Select the Advanced tab of the Reliability and Item Analysis Startup Panel to access the options described here.

Variables. Click the Variables button to display the standard variable selection dialog box, in which you select the variables to be used to perform an item analysis and to compute the reliability of a scale.

Split-half reliability (2 lists). Click the Split-half reliability button to display the Select the items in the two halves: dialog. After the Variables have been selected for the analysis (see above), you can divide the variables into two variable (item) lists (the two lists do not have to contain all the items that were originally selected, see also Split-half reliability). For each item list, STATISTICA will calculate the reliability, the correlation between the two lists (i.e., their sums), and the correlation corrected for attenuation, as well as the split-half reliability. Note that the Split-half reliability button is available only after the Variables for the analysis have been selected.

Input file. The Input file box contains two options: Raw Data and Correlation Matrix.

Raw Data. If you select Raw Data via the Input file box, STATISTICA expects a standard raw data file as input.

Correlation Matrix. If you select Correlation Matrix via the Input file box, STATISTICA expects a correlation matrix as input. Correlation matrix files can be created from within Reliability and Item Analysis or another STATISTICA module (e.g., Basic Statistics, Canonical Analysis, Factor Analysis, Multiple Regression, etc.). Correlation matrix files can also be created directly via the Create New Document - Spreadsheet tab (see also, Matrix file format). Note that if your Input file consists of correlation coefficients only (e.g., from a published source), and no means, standard deviations, or N is available, you may simply assume standardized data (mean = 0, standard deviation = 1) and an N of, for example, 100 (N must be greater than the number of variables in the analysis). You will first need to add these four cases (means, standard deviation, cases, and matrix) to your spreadsheet before you can run the analysis. Of course, in the results, the descriptive statistics for each variable are not meaningful in that case, however, the reliability/item analysis can be performed based on the correlation coefficients alone.

Correlation matrix. The Correlation matrix box contains four options: Standard Pearson r, NO, Tetrachoric r (quick cos p approx.), and Tetrachoric r (iterative approx.). For information on each type of correlation, see Correlation matrices in Reliability and Item Analysis.

Codes for dichotomized variables. The tetrachoric correlation coefficient assumes that the data in the selected variables (items) consist of codes that indicate which one of two responses the respective respondent gave for the respective item. Enter two integer values in the range of -999 to +999 in the Codes for dichotomized variables boxes to indicate the (integer) values used in the selected items to indicate the two responses. Note that STATISTICA always assumes that the first code that is entered represents the lower value, and the second code the higher value of the dichotomized variable, and the directions of the tetrachoric correlations are determined accordingly. Note that the Codes for dichotomized variables boxes are only available if tetrachoric correlations are selected via the Correlation matrix box.

Compute multiple regression items/scale. Select the Compute multiple regression items/scale check box to calculate the multiple correlation (between each item and the sum of all others in the scale). This calculation may increase processing time if the scale contains many items (i.e., if many items were selected for the analysis).

Batch processing/reporting. If you select the Batch processing/reporting check box, STATISTICA automatically performs the analysis (after you click the OK button) and sends the entire output from the analysis to a workbook, individual windows, and/or to a report (depending to the options selected in the Analysis/Graph Output Manager).