Testing for intercept‐scale switch in linear autoregression

Autoregressive models with switching regime are a frequently used class of nonlinear time series models, which are popular in finance, engineering, and other fields. We consider linear switching autoregressions in which the intercept and variance possibly switch simultaneously, while the autoregressive parameters are structural and hence the same in all states, and we propose quasi‐likelihood‐based tests for a regime switch in this class of models. Our motivation is from financial time series, where one expects states with high volatility and low mean together with states with low volatility and higher mean. We investigate the performance of our tests in a simulation study, and give an application to a series of IBM monthly stock returns. The Canadian Journal of Statistics 40: 427–446; 2012 © 2012 Statistical Society of Canada     

The transition to tertiary education and parental background over time

We analyze the role of parental background for transitions to tertiary education in Germany and answer three questions: (a) does the relevance of parental background shift from short-term (contemporary income) to long factors (ability, parental education) at higher levels of education? (b) Did the impact of parental background on participation in tertiary education change over time? (c) Are there different patterns by sex and region? Parental income significantly affects transitions to tertiary education. Its impact seems to have lost magnitude over time. We find no clear differences by sex and larger parental income effects in West than in East Germany.     

Partnerwahl als konsensuelle Entscheidung

This study continues our analyses of contacting behavior in online dating (KZfSS 2/2009). As the beginning and continuation of a relationship is based on consensual decisions of both partners to interact, we concentrate on the question if and how potential partners indeed reply to contact offers. Data from online dating platforms therefore offer a unique opportunity for sociologists to study how partnerships are initiated and how they develop over time. This contribution provides four important empirical results: Firstly, it demonstrates that only 20% of all first contact offers are answered. This is a surprisingly small proportion. Secondly, it supports the hypothesis of homophily. According to this hypothesis, people with similar education, age and physical attractiveness should prefer each other and thus are more likely to form couples. Third, it shows that women still have severe problems to reply to contact offers from lower educated men, while men are already less reluctant to reply to higher educated women. Thus, the rarity of couples where women are higher educated than their partners are to a large proportion the consequence of women’s preferences rather than men’s preferences. Finally, our study does not find any support for the trade-off hypothesis, indicating that women do not exchange their physical attractiveness for men’s educational resources, and vice versa.     

Informed sub-sampling MCMC: approximate Bayesian inference for large datasets

Statistics and Computing - This paper introduces a framework for speeding up Bayesian inference conducted in presence of large datasets. We design a Markov chain whose transition kernel uses an...     

Anxiety,Depression and Emotion Regulation Among Regular Online Poker Players

Poker is a type of gambling that has specific features, including the need to regulate one’s emotion to be successful. The aim of the present study is to assess emotion regulation, anxiety and depression in a sample of regular poker players, and to compare the results of problem and non-problem gamblers. 416 regular online poker players completed online questionnaires including sociodemographic data, measures of problem gambling (CPGI), anxiety and depression (HAD scale), and emotion regulation (ERQ). The CPGI was used to divide participants into four groups according to the intensity of their gambling practice (non-problem, low risk, moderate risk and problem gamblers). Anxiety and depression were significantly higher among severe-problem gamblers than among the other groups. Both significantly predicted problem gambling. On the other hand, there was no difference between groups in emotion regulation (cognitive reappraisal and expressive suppression), which was linked neither to problem gambling nor to anxiety and depression (except for cognitive reappraisal, which was significantly correlated to anxiety). Our results underline the links between anxiety, depression and problem gambling among poker players. If emotion regulation is involved in problem gambling among poker players, as strongly suggested by data from the literature, the emotion regulation strategies we assessed (cognitive reappraisal and expressive suppression) may not be those involved. Further studies are thus needed to investigate the involvement of other emotion regulation strategies.     

A multiperiod auto-carrier transportation problem with probabilistic future demands

In this paper we study the problem of delivering finished vehicles from a logistics yard to dealer locations at which they are sold. The requests for cars arrive dynamically and are not announced in advance to the logistics provider who is granted a certain time-span until which a delivery has to be fulfilled. In a real-world setting, the underlying network is relatively stable in time, since it is usually a rare event that a new dealership opens or an existing one terminates its service. Therefore, probabilities for incoming requests can be derived from historical data. The study explores the potential of using such probabilities to improve the day-to-day decision of sending out or postponing cars that are ready for delivery. Apart from the order selection, we elaborate a heuristic to optimize delivery routes for the selected vehicles, whereby special loading constraints are considered to meet the particular constraints of car transportation via road. In a case study, we illustrate the value of introducing probabilistic information to the planning process and compare the quality of different configurations of our approach.     

The impact of corporate governance on auditor choice: evidence from Germany

Statutory audits are only beneficial if the appropriate audit quality is both provided and perceived by the users of audited financial statements. On the one hand, Big 4 audit firms are commonly viewed as producing high quality audits. On the other hand, regulators complain about the high market share of Big 4 audit firms. In this context, it is of interest to examine the drivers of a Big 4 audit firm selection. Despite extensive prior research, there is still a lack of findings form Continental European countries and on the impact of corporate governance on auditor choice. This paper on hand is intended to fill the related research gap. Thus, our study identifies variables that determine the auditor choice of large German listed companies. Based on a sample of 432 firm-year observations for the period 2010–2014, our logistic regression analysis suggests that the corporate governance structure influences auditor choice significantly. Notably, the annual meeting frequency of the audit committee and the size of the supervisory board are positively associated with the engagement of a Big 4 audit firm. However, the meeting frequency of the supervisory board and the compliance to the German corporate governance code are negatively related to the choice of a Big 4 auditor. Additionally, the proportion of female supervisory board members does not exert a significant impact. The results remain stable when the DAX30 observations, for which statutory audits are exclusively performed by Big 4 audit firms, are excluded. The main contribution of our paper is, that it sheds light on the impact of corporate governance variables not analyzed by prior research, like supervisory board characteristics, deviations from a corporate governance code, or the female quota, in a Continental European setting, and that it mainly indicates a complementary relationship. Despite the peculiarities of the German setting, the two-tier corporate governance system and the low level of investor protection, the findings of our study are not only relevant for Germany, since many other Continental European countries are characterized by a similar environment. The study’s findings are of particular interest for regulators when addressing audit market structure problems.