Manuel Ato

Modified Brown-Forsythe Procedure for Testing Interaction Effects in Split-Plot Designs.

The standard univariate and multivariate methods are conventionally used to analyze continuous data from groups by trials repeated measures designs, in spite of being extremely sensitive to departures from the multisample sphericity assumption when group sizes are unequal. However, in the last 10 years several authors have offered alternative solutions to these tests that do not rest on this assumption. In an attempt to improve the precision of the Brown–Forsythe (BF) procedure, a new approximate degrees of freedom (df) approach is presented in this article. Unlike the BF test, the new method not only assures that the df will be always positive but also provides invariant solutions under linear transformations of the data. Monte Carlo methods are used to compare the new solution, in terms of control of Type I error rates, with the modified empirical generalized least squares and BF methods. Our extensive numerical studies show that the modified BF procedure outperformed the other two methods for a wide range of conditions.

Bullying in Spanish and English pupils: A sociometric perspective using the BULL‐S questionnaire

Most researchers into bullying agree on its social implications and on some inner aspects of the aggressive situations. Methods of identifying bullying among peers used to be very costly in time and effort. In order to simplify the task, the Bull‐S questionnaire has been elaborated. After its confirmation as a usable instrument in Spanish schools, we attempted to find out whether it could also be a good tool in foreign schools, by applying it to both an English and a Spanish sample. Results showed very high similarity between samples, which allows us to say that the aspects measured by the questionnaire are the same in both samples. First, we did not find significant differences in the extent of bullying in schools. Second, an item‐by‐item comparison showed significant differences between means in only: “Leave out of activities and games.” From a sociometric perspective, rejection is presented as associated with bullying and especially linked to victimisation, and acceptance is associated with those pupils not involved in bullying. Finally, factorial analyses confirmed that variables conformed to a different structure for bullies, for victims, and for not‐involved pupils. These different structures are quite similar in both countries.

Consequences of Misspecifying the Error Covariance Structure in Linear Mixed Models for Longitudinal Data

Abstract. Repeated measures and longitudinal data are frequently analyzed using a linear mixed model. According to this approach, rather than presuming a certain type of covariance structure analysts choose the model that best describes their data prior to carrying out inferences of interest. Because it is not possible to know the underlying covariance structure in advance, researchers often use fit criteria to select from possible covariance structures. SAS Institutes (2004) Proc Mixed program, allows users to model the correct covariance structure by comparing Akaikes Information Criterion (AIC), Hurvich and Tsais Criterion (AICC), Schwarzs Bayesian Criterion (BIC), Bozdogans Criterion (CAIC), and Hannan and Quinns Criterion (HQIC). Monte Carlo methods are used to examine performance of these criteria. The program also investigated the effects of misspecification on properties of the inferences. The results of the simulation show that neither criterion always lead to correct selection of model and...

Robust tests for multivariate factorial designs under heteroscedasticity

The question of how to analyze several multivariate normal mean vectors when normality and covariance homogeneity assumptions are violated is considered in this article. For the two-way MANOVA layout, we address this problem adapting results presented by Brunner, Dette, and Munk (BDM; 1997) and Vallejo and Ato (modified Brown–Forsythe [MBF]; 2006) in the context of univariate factorial and split-plot designs and a multivariate version of the linear model (MLM) to accommodate heterogeneous data. Furthermore, we compare these procedures with the Welch–James (WJ) approximate degrees of freedom multivariate statistics based on ordinary least squares via Monte Carlo simulation. Our numerical studies show that of the methods evaluated, only the modified versions of the BDM and MBF procedures were robust to violations of underlying assumptions. The MLM approach was only occasionally liberal, and then by only a small amount, whereas the WJ procedure was often liberal if the interactive effects were involved in the design, particularly when the number of dependent variables increased and total sample size was small. On the other hand, it was also found that the MLM procedure was uniformly more powerful than its most direct competitors. The overall success rate was 22.4% for the BDM, 36.3% for the MBF, and 45.0% for the MLM.

