104: 116–121. January 1987 | C. M. LESSELS1 AND PETER T. BOAG2
The article by C. M. Lesells and Peter T. Boag addresses the common mistake in calculating repeatability, a measure used in quantitative genetics to describe the proportion of variance in a character that occurs among rather than within individuals. Repeatability is calculated using variance components from a one-way analysis of variance (ANOVA), where the intraclass correlation coefficient is given by:
\[ r = \frac{s^2_A}{s^2 + s^2_A} \]
where \( s^2_A \) is the among-groups variance component and \( s^2 \) is the within-group variance component. The authors outline the correct method for calculating repeatability, point out the common mistake of equating \( MS_A \) with mean square, and show how this mistake affects the calculated values. They provide a method for checking published values and calculating approximate repeatability values from the \( F \) ratio (mean squares among groups/mean squares within groups). The article includes examples and detailed calculations to illustrate the correct and incorrect methods, emphasizing the importance of using variance components rather than mean squares for accurate repeatability estimation.The article by C. M. Lesells and Peter T. Boag addresses the common mistake in calculating repeatability, a measure used in quantitative genetics to describe the proportion of variance in a character that occurs among rather than within individuals. Repeatability is calculated using variance components from a one-way analysis of variance (ANOVA), where the intraclass correlation coefficient is given by:
\[ r = \frac{s^2_A}{s^2 + s^2_A} \]
where \( s^2_A \) is the among-groups variance component and \( s^2 \) is the within-group variance component. The authors outline the correct method for calculating repeatability, point out the common mistake of equating \( MS_A \) with mean square, and show how this mistake affects the calculated values. They provide a method for checking published values and calculating approximate repeatability values from the \( F \) ratio (mean squares among groups/mean squares within groups). The article includes examples and detailed calculations to illustrate the correct and incorrect methods, emphasizing the importance of using variance components rather than mean squares for accurate repeatability estimation.