General Interest Boxes The Distribution of Adulthood Earnings in the United Kingdom by Childhood Socioeconomic Circumstances 72 The Unpegging of the Swiss Franc 77 Financial Diversification and Portfolios 84 Off the Mark！108 Social Class or Education?Childhood Circumstances and Adult Earnings Revisited 122 A Way to Increase Voter Turnout 124 The"Beta"ofa Stock 152 The Economic Value of a Year of Education:Homoskedasticity or Heteroskedasticity?193 Is Coffee Good for Your Health?214 The Effect of Ageingon Healthcare Expenditures:A Red Herring?304 The Demand for Economics Journals 307 Do Stock Mutual Funds Outperform the Market?341 James Heckman and Daniel McFadden,Nobel Laureates 414 When Was Instrumental Variables Regression Invented?430 The First IV Regression 447 The Externalities of Smoking 451 The Hawthormne Effect 480 Conditional Cash Transfers in Rural Mexico to Increase School Enrollment 483 Text as Data 543 Can You Beat the Market?564 The River of Blood 577 Orange Trees on the March 635 NEWS FLASH:Commodity Traders Send Shivers Through Disney World 636 Nobel Laureates in Time Series Econometrics 680 25
General Interest Boxes 25 The Distribution of Adulthood Earnings in the United Kingdom by Childhood Socioeconomic Circumstances 72 The Unpegging of the Swiss Franc 77 Financial Diversification and Portfolios 84 Off the Mark! 108 Social Class or Education? Childhood Circumstances and Adult Earnings Revisited 122 A Way to Increase Voter Turnout 124 The “Beta” of a Stock 152 The Economic Value of a Year of Education: Homoskedasticity or Heteroskedasticity? 193 Is Coffee Good for Your Health? 214 The Effect of Ageing on Healthcare Expenditures: A Red Herring? 304 The Demand for Economics Journals 307 Do Stock Mutual Funds Outperform the Market? 341 James Heckman and Daniel McFadden, Nobel Laureates 414 When Was Instrumental Variables Regression Invented? 430 The First IV Regression 447 The Externalities of Smoking 451 The Hawthorne Effect 480 Conditional Cash Transfers in Rural Mexico to Increase School Enrollment 483 Text as Data 543 Can You Beat the Market? 564 The River of Blood 577 Orange Trees on the March 635 NEWS FLASH: Commodity Traders Send Shivers Through Disney World 636 Nobel Laureates in Time Series Econometrics 680 A01_STOC4455_04_GE_FM.indd 25 20/12/18 5:20 PM
This page intentionally left blank
A01_MISH4182_11_GE_FM.indd 6 10/06/15 11:46 am This page intentionally left blank
Preface conometrics can be a fun course for both teacher and student.The real world Lof economics,business,and government is a complicated and messy place,full of competing ideas and questions that demand answers Does healthcare spending actually improve health outcomes?Can you make money in the stock market by buying when prices are historically low,relative to earnings,or should you just sit tight,as the random walk theory of stock prices suggests?Does heavy intake of cof- fee lower the risk of disease or death?Econometrics helpsus sor out sound ideas from crazy ones and find quantitative answers to important quantitative questions. Econometrics opens a window on our complicated world that lets us see the relation- ships on which people,businesses,and governments base their decisions Introduction to Econometrics is designed for a first course in undergraduate econometrics.It is our experience that to make econometrics relevant in an introduc- tory course.interesting applications must motivate the theory and the theory must match the applications This simple principle represents a significant departure from the older generation of econometrics books,in which theoretical models and assump- tions do not match the applications.It is no wonder that some students question the relevance of econometrics after they spend much of their time learning assumptions that they that they must then to "problems"that arise when the applications do not match the assumptions.We believe that it is far better to motivate the need for tools with a concrete application and then to provide a few simple assumptions that match the application.Becaus the methods are immediately relevant to the applications,this approach can make econometrics come alive. To improve student results,we recommend pairing the text content with MyLab Economics,which is the teaching and learning platform that empowers you to reach every student.By combining trusted author content with digital tools and a flexible platform,MyLab personalizes the learning experience and will help your students earn and retain key course concepts while develo oping skills that future employers are seeking in their candidates.MyLab Economics helps you teach your course.your way.Learn more at www.pearson.com/mylab/economics. New To This Edition New chapter on"Big Data"and machine learning .Forecasting in time series data with large data sets 27
