Analysis of an Experiment with Two-Level Factors - Means Tab

This group box contains options for displaying the observed means in your experiment.

Click this button to produce a spreadsheet showing the unique runs (those with unique combinations of factor settings) in the experiment. In addition, for each unique run, Statistica will compute the mean, standard deviation, and standard error of the mean (if there is more than one run for the respective unique combination of factor settings).

When this check box is selected, the factor settings in the spreadsheet will be identified by their respective text labels. If there are no text labels in the file (for the list of independent variables or factors), this option will not be available. Note that the setting of this option also determines whether text labels will be shown in square and cube plots, in spreadsheets with marginal means, and in marginal means plots.

Use the options in this group box to compute the marginal means for the design (e.g., the means for Factor 1 by Factor 2, collapsed across Factor 3 and Factor 4). When the Show text labels instead of factor values check box is selected on the Design tab or Means tab, the factor levels in the spreadsheet and/or plot are labeled with their text labels.

Click the Display button to display the Compute marginal means for dialog box, in which you specify for which factors to display marginal means. Specify the factors and click the OK button to compute the marginal means for the design and display them in a spreadsheet. See Marginal Means for Screening Experiments for a description of that spreadsheet.

Click the Means plot button to produce a plot of weighted or unweighted marginal means. First, the Compute marginal means for dialog box is displayed, in which you specify for which factors to display marginal means. After selecting the factors, the Specify the arrangement of the factors in the plot dialog box is displayed, in which you select the assignment of factors. Note that the orientation and layout of the x-upper value labels can be adjusted via the Graph Options dialog box. The computation of the marginal means, standard errors, and confidence intervals follows the procedures outlined in the note on Marginal means.

Select this check box to compute weighted means for the marginal means plot or spreadsheet.

Use the options in this group box to produce the so-called square or cube plots for the predicted (estimated) means (see also the Introductory Overview).

Square plot of predicted means. Click this button to display the Factors for square plot dialog box, in which you select the two lists of factors for the square plot. Click the OK button on this dialog to plot the predicted means for the low and high settings for two factors. When the Show text labels instead of factor levels check box is selected, this plot will contain the text labels of the factor levels. The predicted means are computed based on the current model as specified in the Include in model group box on the Model tab. If there are more factors in the current design (including blocks and curvature check) than what is to be plotted in the square plot (2 factors), Statistica computes the predicted means based on the means for all other factors in the design, including block factors (i.e., the recoded new variables to compute the block effects; see Main Effects and Interactions; if the design has equal N per experimental condition, then the block effects will be ignored because the means for the recoded new variables will be 0). The coefficient for curvature (if requested) will always be ignored.

Click this button to display the Factors for cube plot dialog box, in which you select the factors for the cube plot. Click the OK button in this dialog box to plot the predicted means for the low and high settings for three factors. When the Show text labels instead of factor levels check box is selected, this plot will contain the text labels of the factor levels. The predicted means are computed based on the current model as specified in the Include in model group box on the Model tab. If there are more factors in the current design (including blocks and curvature check) than what is to be plotted in the cube plot (3 factors), Statistica computes the predicted means based on the means for all other factors in the design, including block factors (i.e., the recoded new variables to compute the block effects; see Main Effects and Interactions; if the design has equal N per experimental condition, the block effects will be ignored because the means for the recoded new variables will be 0). The coefficient for curvature (if requested) will always be ignored.

When the Show confidence intervals check box is selected, Statistica computes the confidence intervals for the predicted means based on the current model and ANOVA error term selected via the Model tab. The percentile value for the confidence intervals is taken from the Confidence interval box on the ANOVA/Effects tab. If no error term is available (e.g., df-error = 0), this option is not applicable, and confidence intervals cannot be computed.

Click this button to display the Profiler dialog box. Use the Profiler to inspect the predicted values for the dependent variables at different combinations of levels of the independent variables, to specify desirability functions for the dependent variables, and to specify a search for the levels of the independent variables that produce the most desirable response on the dependent variables.