USING OF COVARIANCE ANALYSIS TO CONTROL FERTILITY GRADIENT IN FIELD EXPERIMENTS | ||||
| Egyptian Journal of Agricultural Research | ||||
| Article 34, Volume 77, Issue 1, March 1999, Page 451-463 PDF (3.21 MB) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ejar.1999.326683 | ||||
 View on SCiNiTO | ||||
| Author | ||||
| SAED M. NASR | ||||
| Scientific Computation Section, Central Laboratory for Design and Statistical Analysis, Agricultural Research Centre, Giza, Egypt | ||||
| Abstract | ||||
| Adjustment for fertility trends within a trial may increase precision. Two methods of controling fertility trends were used in this study. The first was moving mean covariance analysis (MMCA) and the second was check-row mean covariance analysis (CRMCA). The effectiveness of using moving mean covariance analysis (MMCA) for experimental error control was compared in soybean yield trial. The MMCA was superior to the RCBD, since it significantly reduced the experimental error and the coefficient of variation (CV.) Inclusion of five neighboring plots in moving mean computation provided better error control. However, the estimation of optimum number of neighboring plots to be used and moving mean were not easily calculated. The feasibility of using check-row measurements such as mean seed yield/m of row as a covariate in an analysis of covariance (CRMCA) was examined in a separate wheat yield trial in which check rows were planted with check cultivar. Check-row measurements were effective in reducing the experimental error. Check-row measurements could be easily used as a covariate in analysis of covariance without need for moving mean computation from the response variable. | ||||
|
Statistics Article View: 25 PDF Download: 111 |
||||
