Determining the Minimum Sample Size Required to Create Regression Model in Plant Ecology (Case Study: Cover-Production Relationship)

Regression analysis is one of the most widely used statistical tests in vegetation evaluation. Indirect methods of estimating forage yield always require regression analysis. The basic question in such research is that at least a few pairs of samples are required to achieve a valid regression equation. Therefore, this study determines the sample size required to estimate the yield of Haloxylon persicum Bunge, Artemisia sieberi Besser and Stipagrostis pennata (Trin.) De Winter using plant dimensions including cover percentage, plant area, height and volume. After correlation and regression analyzes, power analysis and effect size were calculated. The results showed that for regression analysis and the statistical importance of the equation and regression coefficients between the cover and yield for these species, about 26, 14 and 18 pairs (respectively) were proposed. By comparing the method used in this study with other rules of thumb, it can be deduced that the use of Green's rule (N≥ 50 + 8M and N ≥104 + M) is not recommended, because with at least one independent variable (M) About 58 to 105 pairs of samples are required. In the studies within Iran, double sampling methods are generally used, in which between 7 and 30 pairs (an average of 15 pairs) are recommended, which is closer to the number of pairs of the present study (14 to 26) than the rules of thumb.

Determining the Minimum Sample Size Required to Create Regression Model in Plant Ecology (Case Study: Cover-Production Relationship) Keywords:

Cover , Power analysis , Rangeland , Regression , Sample size