Beginners in many disciplines learn that correlation never proves causation, but sometimes, even in public health, correlation, mistaken for causation, becomes the basis for policy and great expenditures of public and private money. "True experiments" with random assignment to experimental and control groups hold a special place in the realm of scientific research. The results of such experiments, particularly when replicated under many, varied conditions, provide the most dependable basis for policy and practice, as clearly demonstrated and even required for definitive conclusions in agronomy and medicine. The case for experiments is pressing in K through 12 education, which lacks a strong foundation of causal research, particularly disciplined-based control group experiments and large-scale, well-controlled statistical studies. Given the strong consensus among policymakers about the need for improved academic performance on the part of our nation's students--as evidenced by the federal No Child Left Behind Act and more stringent state testing and accountability systems--educators want to know how to raise achievement and efficiency. Without causal confidence, their efforts may be on shaky scientific ground. Given this need for knowledge about what works, the Laboratory for Student Success, the mid-Atlantic Regional Educational Laboratory at Temple University, and the American Psychological Association convened a national invitational conference, "The Scientific Basis of Educational Productivity," on May 13 and 14, 2004, in Arlington, Virginia. The commissioned conference papers, written by nationally recognized experts and summarized in this issue of "The LSS Review"--exhibit a variety of scientific approaches to research, emphasizing the special credibility of multiple methods and multiple studies converging on policy-and practice-relevant results. The following papers are summarized in this issue: The Scientific Basis of Educational Productivity: Proceedings and Recommendations from a National Invitational Conference (Rena F. Subotnik and Herbert J. Walberg); Experimental and Quasi-Experimental Research Designs (Susan J. Paik); Scientific Formative Evaluation: The Role of Individual Learners in Generating and Predicting Successful Educational Outcomes (T. V. Joe Layng, Greg Stikeleather, and Janet S. Twyman); Blending Experimental and Descriptive Research: The Case of Educating Reading Teachers (Elizabeth S. Pang and Michael L. Kamil); The Enhancement of Critical Thinking (Diane F. Halpern); Improving Educational Productivity: An Assessment of Extant Research (Herbert J. Walberg); The Scientific Basis for the Theory of Successful Intelligence (Robert J. Sternberg); Science, Politics, and Education Reform: The National Academies' Role in Defining and Promoting High-Quality Scientific Education Research, 2000-2004 (Lisa Towne); American Board for Certification of Teacher Excellence: Applying Research to Develop a Standards-Based Teacher Certification Program (Kathleen Madigan); Evidence-Based Interventions and Practices in School Psychology: The Scientific Basis of the Profession (Thomas R. Kratochwill); The Institute of Education Sciences' What Works Clearinghouse (Robert Boruch and Rebecca Herman); and Conclusions and Recommendations (Herbert J. Walberg and Rena F. Subotnik). ["The LSS Review" is a product of the Mid-Atlantic Regional Educational Laboratory, the Laboratory for Student Success (LSS), one of ten regional educational laboratories funded by the Institute of Education Sciences (IES) of the U.S. Department of Education. For "The LSS Review. Volume 3, Number 1," see ED497188.]