Variance Estimation and Precision Results - Variance Evaluation Tab

Select the Variance Evaluation tab of the Variance Estimation and Precision Results dialog box to access the options described here.

Variability plot

Click the Variability plot button to display a variability plot for each of the selected response variable(s). This type of graph is useful to evaluate the variability of one factor within several other organizing factors. Options for customizing the default variability plot (e.g., putting boxes around organizing factors or showing group means/medians) are available by double-clicking in the graph background and selecting the Plot: Variability Plot tab of the Graph Options dialog box. If there are more than seven factors in the design, you will be prompted to select the (up to seven) factors to use in the variability plot. Initially, selected factors are plotted using the order found in the spreadsheet (e.g., Var1, Var2, Var3, etc.). Options for rearranging factor order and adding a replicate factor are available on the Plot: Variability Plot tab of the Graph Options dialog box.

Variance estimates

Click the Variance estimates button to produce a spreadsheet of the variance estimates. For REML analysis, variance components are displayed in design order with their approximate standard error and corresponding degrees of freedom. Additional results in this spreadsheet include upper and lower confidence bounds with their corresponding alpha and the z value with its corresponding probability. Note that standard errors and confidence bounds are not computed for ANOVA analysis. For both analysis types, three other values are reported for each variance component: a cumulative value (given in the sum column), the percent of the total sum of variance components, and a relative standard deviation (RSD) that is calculated as the square root of the variance component divided by the average value of all data and this quotient multiplied by 100%. For more information on how degrees of freedom and other values are calculated, see Computational Details.

Pie chart of var. estimates.

Click the Pie chart of var. estimates button to produce a pie chart of the estimated variance components, showing the relative percentages (i.e., percent of total variability) of the nonzero variance components. These relative variances can be interpreted as zero-order intraclass correlations when there is only one random factor in the analysis. If there is more than one random effect in the analysis and the random effects are correlated, the relative variances should be interpreted as partial intraclass correlations. If more than one response variable has been selected to be analyzed, a separate graph will be produced for each dependent variable. The graphs can then be viewed side-by-side using the workbook multi-item display.

Pareto chart of var. estimates.

Click the Pareto chart of var. estimates button to produce a Pareto chart of the estimated variance components, showing the relative percentages (i.e., percent of total variability) of the nonzero variance components. These relative variances can be interpreted as zero-order intraclass correlations when there is only one random factor in the analysis. If there is more than one random effect in the analysis and the random effects are correlated, the relative variances should be interpreted as partial intraclass correlations. If more than one response variable has been selected to be analyzed, a separate graph will be produced for each dependent variable. The graphs can then be viewed side-by-side using the workbook multi-item display.

Stacked bar of var. estimates.

Click the Stacked bar of var. estimates button to produce a stacked bar plot of the estimated variance components, showing the relative percentages (i.e., percent of total variability) of the nonzero variance components. These relative variances can be interpreted as zero-order intraclass correlations when there is only one random factor in the analysis. If there is more than one random effect in the analysis and the random effects are correlated, the relative variances should be interpreted as partial intraclass correlations. If more than one response variable has been selected to be analyzed, a separate graph will be produced for each dependent variable. The graphs can then be viewed side-by-side using the workbook multi-item display.

Plot relative variances (% of total)

Select the Plot relative variances (% of total) check box to plot estimated variance components in terms of percentages of total variance when pie charts or stacked bar charts are requested (see above). Note that estimated population intraclass correlation coefficients are displayed on bar plots and pie charts when the Plot relative variances check box is selected. These relative variances can be interpreted as zero-order intraclass correlations when there is only one random factor in the analysis. If there is more than one random effect in the analysis and the random effects are correlated, the relative variances should be interpreted as partial intraclass correlations.

Plot multiple pareto/stacked bar

Select the Plot multiple pareto/stacked bar check box to generate a compound graph that includes the variance components for each dependent variable when either a Pareto chart of variance estimates or Stacked bar chart of variance estimates is generated. If this check box is cleared, then separate Pareto charts and/or Stacked bar charts will be generated for each dependent variable. Note that this option is only available when more than one dependent variable is selected in the Dependent vars list box.

Alpha for confidence interval

Use the Alpha for confidence interval group box to specify confidence limits. This value is used in calculating confidence limits for variance estimates when REML analysis is used. Confidence limits are not generated for variance estimates when the ANOVA analysis type has been selected.