On Misinterpretation of Course and Instruction Evaluation Data: How Relying Solely on Mean Scores Can Distort Score Meaning

One of the fundamental components of basic statistics is to examine a data distribution, namely its centre (median, mean, etc.), shape (skewness, symmetry, modality, etc.) and spread (variability, range, etc.). When examining research data, most educators are keenly aware of these fundamentals, but curiously seem to forget these fundamentals when examining course and instructor evaluation data. What often occurs is evaluators rely solely on mean score ratings as the basis for making inferences about a course and/or its instructor(s). This is problematic because a mean score alone does not illustrate the underlying score distribution, which in turn could completely alter the meaning of the data. The aim of this article is to present an illustrative example from basic statistics illustrating how course and instructor evaluation score inferences may be distorted by the underlying distribution of scores, thus threatening the validity of the measures. Suggestions for improving data reporting are provided.