A tutorial for analyzing human reaction times: How to filter data, manage missing values, and choose a statistical model

• CHRISTIAN MICHEL LACHAUD ^[1] ; OLIVIER RENAUD ^[2]
  1. [1] University of Oslo

     University of Oslo

     Noruega

     
  2. [2] Université de Genève

     Université de Genève

     Genève, Suiza

     
• Localización: Applied psycholinguistics, ISSN 0142-7164, Vol. 32, Nº 2, 2011, págs. 389-416
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • This tutorial for the statistical processing of reaction times collected through a repeated-measure design is addressed to researchers in psychology. It aims at making explicit some important methodological issues, at orienting researchers to the existing solutions, and at providing them some evaluation tools for choosing the most robust and precise way to analyze their data. The methodological issues we tackle concern data filtering, missing values management, and statistical modeling (F1, F2, F1 + F2, quasi-F, mixed-effects models with hierarchical, or with crossed factors). For each issue, references and remedy suggestions are given. In addition, modeling techniques are compared on real data and a benchmark is given for estimating the precision and robustness of each technique.