Basic algorithms for random sampling and treatment randomization

Abstract

Five BASIC programs to select random samples from populations or to randomize treatments are presented. Program 1 is used to obtain randomization of any number of treatments in an equal number of positions or test units for any number of replicates. Program 2 produces latin squares of any size for treatment randomization. Program 3 is used to obtain a specific number of randomly selected samples from a population without replacement. Program 4 produces quasi-latin squares that have treatments repeated equally in all rows and columns, with identical treatments either spaced or not. Program 5 can be used with any size grid to place 3-100 treatments in equal proportions and with spacing of identical treatments. Both programs 4 and 5 allow for horizontal and vertical separation between identical treatments at sampling places while still retaining the quality of randomness. These programs should facilitate random sampling and randomization procedures which are required to correctly analyze experiments by the methods of statistical probability.