Germà Coenders’s scientific contributions

RESUMEN El investigador que en Ciencias de la Salud usa cuestionarios se basa tácitamente (a menudo inadvertidamente) en la Teoría Clásica del Test, cuyos supuestos, poco realistas, con frecuencia se violan, y conducen a evaluar deficientemente la fiabilidad y la validez del instrumento. Este artículo pone el énfasis en la necesidad de precisar los términos esenciales de la medición -fiabilidad y validez- clarificando las deficiencias que en su uso incurre la metodología tradicional. Señala las limitaciones de la evaluación de la fiabilidad mediante el alfa de Cronbach o la laxitud en la valoración cuantitativa de la validez mediante el Análisis Factorial Exploratorio. Como alternativa se propone el tratamiento secuencial e integrado de la validez y la fiabilidad en el marco de los modelos de Análisis Factorial Confirmatorio. Estos modelos proporcionan el marco estadístico adecuado para evaluar la validez y la fiabilidad de cada ítem, en lugar de efectuar sólo valoraciones globales. La perspectiva confirmatoria guía al investigador para que optimice el proceso de construcción o adaptación de un cuestionario, liberándole del poco fundamentado ritual que recetaba la metodología clásica. Palabras clave: Validez, Fiabilidad, Análisis Factorial Confirmatorio, Análisis Factorial Exploratorio, alfa de Cronbach SUMMARY The researcher who in Health Sciences uses questionnaires tacitly (and often inadvertently) bases him or herself on the Classical Theory of the Test, whose unrealistic hypotheses are frequently violated, leading to a deficient assessment of the reliability and the validity of the instrument. This article stresses the need to specify the essential terms of the measurement --reliability and validity-- clarifying the deficiencies that the traditional methodology incurs on using it. It indicates the limitations of the assessment of reliability using Cronbach’s alpha and the laxity of the quantitative evaluation of the validity using the Exploratory Factor Analysis. As an alternative it proposes the sequential and integrated treatment of the validity and the reliability within the framework of the Confirmatory Factor Analysis models. These models provide an adequate statistical framework to assess the validity and the reliability of each item, instead of carrying out only overall evaluations. The confirmatory perspective guides the researcher in order to optimize the process to construct or adapt a questionnaire, releasing him or her from the unfounded ritual prescribed by the classical methodology. Key words: Validity, Reliability, Confirmatory Factor Analysis, Exploratory Factor Analysis, Cronbach’s alfa

The primary goal of the study is to diagnose satisfaction and loyalty drivers in Polish retail banking sector. The problem is approached with Customer Satisfaction Index (CSI) models, which were developed for national satisfaction studies in the United States and European countries. These are multiequation path models with latent variables. The data come from a survey on Poles’ usage and attitude towards retail banks, conducted quarterly on a representative sample. The model used in the study is a compromise between author’s synthesis of national CSI models and the data constraints. There are two approaches to the estimation of the CSI models: Partial Least Squares - used in national satisfaction studies and Covariance Based Methods (SEM, Lisrel). A discussion is held on which of those two methods is better and in what circumstances. In this study both methods are used. Comparison of their performance is the secondary goal of the study.