A comparative study of robust tests for spread: asymmetric trimming strategies

Will game-based learning enhance performance?

Purpose

Extending the study of Chan et al. (2016), this paper aims to focus on specific aspects of performance (conceptual and factual knowledge) to provide insight into whether computer game attributes designed into Prrinciples Aren’t That Hard (PATH) improve performance.

Design/methodology/approach

A between-subjects experiment is conducted to test the hypotheses. The experimental and control groups are PATH and traditional paper medium, respectively.

Findings

The results reveal that PATH users perform better on the conceptual knowledge questions compared to the traditional paper medium users. No significant difference in performance on the factual knowledge (computational) questions is found between PATH and traditional paper medium users.

Research limitations/implications

This study demonstrates that PATH creates an engaging learning environment, which facilitates the acquisition of conceptual knowledge and improved (conceptual) performance. Research can investigate whether technology may be used to facilitate automation of computational tasks which downplay the importance of computational skills (factual knowledge) and focus on the design of computer game attributes in educational or training programs to enhance conceptual knowledge and (conceptual) performance.

Practical implications

The findings of this study will assist educators and educational technology developers to identify and design motivation-enhancing computer game features to promote remember and understand cognitive processes which improve (conceptual) performance.

Originality/value

Game-based learning serves as the underlying theoretical framework for the design of PATH used in an experimental study to examine the positive effects of motivation-enhancing computer game attributes on remember and understand cognitive processes which facilitate (conceptual) performance. This study also uses separate measures of performance; that is, conceptual and factual knowledge, to provide additional insight into the findings of Chan et al. (2016).

Variance Heterogeneity in Published Psychological Research

Parametric assumptions for statistical tests include normality and equal variances. Micceri (1989) found that data frequently violate the normality assumption; variances have received less attention. We recorded within-group variances of dependent variables for 455 studies published in leading psychology journals. Sample variances differed, often substantially, suggesting frequent violation of the assumption of equal population variances. Parallel analyses of equal-variance artificial data otherwise matched to the characteristics of the empirical data show that unequal sample variances in the empirical data exceed expectations from normal sampling error and can adversely affect Type I error rates of parametric statistical tests. Variance heterogeneity was unrelated to relative group sizes or total sample size and observed across subdisciplines of psychology in experimental and correlational research. These results underscore the value of examining variances and, when appropriate, using data-analytic methods robust to unequal variances. We provide a standardized index for examining and reporting variance heterogeneity.

A Characterization of Power Method Transformations throughL-Moments

Power method polynomial transformations are commonly used for simulating continuous nonnormal distributions with specified moments. However, conventional moment-based estimators can (a) be substantially biased, (b) have high variance, or (c) be influenced by outliers. In view of these concerns, a characterization of power method transformations byL-moments is introduced. Specifically, systems of equations are derived for determining coefficients for specifiedL-moment ratios, which are associated with standard normal and standard logistic-based polynomials of order five and three. Boundaries forL-moment ratios are also derived, and closed-formed formulae are provided for determining if a power method distribution has a valid probability density function. It is demonstrated thatL-moment estimators are nearly unbiased and have relatively small variance in the context of the power method. Examples of fitting power method distributions to theoretical and empirical distributions based on the method ofL-moments are also provided.