Viewpoint: improving range science through the appropriate use of statistics.

Abstract

We examined a stratified random sample of articles published over 3 decades of the Journal of Range Management to study the applications and changes in statistical methodology employed by range scientists. Our objectives were to characterize the philosophical nature of statistics use in range science and to identify strengths and weaknesses inherent in these approaches. In each article, we examined the research design efficacy and whether the statistical analysis was adeptly used to convey the relevant information. The majority of articles we examined were conducted appropriately. In general, we found more emphasis has been placed on statistical testing than effect size estimation in the last decade. On an average, 82 tests or means comparisons (s.e. = 20) were presented in each article during the 1990's. Articles that reported an effect size via a sample mean frequently did not report an associated standard error. Research designs lacked adequate descriptions in several cases, making it difficult to determine if the appropriate analysis was performed. Improper identification of the experimental or sampling unit and/or the interdependence of observations occurred in all decades. We recommend increased inferential use of confidence intervals and suggest that the practical significance (as opposed to statistical significance) of results be considered more often. Improvements in the 'science' of range science can be made by greater understanding and communication of statistical concepts through consultation with statisticians.

DOI:10.2458/azu_jrm_v55i6_gould