Residual Analysis - Advanced Tab

Multiple Regression - Computational Approach

Select the Advanced tab of the Residual Analysis dialog to access options to review various statistics. Note that when Pairwise deletion is selected in the MD deletion group box in the Startup Panel, the program will substitute any missing values with the respective means in the computations for predicted and residual values (and related statistics).

Summary: Residuals & predicted

Click the Summary: Residuals & predicted button to display a spreadsheet with various statistics (types of residuals) for each observation. For a detailed description of the available statistics, see Residuals and predicted values.

Descriptive statistics. Click the Descriptive statistics button to display the Review Descriptive Statistics dialog from which you can choose to review the means and standard deviations, the correlation matrix and the covariance matrix, or choose to display the correlation matrix in a standard matrix spreadsheet.

Regression summary

Click the Regression summary button to display a spreadsheet with the standardized (Beta) and non-standardized (B) regression coefficients, their standard errors, and statistical significance's. The summary statistics for the regression analysis (e.g., R, R-square, etc.) will be displayed in the headers of the spreadsheet.

Durbin-Watson statistic

Click the Durbin-Watson statistic button to display a spreadsheet with the Durbin-Watson D statistic and the serial correlation (correlation of adjacent residuals). The Durbin-Watson statistic is useful for evaluating the presence or absence of a serial correlation of residuals (i.e., whether or not residuals for adjacent cases are correlated, indicating that the observations or cases in the data file are not independent). Note that all statistical significance tests in multiple regression assume that the data consist of a random sample of independent observations. If this is not the case, then the estimates (B coefficients) may be more unstable than the significance levels would lead one to believe. Intuitively, it should be clear that, for example, giving the same questionnaire to the same person 100 times will yield less information about the general population than administering that questionnaire to a random sample of 100 different individuals, who complete the questionnaire only once. In the former case, observations are not independent of each other (the same respondent will give similar responses in repeated questionnaires), while in the latter case, the observations are independent (different people).

Maximum number of rows (cases) in a single results Spreadsheet or Graph

Enter the Maximum number of rows (cases) in a single results Spreadsheet or Graph value to control the maximum number of cases to be displayed in a single spreadsheet or graph, when choosing any of the options to display residuals. If there are more valid cases (valid residuals) than the number specified in this field, then multiple spreadsheets or graphs will be displayed, with sequential "chunks" of the cases. The default value is 100,000.