Duo Qin – författare

Reformation of Econometrics is a sequel to The Formation of Econometrics: A Historical Perspective (1993, OUP) which traces the formation of econometric theory during the period 1930-1960. This book provides an account of the advances in the field of econometrics since the 1970s. Based on original research, it focuses on the reformists'' movement and schools of thought and practices that attempted a paradigm shift in econometrics in the 1970s and1980s.It describes the formation and consolidation of the Cowles Commission (CC) paradigm and traces and analyses the three major methodological attempts to resolve problems involved in model choice and specification of the CC paradigm. These attempts have reoriented the focus of econometric research from internal questions (how to optimally estimate a priori given structural parameters) to external questions (how to choose, design, and specify models). It also examines various modelling issues andproblems through two case studies - modelling the Phillips curve and business cycles. The third part of the book delves into the development of three key aspects of model specification in detail - structural parameters, error terms, and model selection and design procedures. The final chapter usescitation analyses to study the impact of the CC paradigm over the span of three and half decades (1970-2005). The citation statistics show that the impact has remained extensive and relatively strong in spite of certain weakening signs. It implies that the reformative attempts have fallen short of causing a paradigm shift.

Reformation of Econometrics is a sequel to The Formation of Econometrics: A Historical Perspective (1993, OUP) which traces the formation of econometric theory during the period 1930-1960. This book provides an account of the advances in the field of econometrics since the 1970s. Based on original research, it focuses on the reformists' movement and schools of thought and practices that attempted a paradigm shift in econometrics in the 1970s and 1980s. It describes the formation and consolidation of the Cowles Commission (CC) paradigm and traces and analyses the three major methodological attempts to resolve problems involved in model choice and specification of the CC paradigm. These attempts have reoriented the focus of econometric research from internal questions (how to optimally estimate a priori given structural parameters) to external questions (how to choose, design, and specify models). It also examines various modelling issues and problems through two case studies - modelling the Phillips curve and business cycles. The third part of the book delves into the development of three key aspects of model specification in detail - structural parameters, error terms, and model selection and design procedures. The final chapter uses citation analyses to study the impact of the CC paradigm over the span of three and half decades (1970-2005). The citation statistics show that the impact has remained extensive and relatively strong in spite of certain weakening signs. It implies that the reformative attempts have fallen short of causing a paradigm shift.

This book contains a set of notes prepared by Ragnar Frisch for a lecture series that he delivered at Yale University in 1930. The lecture notes provide not only a valuable source document for the history of econometrics, but also a more systematic introduction to some of Frisch’s key methodological ideas than his other works so far published in various media for the econometrics community. In particular, these notes contain a number of prescient ideas precursory to some of the most important notions developed in econometrics during the 1970s and 1980s More remarkably, Frisch demonstrated a deep understanding of what econometric or statistical analysis could achieve under the situation where there lacked known correct theoretical models. This volume has been rigorously edited and comes with an introductory essay from Olav Bjerkholt and Duo Qin placing the notes in their historical context.

In the memorable words of Ragnar Frisch, econometrics is ‘a unification of the theoretical–quantitative and the empirical–quantitative approach to economic problems’. Beginning to take shape in the 1930s and 1940s, econometrics is now recognized as a vital subdiscipline supported by a vast—and still rapidly growing—body of literature.Edited by a leading researcher in the history of econometrics, this new collection from Routledge’s Critical Concepts in Economics series brings together in one ‘mini library’ the best and most influential scholarship on the rise of econometrics. The set provides an authoritative one-stop resource to enable users to understand what has shaped econometrics into its current form. With a full index and comprehensive introductions to each volume, newly written by the editor, the collection also provides a synoptic view of many current key debates and issues.

This book contains a set of notes prepared by Ragnar Frisch for a lecture series that he delivered at Yale University in 1930. The lecture notes provide not only a valuable source document for the history of econometrics, but also a more systematic introduction to some of Frisch’s key methodological ideas than his other works so far published in various media for the econometrics community. In particular, these notes contain a number of prescient ideas precursory to some of the most important notions developed in econometrics during the 1970s and 1980s More remarkably, Frisch demonstrated a deep understanding of what econometric or statistical analysis could achieve under the situation where there lacked known correct theoretical models. This volume has been rigorously edited and comes with an introductory essay from Olav Bjerkholt and Duo Qin placing the notes in their historical context.

