This book was first published in 1989. Inference and prediction in human affairs are characterised by a cognitive and reactive sample space, the elements of which are aware both of the statistician and of each other. It is therefore not surprising that methodologies borrowed from classical statistics and the physical sciences have yielded disappointingly few lasting empirical insights and have sometimes failed in predictive mode. This book puts the underlying methodology of socioeconomic statistics on a firmer footing by placing it within the ambit of inferential and predictive games. It covers such problems as learning, publication, non-response, strategic response, the nature and possibility of rational expectations, time inconsistency, intrinsic nonstationarity, and the existence of probabilities. Ideas are introduced such as real-time survey schemes, argument instability and reaction-proof forecasting based on stochastic approximation. Applications are canvassed to such topics as attitude measurement, political polling, econometric modelling under heterogeneous information, and the forecasting of hallmark events.

Recent advances in establishing the nature and scope of estimators in econometrics have shed more light on the importance of instrumental variables. In this book, the authors argue that such methods may be regarded as a strong organizing principle for a wide variety of estimation and hypothesis testing problems in econometrics and statistics. In support of this claim they present and develop the methodology of instrumental variables in its most general and explanatory form. They show, for instance, that techniques commonly used to handle simultaneity and related problems can be reduced to one of two generic variables of instrumental variables estimators, allowing them to explore further the conditions under which different proposed estimators are efficient.