Abstract Before analyzing the results of experimental design, researchers have to choose the proper experimental design. Random Group (Randomized Completely Block Design) including single-factor design (consists of only one factor) is still a fairly simple design for field trials. On the field is generally difficult to obtain conditions that totally homogeneous, so that when the experiments were conducted with RAL will certainly gain a great error. The study was conducted using ethanol extract of plant roots tuba dissolved in 70% ethanol is sprayed on the outside of the body of a cockroach / cockroaches. Then observed how many cockroaches are dying as a result of an increase in the concentration level of tuba root extract. Researchers generally have been experimenting with caution, but several factors under the researchers' ability can cause data loss. Yates method is a method for the analysis of missing data on an experimental design by inserting the estimated value that minimizes the Sum of Squares Error. The use of Yates method for estimating missing data is very helpful to be able to do further analysis, in this case, analysis of variance (ANOVA). Results of analysis of variance showed Award tuba root concentration levels in experimental animals has a significant influence, though not using the original data.