A good data set is the foundation of a successful statistical review of compensation. The old adage of “garbage in, garbage out” could not be more fitting. Any quantitative analysis is only as good as the underlying data set. Inaccuracies and inconsistencies in the data not only can render the analysis inaccurate and unreliable but can also lead to incorrect inferences regarding the relationships being investigated. If these incorrect inferences are applied to business decisions, an employer could unintentionally create the very situation it was trying to remedy.