Sentences Recognition Memory and Extraversion-Introversion Levels: A Statistical Modelling Approach

This research aimed to analyse individual differences in recognition of semantic memory by means of a statistical modelling approach, because some difficulties arise when traditional experimental designs and statistical hypotheses tests are used. In this field, statistical modelling provides the possibility of obtaining a data-fitted model for each experimental condition. One hundred and thirty five adult students, both males and females, agreed to participate in our study and were classified as high, middle and low extraverts. Sentences with a high semantic organisation were used as material to be recognised. A statistical modelling process was then applied using the lEM program. Differences in recognition memory for hits were found between middle and low extraversion levels, as revealed by the different data-fitted models.     

The impact of mobile financial services’ usage on microfinance delinquency

This paper studies the impact of Mobile Financial Systems’ usage on microcredit delinquency ratios in Tunisia by using either a two-part model or matching econometric procedures. Our large dataset contains all of the administrative registers that belong to the six branches of Enda, the incumbent Institution leader in Tunisia. We find a significant reduction of 4.92 days of late repayment for an average user of MFS in an environment where 15% of loans have been paid late at least once. We foresee a tremendous opportunity to improve the MFIs’ repayment ratios and, consequently, provide microcredit customers with more financing for income generating activities.     

The vector lattice structure of the n-person TU games

We show that any cooperative TU game is the maximum of a finite collection of a specific class of the convex games: the almost positive games. These games have non-negative dividends for all coalitions of at least two players. As a consequence of the above result we show that the class of modular games is a set of generators of the distributive lattice of all cooperative TU games. Finally, we characterize zero-monotonic games using a strong max-convex decomposition.