Comparing efficiency of randomized complete block and alpha lattice designs in agricultural field experiment. (case study, at bako agriculture research center, west shoa zone, Ethiopia)

Abstract

The choices of experimental design as well as of statistical analysis are of huge importance in field experiments. The efficiency of alpha lattice design and randomized complete block design (RCBD) were compared in maize trials conducted in 2010 at Bako Agricultural Research Centre (BARC), in Ethiopia on 45 treatments to assess the efficiency of each in minimizing experimental error, coefficient of variation and error mean square for yield variable. Bread wheat variety trials also conducted on 16 treatments to asses the performance of RCBD compared to CRD. Alpha designs are used for field trials because they provide better control on experimental variability among the experimental units under field conditions. The coefficient of variations (CV) compared to be 12.6 % for alpha lattice design and 14.6 % for RCBD respectively. The error mean squares calculated for these trials are 1.0418 for alpha lattice design and 1.4081 for randomized complete block design (RCBD) respectively. The relative efficiency of trials shows that alpha lattice design is more efficient than RCBD. The value of relative efficiency 1.35 indicates that the use of alpha lattice design instead of randomized complete block design (RCBD) increased experimental precision by 35 percent. The gain is considerable in terms of efficiency attained by using alpha lattice design which favors wider use of these designs under field conditions. Based on the results we conclude that alpha lattice designs are more efficient than RCBD. In order to increase the precision of agricultural field experiments researchers are advised to use RCBD for small number of treatments, and alpha lattice designs for large number of treatments.