ABSTRACT: When a model is created which correctly leaves out one or more important variables, one rarely know which test has the highest power for detecting the associated specification error. This research adopts the use of bootstrapping experiment. The models investigated consist of three omitted variables which have a coefficient that varies from 0.1 through 1 and 2. A bootstrap simulation approach was used to generate data for each of the models at different sample sizes (n) 20, 30, 50, and 80 respectively, each with 100 replications(r). For the models considered, the experiment reveals that the Ramsey Regression Equation Specification Error Test (RESET test) is more efficient than that of Durbin-Watson test in detecting the error of omitted variable in specification error.