Explains how social scientists can evaluate the reliability and validity of empirical measurements, discussing the three basic types of validity: criterion related, content, and construct. In addition, the paper shows how reliability is assessed by the retest method, alternative-forms procedure, split-halves approach, and internal consistency method.

 Edward G. Carmines is Warner O. Chapman Professor of Political Science and Rudy Professor at Indiana University. He is also the director of the Center on American Politics and the research director at the Center on Congress at Indiana University. His research focuses on American politics, especially elections, public opinion, and political behavior. He has published widely in the major journals in the discipline including the American Political Science Review, American Journal of Political Science, and Journal of Politics. He is the coauthor of seven books, two of which, Issue Evolution: Race and Transformation of American Politics, with James A. Stimson (Princeton University Press 1992), and Reaching beyond Race, with Paul M. Sniderman (Harvard University Press 1997), won the American Political Science Association's Gladys M. Kammerer Award for best book in the field of U.S. national policy. Four of his papers presented at academic conferences have won outstanding paper awards, including the Franklin L. Burdette Pi Sigma Alpha Award, the Pi Sigma Alpha Award, and the Chastain Award.
Professor Carmines was a Visiting Professor at the University of Oxford in 1998, a Fellow at the Center for the Advanced Study in Behavioral Sciences at Stanford University in 2000-01, and a Fellow at the Center for the Study of Democratic Politics at Princeton University in 2006-07. In 1987 he was awarded the AMOCO Award for Distinguished Teaching from Indiana University.