ABSTRACT: The practical problem is not why specification errors are made but how to detect them. There are number of tests for specification error in detecting the errors of omitted variables from a regression analysis. Using the observations on the dependent variables generated from Microsoft Excel according to the specification labeled true, a bootstrap simulation approach was used for the data generated for each of the models at different sample sizes 20, 30, 50, and 80 respectively each with 100 replications. Using bootstrapping experiment and some properties which estimators should possess if their estimates are to be accepted as good and satisfactory estimates of the parameters, namely, the bias, variance, mean square error, and root mean square error. The models investigated in the bootstrapping experiment consist of the problem of omitted variables. For the models considered, the experiment reveals that the estimated changes the effect of omitted variable as the coefficient varies in the different models. The effect of omitted variable becomes unstable which produces a bias and inconsistent.