Eliminating ANOVA Hand Calculations Predicts Improved Mastery in an Undergraduate Statistics Course

Abstract

Background: Presumably, most statistics professionals use a software program to perform statistical analyses, yet statistics textbooks and classes commonly teach hand calculations. Objective: This study examined whether, in an undergraduate psychology statistics course, hand calculations related to students' conceptual and applied analysis of variance (ANOVA) literacy. Method: Quasi-experimentally, we compared 95 students’ mastery of one-factor between- and within-subjects ANOVAs, using the unit quiz and SPSS data analytics lab, between sections which did and did not include hand calculations. Results: Controlling for GPA, gender, ethnicity, major, age, and math preparation to offset nonrandom assignment to section, eliminating ANOVA hand calculations predicted better performance on the quiz by 8% and on the SPSS lab by 6%. Conclusion: Shifting instructional focus away from hand calculations could enhance students’ conceptual and practical understanding of one-factor ANOVAs. Teaching Implications: Given time limitations, instructors might forgo teaching ANOVA hand calculations and focus on conceptual information and software applications.