Union–intersection permutation solution for two-sample equivalence testing

One of the well-known problems with testing for sharp null hypotheses against two-sided alternatives is that, when sample sizes diverge, every consistent test rejects the null with a probability converging to one, even when it is true. This kind of problem emerges in practically all applications of traditional two-sided tests. The main purpose of the present paper is to overcome this very intriguing impasse by considering a general solution to the problem of testing for an equivalence null interval against a two one-sided alternative. Our goal is to go beyond the limitations of likelihood-based methods by working in a nonparametric permutation framework. This solution requires the nonparameteric Combination of dependent permutation tests, which is the methodological tool that achieves Roy’s Union–intersection principle. To obtain practical solutions, the related algorithm is presented. To appreciate its effectiveness for practical purposes, a simple example and some simulation results are also presented. In addition, for every pair of consistent partial test statistics it is proved that, if sample sizes diverge, when the effect lies in the open equivalence interval, the Rejection probability (RP) converges to zero. Analogously, if the effect lies outside that interval, the RP converges to one.     

The Voice of Deception: Vocal Strategies of Naive and Able Liars

The aim of this research was to analyze the main vocal cues and strategies used by a liar. 31 male university students were asked to raise doubts in an expert in law about a picture. The subjects were required to describe the picture in three experimental conditions: telling the truth (T) and lying to a speaker when acquiescent (L1) and when suspicious (L2). The utterances were then subjected to a digitized acoustic analysis in order to measure nonverbal vocal variables. Verbal variables were also analyzed (number of words, eloquency and disfluency index). Results showed that deception provoked an increment in F₀, a greater number of pauses and words, and higher eloquency and fluency indexes. The F₀ related to the two types of lie—prepared and unprepared—identified three classes of liars: good liars, tense liars (more numerous in L1), and overcontrolled liars (more numerous in L2). It is argued that these differences are correlated to the complex task of lying and the need to control one's emotions during deception. The liar's effort to control his/her voice, however, can lead to his/her tone being overcontrolled or totally lacking in control (leakage). Finally, the research forwards an explanation on the strategies used by the good liar and in particular treats the self-deception hypothesis.     

The impact of related party transactions on earnings management: some insights from the Italian context

Related party transactions have become a key issue as a result of recent financial scandals. This study examines whether firms use related party transactions for earnings management, and then, whether they try to minimize detection through the format of related party transactions disclosure. Firstly, we analyze the association between related party transactions structure (types and parties involved) and the probability of reporting small earnings increase. Related party transactions may have significant impact on, and implications for, earnings management. According to the agency theory, related party transactions are used opportunistically, while the efficient transaction hypothesis argues that related party transactions meet the economic needs of the business. We next investigate the association between the probability of reporting small earnings increases through related party transactions and disclosure quality. Disclosure quality should be studied in relation to impression management and investor attention; this approach takes account of the idea that earnings management behavior may influence the quality of disclosure as a possible way of lowering conflict of interest. In line with the agency theory, our findings show that revenue related party transactions are more likely to be used to manage earnings than other types of transaction; related party transactions with ultimate parents are associated with lower probability of reporting small earnings increases compared to operations with other related parties. Lastly, our results confirm that the decision to engage in earnings management is related to lower disclosure quality.