HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Snedecor, G. W. Articles by Culbertson, C. C. Search for Related Content PubMed Articles by Snedecor, G. W. Articles by Culbertson, C. C.

An Improved Design for Experiments with Groups of Animals Whose Outcome May Be Estimated

Iowa State College

Abstract

He who experiments with animals in lots has had to contend with many difficulties in using the statistical tests of significance. First, he was usually limited to small samples, whereas the conventional statistical theory was based on large samples; second, he frequently had a knowledge of outcome which tempted him to select the animals for his lots rather than leave the choice to random sampling. He was thus confronted with this dilemma; to utilize his ability in selecting the lots and forfeit the benefits of tests of significance, or to randomize his lots and sacrifice the precision of his mean differences.

It was not until 1924 that R. A. Fisher² extended the small sample theory to include the kind of results obtained in lot experiments. As an integral part of one particularly efficient style of analysis of variance, Fisher devised a scheme of restricted random sampling which has been applied with signal success in field crops experiments.