Statistical Practices of Educational Researchers: An Analysis of their ANOVA, MANOVA, and ANCOVA Analyses

Abstract

Articles published in several prominent educational journals were examined to investigate the use of data-analysis tools by researchers in four research paradigms: between-subjects univariate designs, between-subjects multivariate designs, repeated measures designs, and covariance designs. In addition to examining specific details pertaining to the research design (e.g., sample size, group size equality/inequality) and methods employed for data analysis, we also catalogued whether: (a) validity assumptions were examined, (b) effect size indices were reported, (c) sample sizes were selected based on power considerations, and (d) appropriate textbooks and/or articles were cited to communicate the nature of the analyses that were performed. Our analyses imply that researchers rarely verify that validity assumptions are satisfied and accordingly typically use analyses that are nonrobust to assumption violations. In addition, researchers rarely report effect size statistics, nor do they routinely perform power analyses to determine sample size requirements. We offer many recommendations to rectify these shortcomings. Data Analytic Practices 3 Statistical Practises of Educational Researchers:An Analysis of Their ANOVA, MANOVA and ANCOVA Analyses It is well known that the volume of published educational research is increasing at a very rapid pace. As a consequence of the expansion of the field, qualitative and quantitative reviews of the literature are becoming more common. These reviews typically focus on summarizing the results of research in particular areas of scientific inquiry (e.g., academic achievement or English as a second language) as a means of highlighting important findings and identifying gaps in the literature. Less common, but equally important, are reviews that focus on the research process, that is, the methods by which a research topic is addressed, including research design and statistical analysis issues.Methodological research reviews have a long history (e.g., Edgington, 1964; Elmore & Woehlke, 1988 Goodwin & Goodwin, 1985a, 1985bWest, Carmody, & Stallings, 1983).One purpose of these reviews has been the identification of trends in data-analytic practice. The documentation of such trends has a two-fold purpose: (a) it can form the basis for recommending improvements in research practice, and (b) it can be used as a guide for the types of inferential procedures that should be taught in methodological courses, so that students have adequate skills to interpret the published literature of a discipline and to carry out their own projects.One consistent finding of methodological research reviews is that a substantial gap often exists between the inferential methods that are recommended in the statistical research literature and those techniques that are actually adopted by applied researchers (Goodwin & Goodwin, 1985b;Ridgeway, Dunston, & Qian, 1993). The practice of relying on traditional methods of analysis is, however, dangerous. The field of statistics is by no means static; improveme...

Measures of Effect Size for Comparative Studies: Applications, Interpretations, and Limitations

“…Textbooks on statistical methods have also included procedures for computing a number of indices of effect (e.g., Huberty, 1994;Keppel, 1991;Maxwell & Delaney, 1990;Stevens, 1996). In spite of an abundance of references, applied researchers have apparently not accepted the call for the use of effect size measures (Keselman et al, 1998;McNamara, 1978).…”

Importancia del tamaño del efecto en el análisis de datos de investigación en psicología

“…Como evidencia empírica sobre la aplicación de las medidas del tamaño del efecto, mediante una metodología de revisión metodológica de investigación (Keselman et al, 1998), hay estudios que hacen revisión y análisis sobre la aplicación del tamaño del efecto en los resultados de investigaciones en importantes y reconocidas revistas internacionales de Psicología. Entre estos estudios se tienen los desarrollados por Sun, Pan y Wang (2010), García, Ortega y De la Fuente (2008, 2011, Vacha-Haase y Ness (1999), Keselman et al (1998), Snyder y Thompson (1998), entre otros.…”

“…Entre estos estudios se tienen los desarrollados por Sun, Pan y Wang (2010), García, Ortega y De la Fuente (2008, 2011, Vacha-Haase y Ness (1999), Keselman et al (1998), Snyder y Thompson (1998), entre otros. Estos autores encontraron un porcentaje de reporte del tamaño del efecto de 57 %, 20 %, 9 % y 54 %, respectivamente.…”

Uso da estatística na Educação Física: análise das publicações nacionais entre os anos de 2009 e 2011

“…Estudos demonstram que a checagem de pressupostos para utilização de testes estatísticos é reportada em apenas 8-25% dos estudos 8,[11][12] . Além disso, tal fato não ocorre devido ao conhecimento da robustez dos testes utilizados, e sim por desconhecimento dos pressupostos e de como verifi ca-los 8 .…”