Reliability Results - Advanced Tab

Select the Advanced tab of the Reliability Results dialog box to access options to review the key results of the analysis. For more information, see Reliability and Item Analysis - Introductory Overview.

Summary: Item-total statistics. Click the Summary: Item-total statistics button to display a spreadsheet containing various statistics regarding the relationship between each item and the scale without the respective item [the mean of the scale without the respective item, the variance of the scale without the respective item, the standard deviation of the scale without the respective item, the correlation between the respective item and the scale (without the item), and Cronbach's Alpha for the scale without the respective item]. In addition, if the Compute multiple regression items/scales check box was selected on the Reliability and Item Analysis dialog box, the multiple R-square of each item with the scale without the respective item will be displayed. Summary statistics for the analysis (e.g., Cronbach's Alpha, scale mean, etc.) are displayed in the spreadsheet header.

Split-half reliability. Click the Split-half reliability button to display the Split-Half Reliability dialog box, which displays a summary of the descriptive statistics and reliabilities for the two halves of the scale and contains options to access summary results for the split-half analysis. The Split-half reliability button is available only if two variable lists were specified via the Reliability and Item Analysis Startup Panel - Advanced tab.

Correlations. Click the Correlations button to display a spreadsheet containing the correlation matrix. A particularly useful Graph of Input Data for this spreadsheet is the scatterplot. The Correlations button is available only if a correlation matrix was selected via the Reliability and Item Analysis Startup Panel - Advanced tab.

Box & whisker plot. Click the Box & whisker plot button, select the variables you want to plot via the standard variable selection dialog, and select an option from the Box-Whisker Type dialog box to produce a box and whisker plot. For details concerning the median and the quartiles, refer to the Computation of percentiles option in the Options dialog - Analyses/Graphs: Limits tab (accessible by selecting Options from the Tools menu). For more information, see Percentile Calculation Options in STATISTICA.

Analysis of variance. Click the Analysis of variance button to display a spreadsheet with a complete analysis of variance table for the items in the scale. This analysis is equivalent to a one-way repeated measures ANOVA, where each item represents one level of the repeated measures factor (refer to the Introductory Overview of ANOVA/MANOVA for more details concerning repeated measures ANOVA).

Means & standard deviations. Click the Means & standard deviations button to display a spreadsheet with the means and standard deviations for all items. The standard deviations will be computed in the manner indicated by the SD=Sums of Squares/N check box on the Review Descriptive Statistics dialog box. Namely, they will either be computed as the square roots of the sums of deviation squares divided by N-1 or N. If divided by N-1, the resulting standard deviations are estimates of the standard deviations in the population (Sigma); if divided by N, the resulting standard deviations are descriptions of the sample only.

A particularly useful Graph of Input Data for this spreadsheet is a histogram (frequency distribution) of the selected variable, with the normal distribution superimposed. This plot can be beneficial as a quick check of whether the assumption of normality has been violated (on which the computation of the correlation coefficients is based, see Correlations - Introductory Overview).

Scatterplot matrix. Click the Scatterplot matrix button to display the standard variable selection dialog, in which you select the variables you wish to plot. Click the OK button to display a matrix scatterplot for the selected variables.