Accumulation Analysis Results - Means Tab
Select the Means tab of the Accumulation Analysis Results dialog to access options to view marginal summary statistics and information about the alias structure.
- Summary: Display design and S/N ratios
- Click the Summary: Display design and S/N ratios button to display a spreadsheet showing the raw frequencies for each run. Using the option buttons below the Display marginal summary statistics button, you can display either Raw frequencies, Cumulative frequencies, Percent, Cumulative percent, or Omegas. Omega values are identical to the familiar logits computed as -10 * log10 [p/(1-p)].
- Display marginal summary statistics
- Click the Display marginal summary statistics button to display a spreadsheet which shows the selected statistic for each level for each factor. You can display either Raw frequencies, Cumulative frequencies, Percent, Cumulative percent, or Omegas. Omega values are identical to the familiar logits computed as -10 * log10 [p/(1-p)]).
- Alias structure
- Click the Alias structure button to display a spreadsheet showing a matrix of main effects (rows) by two-way interaction effects (columns). If the entries in the matrix are blank, then the respective two effects (main effect and interaction effect) are not confounded with each other (they are orthogonal). Asterisks (*) in this matrix mark effects that are not orthogonal.
This option is useful for identifying whether or not certain two-way interactions are confounded with the main effects in the design, and, if so, with which ones. Some orthogonal arrays allow you to estimate some two-way interactions, provided that specific main effects are not used (i.e., that those columns in the design are not used). Please refer to Phadke (1989) or Taguchi (1987) to learn more about advanced methods of "manipulating" and "molding" orthogonal arrays to accommodate specific unusual design needs (via the use of linear graphs).
- Descriptives for untransformed vars
- Click the Descr. for untransformed vars button to display a spreadsheet with the means, sums, and standard deviations for the untransformed dependent variables.
- Bar plot of cumulative proportions
- Click the Bar plot of cumul. prop. button to create a bar plot showing the cumulative proportion across categories within each level of each factor is shown. This plot allows one to easily identify the largest areas of low numbers of defects.
Line graph by factor. Click the Line graph by factor button to produce line plots for each factor separately. These plots show the cumulative distributions across categories for each level of the respective factor.