On the strategic equivalence of multiple-choice test scoring rules

A disadvantage of multiple-choice tests is that students have incentives to guess. To discourage guessing, it is common to use scoring rules that either penalize wrong answers or reward omissions. These scoring rules are considered equivalent in psychometrics, although experimental evidence has not always been consistent with this claim. We model students' decisions and show, first, that equivalence holds only under risk neutrality and, second, that the two rules can be modified so that they become equivalent even under risk aversion. This paper presents the results of a field experiment in which we analyze the decisions of subjects taking multiple-choice exams. The evidence suggests that differences between scoring rules are due to risk aversion as theory predicts. We also find that the number of omitted items depends on the scoring rule, knowledge, gender and other covariates.

On the optimal usage of labelled examples in semi-supervised multi-class classification problems

In recent years, the performance of semi-supervised learning has been theoretically investigated. However, most of this theoretical development has focussed on binary classification problems. In this paper, we take it a step further by extending the work of Castelli and Cover [1] [2] to the multi-class paradigm. Particularly, we consider the key problem in semi-supervised learning of classifying an unseen instance x into one of K different classes, using a training dataset sampled from a mixture density distribution and composed of l labelled records and u unlabelled examples. Even under the assumption of identifiability of the mixture and having infinite unlabelled examples, labelled records are needed to determine the K decision regions. Therefore, in this paper, we first investigate the minimum number of labelled examples needed to accomplish that task. Then, we propose an optimal multi-class learning algorithm which is a generalisation of the optimal procedure proposed in the literature for binary problems. Finally, we make use of this generalisation to study the probability of error when the binary class constraint is relaxed.

Usage of substances and their dosage regimes in pharmacological animal models of schizophrenia

Background: Contrary to what is generally thought schizophrenia is a very common mental health issue. For this, several animal models are used to assess the illness in order to develop a definitive. The most widely spread paradigm is the use of pharmacological models. Aim: The aim of this review is to display which are the most used insults for the assessment of social behaviour related negative symptoms in animal models as well as to ascertain which is the most adequate regime. Design: Literature review. Methods: PubMed database was used for this article by the search of the indexed “schizophrenia”, “animal models”, “social behaviour” and “negative symptoms” descriptors. With the exception of a single article due to it value this review is based on articles from 10 years onwards. Besides, only clinical trials and reviews written in English or Spanish and that had laboratory rodents as target population were accepted. Results: The studies assessed agree that pharmacological models (specially those regarding the NMDA receptor antagonists) are a valuable means for the experimental investigation of negative symptoms in schizophrenia with the necessity to emphasise that only some negative symptoms (anhedonia and social interaction, mainly) can be experimentally assessed. Conclusions: There is not enough evidence regarding the fours aspects of this review. PCP, Ketamine or MK-801 in sub-acute dosage regimes are currently the most indicated insults to mimic schizophrenic symptoms in rodents, although further research in needed, albeit other substances are valuable as well. (In English language exclusively)