fre TQMP Tutorials in Quantitative Methods for Psychology 1913-4126 2008-03-01 4 1 1 12 article Louis Laurencelle ll@uqtr.ca 1 Université du Québec à Trois-Rivières La sélection de personnel pour un emploi se base souvent sur une norme psychométrique qu’un candidat doit atteindre afin d’être recruté. Or, cette norme est statistique, c’est-à-dire calculée sur les mesures d’un simple échantillon de la population concernée, et il s’ensuit une incertitude, voire un risque d’erreur, dans la décision de retenir ou rejeter le candidat. Nous proposons une méthode d’établissement d’une norme psychométrique dont la probabilité d’erreur est strictement contrôlée, une « norme sûre », dont la valeur s’appuie uniquement sur les propriétés de base d’une série statistique, sans modèle paramétrique invoqué. http://www.tqmp.org/Content/vol04-1/p001/p001.pdf Statistics Confidence intervals eng TQMP Tutorials in Quantitative Methods for Psychology 1913-4126 2008-03-01 4 1 13 20 article Nadim Nachar nadim.nachar@umontreal.ca 1 Université de Montréal It is often difficult, particularly when conducting research in psychology, to have access to large normally distributed samples. Fortunately, there are statistical tests to compare two independent groups that do not require large normally distributed samples. The Mann-Whitney U is one of these tests. In the following work, a summary of this test is presented. The explanation of the logic underlying this test and its application are presented. Moreover, the forces and weaknesses of the Mann-Whitney U are mentioned. One major limit of the Mann-Whitney U is that the type I error or alpha (?) is amplified in a situation of heteroscedasticity. http://www.tqmp.org/Content/vol04-1/p013/p013.pdf Statistics Mann-Whitney test eng TQMP Tutorials in Quantitative Methods for Psychology 1913-4126 2008-03-01 4 1 21 34 article Glenn L. Thompson GlennLThompson@gmail.com 1 University of Ottawa Experimental psychologists routinely simplify the structure of their data by computing means for each experimental condition so that the basic assumptions of regression/ANOVA are satisfied. Typically, these means represent the performance (e.g. reaction time or RT) of a participant over several items that share some target characteristic (e.g. Mean RT for high-frequency words). Regrettably, analyses based on such aggregated data are biased toward rejection of the null hypothesis, inflating Type-I error beyond the nominal level. A preferable strategy for analyzing such data is random coefficient analysis (RCA), which can be performed using a simple method proposed by Lorch and Myers (1990). An easy to use SPSS implementation of this method is presented using a concrete example. In addition, a technique for evaluating the magnitude of potential aggregation bias in a dataset is demonstrated. Finally, suggestions are offered concerning the reporting of RCA results in empirical articles. http://www.tqmp.org/Content/vol04-1/p021/p021.pdf Statistics ANOVA eng TQMP Tutorials in Quantitative Methods for Psychology 1913-4126 2008-03-01 4 1 35 45 article Yves Lacouture yves.lacouture@psy.ulaval.ca 1 Denis Cousineau denis.cousineau@umontreal.ca 2 Université Laval Université de Montréal This article discusses how to characterize response time (RT) frequency distributions in terms of probability functions and how to implement the necessary analysis tools using MATLAB. The first part of the paper discusses the general principles of maximum likelihood estimation. A detailed implementation that allows fitting the popular ex-Gaussian function is then presented followed by the results of a Monte Carlo study that shows the validity of the proposed approach. Although the main focus is the ex-Gaussian function, the general procedure described here can be used to estimate best fitting parameters of various probability functions. The proposed computational tools, written in MATLAB source code, are available through the Internet. http://www.tqmp.org/Content/vol04-1/p035/p035.pdf Quantitative methods Distribution fitting