Design & Analysis of Latin Square Experiments - Analyze Design Tab

Select the Analyze design tab in the Design & Analysis of Latin Square Experiments dialog box to analyze a Latin square, Greco-Latin square, or Hyper-Greco Latin square design.

Variables

Click the Variables button to display a standard variable selection dialog box in which you select the dependent variable of interest and the independent variable list (list of factors in the design). Valid codes that can be used in the independent variables are positive integers in the range from 1 to 9 (as produced when generating the design via the Experimental Design module). Specifically, when the codes 1 through 3 are used, STATISTICA interprets the design as a 3-level Latin square (or Greco-Latin square, or Hyper-Greco Latin square); if codes 1 through 4 are used, the program interprets the design as a 4-level Latin square, and so on. However, as with all other designs, you can attach any text label to those codes. If the design specified in the independent variables cannot be identified as a valid and balanced Latin square-type design, a warning message will be issued.

Note: Latin square designs can also be analyzed via General Linear Models (GLM), General Regression Models (GRM), or via the (nonlinear) Generalized Linear/Nonlinear Models (GLZ) options.