Multi-agent based simulation (MABS) is increasingly used for so- cial science studies. However, few methodologies and tools ex- ist. A strong issue is the choice of the number of simulation runs and the validation of the results by statistical methods. In this arti- cle, we propose a model of tool which automatically generates and runs new simulations until the results are statistically valid using a chi-square test. The choice of the test configuration allows both a general overview of the variable links and a more specific inde- pendence analysis. We present a generic tool for any RePast-based simulation and apply it on an Academic Labor Market economic simulation.