About Us | Help Videos | Contact Us | Subscriptions



This article in NSE

  1. Vol. 37 No. 1, p. 74-82

    * Corresponding author(s):
Request Permissions


Statistical Measures, Hypotheses, and Tests in Applied Research

  1. David J. Savillea and
  2. Jacqueline S. Rowarth *b
  1. a Bioinformatics, Mathematics and Statistics Section, AgResearch, Lincoln Res. Centre, Private Bag 4749, Christchurch 8140, New Zealand
    b Inst. of Natural Resources, Massey Univ., Private Bag 11222, Palmerston North, New Zealand.


This article reviews and discusses the use of statistical concepts in a natural resources and life sciences journal on the basis of a census of the articles published in a recent issue of the Agronomy Journal and presents a flow chart and a graph that display the inter-relationships between the most commonly used statistical terms. It also discusses the use of contrasts between treatment means for testing ideas that the experimental work is designed to test, and points out that the use of a multiple comparison procedure is appropriate only when such ideas are absent or very vague. In the latter case, use of the unrestricted least significant difference procedure is recommended, with the proviso that it be used as an hypothesis generating method, not a method for simultaneous formulation and testing of hypotheses.

  Please view the pdf by using the Full Text (PDF) link under 'View' to the left.

Copyright © 2008. Copyright © 2008 by the American Society of Agronomy