El papel de la memoria de trabajo en la adquisición lectora en niños de habla castellana

ResumenEn este trabajo se abordan cuestiones basicas relativas a la manipulacion y retencion de la informacion en la Memoria de Trabajo y su vinculacion con la adquisicion lectora desde la perspectiva de los modelos interactivos de procesamiento de la informacion. Se plantean cuatro experimentos aplicados a ninos de nivel lector alto y bajo de primero, tercero y quinto de EGB, respectivamente. Los resultados indican que solo existen diferencias significativas entre grupos de distinto nivel lector en aquellas tareas con mayor implicaion de componentes funcionales, mientras que las diferencias mas importantes entre cursos se dan entre primero y tercero, tanto para componentes estructurales como funcionales.

A robust approach for analyzing unbalanced factorial designs with fixed levels

The goal of this study was to investigate the performance of Hall’s transformation of the Brunner-Dette-Munk (BDM) and Welch-James (WJ) test statistics and Box-Cox’s data transformation in factorial designs when normality and variance homogeneity assumptions were violated separately and jointly. On the basis of unweighted marginal means, we performed a simulation study to explore the operating characteristics of the methods proposed for a variety of distributions with small sample sizes. Monte Carlo simulation results showed that when data were sampled from symmetric distributions, the error rates of the original BDM and WJ tests were scarcely affected by the lack of normality and homogeneity of variance. In contrast, when data were sampled from skewed distributions, the original BDM and WJ rates were not well controlled. Under such circumstances, the results clearly revealed that Hall’s transformation of the BDM and WJ tests provided generally better control of Type I error rates than did the same tests based on Box-Cox’s data transformation. Among all the methods considered in this study, we also found that Hall’s transformation of the BDM test yielded the best control of Type I errors, although it was often less powerful than either of the WJ tests when both approaches reasonably controlled the error rates.

Force-related information and exploratory behavior in infancy

Exploratory behavior allows the child to get to know its own possibilities of action in the environment. The aim of this study was to analyze how children explore the sense of force and to know if they are able to detect and adjust the forces necessary to perform a pulling task. 30 children between 10 and 24 months of age could activate the lights and music of a doll pulling from a ring with a certain force specified by the experimenter. Four decreasing ranges of force were used. Results show that all children were able to adjust their force to the requirements of the task, but the oldest children showed more exploratory behavior than the youngest ones.

