Pronunciation: la'tin sqwar
Definition: A statistical design for experiments that removes from experimental error the variation from two sources that may be identified with the rows and columns of a square. The allocation of experimental treatments is such that each treatment occurs exactly once in each row and column. For example, a design for a 5 × 5 square is as follows:
Search Stedman's Medical Dictionary
Examples: glitazone, GI cocktail, etc.