Understanding the Relationship Between Communication and Political Knowledge: A Model Comparison Approach Using Panel Data

For any given covariance structure model, there will often be alternative models that are indistinguishable from the original model in terms of goodness of fit to data. The existence of such equivalent models is almost universally ignored in empirical studies. A study of 53 published applications showed that equivalent models exist routinely, often in large numbers. Detailed study of three applications showed that equivalent models may often offer substantively meaningful alternative explanations of data. The importance of the equivalent model phenomenon and recommendations for managing and confronting the problem in practice are discussed. Show more

Analyses of the persuasive effects of media exposure outside the laboratory have generally produced negative results. I attribute such nonfindings in part to carelessness regarding the inferential consequences of measurement error and in part to limitations of research design. In an analysis of opinion change during the 1980 presidential campaign, adjusting for measurement error produces several strong media exposure effects, especially for network television news. Adjusting for measurement error also makes preexisting opinions look much more stable, suggesting that the new information absorbed via media exposure must be about three times as distinctive as has generally been supposed in order to account for observed patterns of opinion change. Show more