Methodology - The First Four Years

Methodology has just published its fourth volume. It was planned at this point in time to invite two new editors to take over the journal and to make some necessary changes to the editorial board. To ease the transition process, it was decided that one editor, Professor Manuel Ato, would continue for another year (until the end of 2009). To this end, Professor Michael Eid, who has been an editor during the past four years, first at the University of Geneva and then at the Free University of Berlin, has now ended his editorship and we are pleased to announce that his position has been now filled by Professor Joop Hox from Utrecht University in the Netherlands. Once his final year is up, Manuel Ato will be replaced by Professor Julio Sanchez, who is also from the University of Murcia in Spain. We would like to take the opportunity to thank Michael Eid, and his collaborators Olivier Renaud and Delphine Gross (from the University of Geneva) and Christian Geiser (from the Free University of Berlin), for their excellent editorial work over the past four years. Since its inception, Methodology, the official organ of the European Association of Methodology, has been an online journal with a strong European vocation and dedication ‘‘to promote research and the development of empirical research methods in the fields of behavioral, social, educational, health and economic sciences, as well as in the field of evaluation research’’ (Ato & Eid, 2005). We emphasize our preference towards empirical research methods in the conviction that quantitative orientation embraces all phases of research methodology, including sampling, measurement, design, and data analysis. We also believe that there are strong methodological similarities between the different scientific disciplines using these research methods, in spite of the diversity of the areas of psychology and social sciences to which they can be applied. As mentioned in the Editorial of Volume 1 (2005),Methodology publishes the original contributions of researchers from all over the world in the form of research articles, software information, and instructional papers. In the period 2005–2008, the journal has published 60 research articles and a short note on software information. The authors of these articles come fromvery diverse origins such asGermany (39), Spain (36), USA (24), the Netherlands (19), Austria (7), Australia (3), Belgium (3), United Kingdom (3), Sweden (2), Chile (1), Portugal (1), and Switzerland (1). Topics covered range from data analysis (Finch & Schneider, 2007; Hofler, 2008; Kelley, 2008; Korendijk, Maas, Moerbeek, & Van der Heijden, 2008;Maroco, 2007; Palmer, Losilla, Vives, & Jimenez, 2007) to survey and experimental methodology (Overall & Tonidandel, 2007; Stocke, 2007; Vallejo, Fernandez, & Livacic-Rojas, 2007), psychometrics (Barrada, Olea, & Ponsoda, 2007; Hofmans, Theuns, & Mairesse, 2007; Lozano, Garcia-Cueto, & Muniz, 2008; von Davier & von Davier, 2007), and structural equation modeling (Coffman, 2008; Dimitruk, Schermelleh-Engel, Kelava, & Moosbrugger, 2007; Kelava, Moosbrugger, Dimitruk, & Schmelleh-Engel, 2008). In the last couple of years, we have also introduced special thematic issues edited by prominent researchers in their field. Three special issues that have been published to date include social network analysis (edited by Jeroen K. Vermunt & Marijtje A. J. van Duijn, 2006), mixture structural equation modeling (edited by Jost Reinecke, 2006), and longitudinal approach in psychology and the social sciences: Theoretical and analytical perspectives (edited by Jaume Arnau, 2008). As an online journal, with four issues per volume, and an annual print compendium,Methodology is not only available online via Hogrefe & Huber’s PsyCONTENT platform (www.psycontent.com), but also via the American Psychological Association’s PsycARTICLES fulltext database, which assures us a vast and appropriate audience for the information published and good accessibility for methodologists and applied researchers. Furthermore, we have recently been informed that, due to an agreement with theHogrefe &Huber group, the archives ofMethodologywill be stored by Portico, a digital preservation service for the scholarly community. We thank all authors, members of editorial board, reviewers, and Hogrefe staff for their total confidence in the editors over these four years. We also encourage all our readers to continue submitting papers to Methodology on topics of interest to the journal on data analysis, research methodology, and psychometrics.

A practical method for analyzing factorial designs with heteroscedastic data.

The Type I error rates and powers of three recent tests for analyzing nonorthogonal factorial designs under departures from the assumptions of homogeneity and normality were evaluated using Monte Carlo simulation. Specifically, this work compared the performance of the modified Brown-Forsythe procedure, the generalization of Boxs method proposed by Brunner, Dette, and Munk, and the mixed-model procedure adjusted by the Kenward-Roger solution available in the SAS statistical package. With regard to robustness, the three approaches adequately controlled Type I error when the data were generated from symmetric distributions; however, this studys results indicate that, when the data were extracted from asymmetric distributions, the modified Brown-Forsythe approach controlled the Type I error slightly better than the other procedures. With regard to sensitivity, the higher power rates were obtained when the analyses were done with the MIXED procedure of the SAS program. Furthermore, results also identified that, when the data were generated from symmetric distributions, little power was sacrificed by using the generalization of Boxs method in place of the modified Brown-Forsythe procedure.

Sample size estimation for heterogeneous growth curve models with attrition

In this study, two approaches were employed to calculate how large the sample size needs to be in order to achieve a desired statistical power to detect a significant group-by-time interaction in longitudinal intervention studies—a power analysis method, based on derived formulas using ordinary least squares estimates, and an empirical method, based on restricted maximum likelihood estimates. The performance of both procedures was examined under four different scenarios: (a) complete data with homogeneous variances, (b) incomplete data with homogeneous variances, (c) complete data with heterogeneous variances, and (d) incomplete data with heterogeneous variances. Several interesting findings emerged from this research. First, in the presence of heterogeneity, larger sample sizes are required in order to attain a desired nominal power. The second interesting finding is that, when there is attrition, the sample size requirements can be quite large. However, when attrition is anticipated, derived formulas enable the power to be calculated on the basis of the final number of subjects that are expected to complete the study. The third major finding is that the direct mathematical formulas allow the user to rigorously determine the sample size required to achieve a specified power level. Therefore, when data can be assumed to be missing at random, the solution presented can be adopted, given that Monte Carlo studies have indicated that it is very satisfactory. We illustrate the proposed method using real data from two previously published datasets.