Compared

This paper deals with the role that institutional differences play in managerial risk‐taking when firms engage in international acquisitions. It is assumed that multinational corporations (MNCs) have different interests and capabilities when dealing with international acquisition, which in the authors’ view are significantly shaped by specific home country institutional influences. This study concerns the question of how different forms of ownership – concentrated (e.g. family and bank based) and dispersed (stock market based) – influence risk‐taking and managerial decision‐making in large international acquisitions. Comparing a total of 12 large acquisitions of four leading MNCs in the global brewery industry, the paper shows that mutually reinforcing influences of country of origin (coordinated vs liberal market economies) and ownership (family ownership vs stock market ownership) lead to different risk profiles and managerial risk‐taking with regard to international acquisitions.     

Company Law and Corporate Governance of Start-ups in Germany: Legal Stipulations,Managerial Requirements,and Modification Strategies

Two topics which currently receivesubstantial interest are corporate governanceand start-up companies in the new economy.However, research combining both subjects israre. The present study aims to fill in thisgap because corporate governance is assumed toinfluence start-ups' performance. Sincepeculiarities of start-up companies exclude asimple application of extant governance wisdom,we develop propositions about corporategovernance structures of start-up companies inGermany – a country which has the most activestart-up scene in Europe but is also known forits far-reaching regulations of company law.This regulatory impact is most significantlyassociated with the choice of a legal form ofbusiness organization. While a certain legalform can provide some important advantages, itcan require at the same time corporategovernance structures which could imposeproblems on managing high-tech start-ups.Focussing the increasingly prevalent stockcorporation, we argue that this form, on theone hand, is advantageous for gaining resourcesand for the comprehensiveness of strategicdecision making. On the other hand, regulationsas the obligations to have collectiveresponsibilities in the management board and toset up a supervisory board can be expected todecelerate decision making and thus to putfirms at a disadvantage in high pacedindustries. We suggest that start-ups,therefore, make hidden modifications in orderto design effective corporate governanceconfigurations. The implementation of thesemodifications is facilitated by socialrelationships. First empirical insights intothe governance modalities of German start-upsare offered for illuminating our proposals.Thus, our study contributes to understandhow start-ups try to reconcile the governancedemands of both their business and their legalenvironment.     

Why do families actually pool their income? Evidence from Denmark

This paper analyzes income-pooling by using a unique Danish data set that includes questions on income pooling among 1,696 couples. The analyses show that most Danish households use some kind of income pooling and that the proportion of income pooled varies considerably according to individual characteristics (age, education, occupation, past partners, upbringing) and household characteristics (household income, duration of marriage, location of residence and the existence of public goods, including children). However, when all variables are evaluated in a common model, the duration of marriage and the existence of children predominantly affect the likelihood of income pooling.

Wer spielt Lotto?

On the basis of representative survey data, we examine the distribution effects state lotteries have on the social structure of Germany. Lotteries are highly taxed economic transactions whose proceeds make up a significant share of public fiscal revenues. Our analysis shows that lotteries are a form of regressive taxation. Further, taking the funding of amateur sports as an example, we show that earmarking lottery money increases the regressivity of this tax rather than reducing it. Using key demographic indicators such as levels of income, education, age and migration, we demonstrate the effects of fiscal redistribution. Based on these findings, we discuss implications of earmarking lottery revenues.     

Random projections for Bayesian regression

This article deals with random projections applied as a data reduction technique for Bayesian regression analysis. We show sufficient conditions under which the entire d-dimensional distribution is approximately preserved under random projections by reducing the number of data points from n to \(k\in O({\text {poly}}(d/\varepsilon ))\) in the case \(n\gg d\). Under mild assumptions, we prove that evaluating a Gaussian likelihood function based on the projected data instead of the original data yields a \((1+O(\varepsilon ))\)-approximation in terms of the \(\ell _2\) Wasserstein distance. Our main result shows that the posterior distribution of Bayesian linear regression is approximated up to a small error depending on only an \(\varepsilon \)-fraction of its defining parameters. This holds when using arbitrary Gaussian priors or the degenerate case of uniform distributions over \(\mathbb {R}^d\) for \(\beta \). Our empirical evaluations involve different simulated settings of Bayesian linear regression. Our experiments underline that the proposed method is able to recover the regression model up to small error while considerably reducing the total running time.     

Masturbation Experiences of Swedish Senior High School Students: Gender Differences and Similarities

Research about masturbation tends to be limited to the assessment of masturbation incidence and frequency. Consequently, little is known about what people experience connected to masturbation. This might be one reason why theoretical approaches that specifically address the persistent gender gap in masturbation frequency are lacking. The aim of the current study was to explore several aspects of masturbation in young men and women, and to examine possible associations with their social backgrounds and sexual histories. Data from 1,566 women and 1,452 men (ages 18 to 22) from 52 Swedish senior high schools were analyzed. Comparisons between men and women were made regarding incidence of and age at first masturbation, the use of objects (e.g., sex toys), fantasies, and sexual functioning during masturbation, as well as about their attitudes toward masturbation and sexual fantasies. Cluster analysis was carried out to identify similarities between and differences within the gender groups. While overall more men than women reported experience with several of the investigated aspects, cluster analyses revealed that a large proportion of men and women reported similar experiences and that fewer experiences are not necessarily associated with negative attitudes toward masturbation. Implications of these findings are discussed in consideration of particular social backgrounds.     

Konfliktmoderation mit Gruppen

One professional form of conflict resolution known as ‘mediation’ has itself established globally as an accepted alternative to litigation within the past four decades—albeit most notably for dyadic conflict between two individuals. Conflicts involving a higher number of parties both within and between social groups in organizations or public communities are far more complex and much tougher to be defined than in dyadic settings. They require an expanded repertoire of intervention techniques and more advanced competencies of neutrals as—in addition to the resolution efforts—the conflicting parties’ group dynamics demands attention and participative facilitation. Moreover, this type of conflict is difficult to study. An action strategy for professional group-based conflict resolution is exemplified and contrasted to dyadic mediation of conflict. Based on the analysis, problems for future research are outlined.