The multiple filter test for change point detection in time series

A framework for the detection of change points in the expectation in sequences of random variables is presented. Specifically, we investigate time series with general distributional assumptions that may show an unknown number of change points in the expectation occurring on multiple time scales and that may also contain change points in other parameters. To that end we propose a multiple filter test (MFT) that tests the null hypothesis of constant expectation and, in case of rejection of the null hypothesis, an algorithm that estimates the change points.The MFT has three important benefits. First, it allows for general distributional assumptions in the underlying model, assuming piecewise sequences of i.i.d. random variables, where also relaxations with regard to identical distribution or independence are possible. Second, it uses a MOSUM type statistic and an asymptotic setting in which the MOSUM process converges weakly to a functional of a Brownian motion which is then used to simulate the rejection threshold of the statistical test. This approach enables a simultaneous application of multiple MOSUM processes which improves the detection of change points that occur on different time scales. Third, we also show that the method is practically robust against changes in other distributional parameters such as the variance or higher order moments which might occur with or even without a change in expectation. A function implementing the described test and change point estimation is available in the R package MFT.     

Dinge, die meine Eltern nicht sehen sollten

Every successful communication process requires a certain degree of self-disclosure. However, both in real life and on social network sites like Facebook, self-disclosure does not imply a total sacrifice of privacy. People rather tend to disclose one part of the self while keeping another one protected. In doing so, it is less important where the protective line is drawn, but that a line is drawn at all. This basic principle of conditional self-disclosure can be applied in diverse strategies. An online survey among German Facebook users (n = 684) examined this assumption. Items for a scale of subjective privacy regulation were derived from Burgoon’s four dimensions of privacy. Based on user’s varying emphasis on these privacy dimensions, seven different types of privacy management could be distinguished. Among these, six different strategies of conditional self-disclosure were observed (?chatty“, ?blogging“, ?networking“, ?sorting“, ?passive“, and ?inexperienced“). Only ?careless“ users did not follow our expectations, attaching none of the measured protective conditions to their self-disclosure.     

Corporate Taxation of Heterogeneous Firms and the Welfare Effects of Labour Unions

This paper examines the welfare effects of powerful labour unions when the government levies a uniform tax rate – as is currently the case in most OECD countries – and firms are heterogeneous with respect to productivity. I show that an increase in the bargaining power of labour unions can decrease the welfare loss generated by restriction of the tax policy and provide conditions under which powerful labour unions decrease the likelihood that firms will move abroad. I also reproduce the well‐known effect whereby powerful labour unions decrease corporate tax rates if firms are mobile.     

DETERMINANTS OF PUBLIC PENSION PLAN INVESTMENT RETURN. The role of fund value maximization and public choice theory

Public pension plans are a major type of institutional owner during the new era of investor capitalism, yet little is known about them. Based upon fund value maximization (FVM) and public choice theory (PCT), we develop hypotheses on the determinants of plan performance as measured by plan annual investment return. FVM espouses that the plan's fund or investment portfolio will be invested to maximize return for a given level of risk, while PCT holds that agency costs are significant in the public sector, and will have a negative effect on plan return. Using biennial pension plan data for 1992–96 for several hundred plans, we found that fund value maximization has a much greater influence on plan performance, but that plan performance is also subject to agency costs associated with public choice theory.     

Is investment decision-making influenced by perceptions relating to auditors’ client dependence and amount of audit fees?

The objectives of this study are to examine whether investing decisions are affected by knowledge about the auditor's revenue dependence on a client and whether the amount spent by a company on audit fees affects decisions to invest in the company. A behavioral experiment is conducted where risk assessments and investing decisions are made for four hypothetical investing scenarios. The study finds that investing decisions are affected by knowledge about an auditor's revenue dependence on a client, but are not affected by knowledge about the size of a client's audit fees.     

Earnings Management and the Long-Run Market Performance of Initial Public Offerings

Issuers of initial public offerings (IPOs) can report earnings in excess of cash flows by taking positive accruals. This paper provides evidence that issuers with unusually high accruals in the IPO year experience poor stock return performance in the three years thereafter. IPO issuers in the most "aggressive" quartile of earnings managers have a three-year aftermarket stock return of approximately 20 percent less than IPO issuers in the most "conservative" quartile. They also issue about 20 percent fewer seasoned equity offerings. These differences are statistically and economically significant in a variety of specifications.     

Imaginable surprise in global change science

Decisionmakers at all scales (individuals, firms, and local, national, and international governmental organizations) are concerned about reducing their vulnerability to (or the likelihood of) unexpected events, 'surprises.' After briefly and selectively reviewing the literature on uncertainty and surprise, we adopt a definition of 'surprise' that does not include the strict requirement that it apply to a wholly unexpected outcome, but rather recognizes that many events are often anticipated by some, even if not most observers. Thus, we define 'imaginable surprise' as events or processes that depart from the expectations of some definable community. Therefore, what gets labelled as 'surprise' depends on the extent to which what happens departs from community expectations and on the salience of the problem. We offer a typology of surprise that distinguishes imaginable surprises from risk and uncertainty, and develops several kinds of impediments to overcoming ignorances. These range from the need for more 'normal science' to phenomenological impediments (e.g., inherentunpredictability in some chaotic systems) to epistemological ignorance (e.g., ideological blocks to reducing ignorance). Based on the input of some two dozen scholars at an Aspen Global Change Institute Summer Workshop in 1994 *, we construct two tables in which participants offer many possible 'imaginable surprises' in the global change context, as well as their potential salience for creating unexpectedly high or low carbon dioxide emissions. Improving the anticipation of surprises is an interdisciplinary enterprise that should offer a sceptical welcoming of outlier ideas and methods.