Haavelmo’s 1944 monograph, The Probability Approach in Econometrics, is widely acclaimed as the manifesto of econometrics. This book challenges Haavelmo’s probability approach, shows how its use is delivering defective and inefficient results, and argues for a paradigm shift in econometrics towards a full embrace of machine learning, with its attendant benefits.Machine learning has only come into existence over recent decades, whereas the universally accepted and current form of econometrics has developed over the past century. A comparison between the two is, however, striking. The practical achievements of machine learning significantly outshine those of econometrics, confirming the presence of widespread inefficiencies in current econometric research. The relative efficiency of machine learning is based on its theoretical foundation, and particularly on the notion of Probably Approximately Correct (PAC) learning. Careful examination reveals that PAC learning theory delivers the goals of applied economic modelling research far better than Haavelmo’s probability approach. Econometrics should therefore renounce its outdated foundation, and rebuild itself upon PAC learning theory so as to unleash its pent-up research potential. The book is catered for applied economists, econometricians, economists specialising in the history and methodology of economics, advanced students, philosophers of social sciences.

Haavelmo’s 1944 monograph, The Probability Approach in Econometrics, is widely acclaimed as the manifesto of econometrics. This book challenges Haavelmo’s probability approach, shows how its use is delivering defective and inefficient results, and argues for a paradigm shift in econometrics towards a full embrace of machine learning, with its attendant benefits.Machine learning has only come into existence over recent decades, whereas the universally accepted and current form of econometrics has developed over the past century. A comparison between the two is, however, striking. The practical achievements of machine learning significantly outshine those of econometrics, confirming the presence of widespread inefficiencies in current econometric research. The relative efficiency of machine learning is based on its theoretical foundation, and particularly on the notion of Probably Approximately Correct (PAC) learning. Careful examination reveals that PAC learning theory delivers the goals of applied economic modelling research far better than Haavelmo’s probability approach. Econometrics should therefore renounce its outdated foundation, and rebuild itself upon PAC learning theory so as to unleash its pent-up research potential. The book is catered for applied economists, econometricians, economists specialising in the history and methodology of economics, advanced students, philosophers of social sciences.

Haavelmo’s 1944 monograph, The Probability Approach in Econometrics, is widely acclaimed as the manifesto of econometrics. This book challenges Haavelmo’s probability approach, shows how its use is delivering defective and inefficient results, and argues for a paradigm shift in econometrics towards a full embrace of machine learning, with its attendant benefits.Machine learning has only come into existence over recent decades, whereas the universally accepted and current form of econometrics has developed over the past century. A comparison between the two is, however, striking. The practical achievements of machine learning significantly outshine those of econometrics, confirming the presence of widespread inefficiencies in current econometric research. The relative efficiency of machine learning is based on its theoretical foundation, and particularly on the notion of Probably Approximately Correct (PAC) learning. Careful examination reveals that PAC learning theory delivers the goals of applied economic modelling research far better than Haavelmo’s probability approach. Econometrics should therefore renounce its outdated foundation, and rebuild itself upon PAC learning theory so as to unleash its pent-up research potential. The book is catered for applied economists, econometricians, economists specialising in the history and methodology of economics, advanced students, philosophers of social sciences.

Haavelmo’s 1944 monograph, The Probability Approach in Econometrics, is widely acclaimed as the manifesto of econometrics. This book challenges Haavelmo’s probability approach, shows how its use is delivering defective and inefficient results, and argues for a paradigm shift in econometrics towards a full embrace of machine learning, with its attendant benefits.Machine learning has only come into existence over recent decades, whereas the universally accepted and current form of econometrics has developed over the past century. A comparison between the two is, however, striking. The practical achievements of machine learning significantly outshine those of econometrics, confirming the presence of widespread inefficiencies in current econometric research. The relative efficiency of machine learning is based on its theoretical foundation, and particularly on the notion of Probably Approximately Correct (PAC) learning. Careful examination reveals that PAC learning theory delivers the goals of applied economic modelling research far better than Haavelmo’s probability approach. Econometrics should therefore renounce its outdated foundation, and rebuild itself upon PAC learning theory so as to unleash its pent-up research potential. The book is catered for applied economists, econometricians, economists specialising in the history and methodology of economics, advanced students, philosophers of social sciences.