This book had its conception in 1975in a friendly tavern near the School of Businessand PublicAdministration at the UniversityofMissouri-Columbia. Two of the authors (Fomby and Hill) were graduate students of the third (Johnson), and were (and are) concerned about teaching econometrics effectively at the graduate level. We decided then to write a book to serve as a comprehensive text for graduate econometrics. Generally, the material included in the bookand itsorganization have been governed by the question, " Howcould the subject be best presented in a graduate class?" For content, this has meant that we have tried to cover " all the bases " and yet have not attempted to be encyclopedic. The intended purpose has also affected the levelofmathematical rigor. We have tended to prove only those results that are basic and/or relatively straightforward. Proofs that would demand inordinant amounts of class time have simply been referenced. The book is intended for a two-semester course and paced to admit more extensive treatment of areas of specific interest to the instructor and students. We have great confidence in the ability, industry, and persistence of graduate students in ferreting out and understanding the omitted proofs and results. In the end, this is how one gains maturity and a fuller appreciation for the subject in any case. It is assumed that the readers of the book will have had an econometric methods course, using texts like J. Johnston's Econometric Methods, 2nd ed.

1 Introduction.- 2 Review of Ordinary Least Squares and Generalized Least Squares.- 3 Point Estimation and Tests of Hypotheses in Small Samples.- 4 Large Sample Point Estimation and Tests of Hypotheses.- 5 Stochastic Regressors.- 6 Use of Prior Information.- 7 Preliminary Test and Stein-Rule Estimators.- 8 Feasible Generalized Least Squares Estimation.- 9 Heteroscedasticity.- 10 Autocorrelation.- 11 Lagged Dependent Variables and Autcorrelation.- 12 Unobservable Variables.- 13 Multicollinearity.- 14 Varying Coefficient Models.- 15 Models That Combine Time-Series and Cross-Section Data.- 16 The Analysis of Models with Qualitative or Censored Dependent Variables.- 17 Distributed Lags.- 18 Uncertainty in Model Specification and Selection.- 19 Introduction to Simultaneous Equations Models.- 20 Identification.- 21 Limited Information Estimation.- 22 Full Information Estimation.- 23 Reduced Form Estimation and Prediction in Simultaneous Equations Models.- 24 Properties of Dynamic Simultaneous Equations Models.- 25 Special Topics in Simultaneous Equations.- Appendix Estimation and Inference in Nonlinear Statistical Models.- A.1 Nonlinear Optimization.- A.1.1 Method of Steepest Ascent.- A.1.2 The Method of Newton.- A.1.3 Method of Quadratic Hill Climbing.- A.1.4 Numerical Differentiation.- A.2 Maximum Likelihood Estimation.- A.2.1 Use of the Method of Newton.- A.2.2 Method of Scoring.- A.2.3 The Method of Berndt, Hall, Hall, and Hausman.- A.2.4 Asymptotic Tests Based on the Maximum Likelihood Method.- A.2.4a The Wald Test.- A.2.4b The Lagrange-Multiplier Test.- A.2.4c The Likelihood Ratio Test Statistic.- A.2.4d Concluding Remarks.- A.3 Nonlinear Regression.- A.4 Summary and Guide to Further Readings.- A.5 References.

The scientific advances that underpin economic growth and human health would not be possible without research investments. Yet demonstrating the impact of research programs is a challenge, especially in areas that span disciplines, industrial sectors, and encompass both public and private sector activity. All areas of research are under pressure to demonstrate benefits from federal funding of research. This exciting and innovative study demonstrates new methods and tools to trace the impact of federal research funding on the structure of research, and the subsequent economic activities of funded researchers. The case study is food safety research, which is critical to avoiding outbreaks of disease. The authors make use of an extraordinary new data infrastructure and apply new techniques in text analysis. Focusing on the impact of US federal food safety research, this book develops vital data-intensive methodologies that have a real world application to many other scientific fields.