Principal Components and Classification Analysis Results - Descriptives Tab

Principal Components and Factor Analysis

Select the Descriptives tab of the Principal Components and Classification Analysis Results dialog box to access the options described here.

Summary descriptives

Click the Summary descriptives button to display a spreadsheet with the descriptive statistics, means and standard deviations, for the variables in the current analysis.

Correlation matrix

Click the Correlation matrix button to produce a spreadsheet with the correlation matrix for all variables (active as well as supplementary). Note that the correlation matrix can be produced irrespective of whether the analysis was based on correlations. However, if the Correlations option button was selected in the Analysis based on group box on the Principal Components Classification Analysis Startup Panel - Advanced tab, this is the matrix that has been used for computing the principal components and the related statistics.

Inverse

Click the Inverse button to display the inverse of the correlation matrix for the active variables only.

Save correlation matrix

Click the Save correlation matrix button to display the correlation matrix as a Statistica Spreadsheet Matrix in an individual window (regardless of the settings in the Options dialog box - Output Manager tab or the Analysis/Graph Output Manager dialog box). You can, however, add the spreadsheet to a workbook or report using the or buttons, respectively. Note that, to save the spreadsheet matrix, you must select the spreadsheet and select Save or Save As from the File menu. A matrix thus saved can be used directly in various other types of analyses, for example, in Factor Analysis, Multiple Regression, Canonical Analysis, Reliability and Item Analysis, Cluster Analysis, Multidimensional Scaling, and so on. See STATISTICA Matrix File Format for further information.

Covariance matrix

Click the Covariance matrix button to produce a spreadsheet with the covariance matrix for all variables (active as well as supplementary). Note that the covariance matrix can be produced irrespective of whether the analysis was based on covariances. However, if the Covariances option button was selected in the Analysis based on group box on the Principal Components Classification Analysis Startup Panel - Advanced tab, this is the matrix that has been used for computing principal components and the related statistics.

Inverse

Click the Inverse button to display the inverse of the covariance matrix.

Save covariance matrix

Click the Save covariance matrix button to display the covariance matrix as a Statistica Spreadsheet Matrix in an individual window. Note that, to save the spreadsheet matrix, you must select the spreadsheet and use the Save or Save As options in the File menu. A matrix thus saved can be used directly in various other types of analyses, for example, in Factor Analysis, Multiple Regression, Canonical Analysis, Reliability and Item Analysis, Cluster Analysis, Multidimensional Scaling, and so on. See Save correlation matrix (above) and STATISTICA Matrix File Format for further information.

Include in plots

If you select a Variable for active cases (through the Variables button on the PCA Startup Panel - Quick tab), the code for active cases would categorize the cases into active and supplementary cases. You can then use the options in the Include in plots group box to produce various plots (described below) either for active cases, supplementary cases, or for all cases.

All cases

Select the All cases option button to include both active and supplementary cases in the plots described below.

Active cases only

Select the Active cases only option button to include only the active cases in the plots described below.

Supplementary cases only

Select the Supplementary cases only option button to include only the supplementary cases in the plots described below.

Box & Whisker

Click the Box & Whisker button to display a standard variable selection dialog box, where you can select the variables for which you would like to produce the box & whisker plot. After selecting the variable(s), the Box-Whisker Type dialog box is displayed, where you can select the type of box & whisker plot to be produced. By selecting the appropriate option button in the Include in plots group box (see above), you can choose to include All cases, Active cases only, or Supplementary cases only in the box & whisker plot.

2D scatterplots

Click the 2D scatterplots button to display the standard variable selection dialog box, where you can select a pair of variables for the x- and y-axis, and then produce a 2D scatterplot for this selection. By selecting the appropriate option button in the Include in plots group box (see above), you can choose to include All cases, Active cases only, or Supplementary cases only in the 2D scatterplot.

Histograms

Click the Histograms button to produce a cascade of histograms for the variables in the current analysis. By selecting the appropriate option button in the Include in plots group box (see above), you can choose to include All cases, Active cases only, or Supplementary cases only in the histogram.

3D scatterplots

Click the 3D scatterplots button to display the standard variable selection dialog box, where you can select a triplet of variables for the x-, y-, and z-axis, and then produce a 3D scatterplot for this selection. By selecting the appropriate option button in the Include in plots group box (see above), you can choose to include All cases, Active cases only, or Supplementary cases only in the 3D scatterplot.

Normal prob. plots.

Click the Normal prob. plots button to produce a cascade of normal probability plots for the variables in the current analysis. For more information on how the standard normal probability plot is constructed, see the Factor Analysis topic Computation note for normal probability plots. By selecting the appropriate option button in the Include in plots group box (see above), you can choose to include All cases, Active cases only, or Supplementary cases only in the normal probability plot.

Surface plots

Click the Surface plots button to display the standard variable selection dialog box, where you can select a triplet of variables for the x-, y-, and z-axis, and then produce a surface plot for this selection. By selecting the appropriate option button in the Include in plots group box (see above), you can choose to include All cases, Active cases only, or Supplementary cases only in the surface plot. Note that if the surface fit to the plotted data cannot be computed, only a 3D scatterplot is displayed.