Because of the marked changes in health care expenditures in recent years, there has been a call for greater accountability in the area of health education, policy, services and reform. In recent years, evaluative research has been conducted in health arenas under the rubric of health services research. Health services research methods have not evolved from evaluation research methodology, but rather have adopted methods that often do not lend themselves to deriving appropriate causal inferences in multi-causal environments. Given the complexity of the interrelationships of political, social, psychological and ecc factors that can affect health services, more complex evaluative techniques are demanded. This paper describes the epistemology of evaluative research and through a series of examples from the health services literature demonstrates the strengths of theory-driven approaches and statistical multi-variate techniques compared to traditional black-box methods as ways to increase validity for causal inference.