Preface 27 Econometrics can be a fun course for both teacher and student. The real world of economics, business, and government is a complicated and messy place, full of competing ideas and questions that demand answers. Does healthcare spending actually improve health outcomes? Can you make money in the stock market by buying when prices are historically low, relative to earnings, or should you just sit tight, as the random walk theory of stock prices suggests? Does heavy intake of coffee lower the risk of disease or death? Econometrics helps us sort out sound ideas from crazy ones and find quantitative answers to important quantitative questions. Econometrics opens a window on our complicated world that lets us see the relationships on which people, businesses, and governments base their decisions. Introduction to Econometrics is designed for a first course in undergraduate econometrics. It is our experience that to make econometrics relevant in an introductory course, interesting applications must motivate the theory and the theory must match the applications. This simple principle represents a significant departure from the older generation of econometrics books, in which theoretical models and assumptions do not match the applications. It is no wonder that some students question the relevance of econometrics after they spend much of their time learning assumptions that they subsequently realize are unrealistic so that they must then learn “solutions” to “problems” that arise when the applications do not match the assumptions. We believe that it is far better to motivate the need for tools with a concrete application and then to provide a few simple assumptions that match the application. Because the methods are immediately relevant to the applications, this approach can make econometrics come alive. To improve student results, we recommend pairing the text content with MyLab Economics, which is the teaching and learning platform that empowers you to reach every student. By combining trusted author content with digital tools and a flexible platform, MyLab personalizes the learning experience and will help your students learn and retain key course concepts while developing skills that future employers are seeking in their candidates. MyLab Economics helps you teach your course, your way. Learn more at www.pearson.com/mylab/economics. New To This Edition • New chapter on “Big Data” and machine learning • Forecasting in time series data with large data sets A01_STOC4455_04_GE_FM.indd 27 06/12/18 10:52 AM
28 Preface ·Dynamic factor models Parallel treatment of prediction and causal inference using regression .Coverage of realized volatility as well as autoregressive conditional heteroske- dasticity Updated discussion of weak instruments Very large data sets are increasingly being used in economics and related fields. Applications include predictingconsumer choices measuring the quality of hospitals or schools,analyzing nonstandard data such as text data,and macroeconomic fore- casting with many variables.The three main additions in this edition incorporate the fundamentals of this growing and exciting area of application. First,we have a new chapter(Chapter 14)that focuses on big data and machin learning methods.Within economics,many of the applications to date have focused on the so called many-predictor problem,where the number of predictors is large rel- ative to the sample siz -perhaps even exceeding the sample size.With many predic- tors,ordinary least squares (OLS)provides poor predictions,and other methods,such as the LASSO,can have much lower out-of-sample prediction errors.This chapter and prediction using principal components,shows how to choose tuning parameters by cross-validation.and explains how these methods can be used to analyze nonstan- dard data such as text data.As usual,this chapter has a running empirical example in this case.prediction of school-level test scores given school-level characteristics. for California elementary schools. Second,in Chapter 17(newly renumbered).we extend the many-predictor focus of Chapter 14 to time series data.Specifically.we show how the dynamic factor model can handle a very large number of time series.and show how to implement the dynamic factor model using principal components analysis.We illustrate the dynamic actor model and its use for forecasting with a 131-variable dataset of U.S.quarterly macroeconomic time series Third,we now lay out these two uses of regression-causal inference and tions;the two applications place different demands on how the data are collected. When the data are from a randomized controlled experiment.OLs estimates the causal effect.In observational data,if we are interested in estimating the causal effect.then the econometrician needs to use control variables and/or instruments to produce as-if randomization of the variable of interest.In contrast,for predic- tion,one is not interested in the causal effect so one does not need as-if random variation;however,the estimation("training")data set must be drawn from the same population as the observations for which one wishes to make the prediction
• Dynamic factor models • Parallel treatment of prediction and causal inference using regression • Coverage of realized volatility as well as autoregressive conditional heteroskedasticity • Updated discussion of weak instruments Very large data sets are increasingly being used in economics and related fields. Applications include predicting consumer choices, measuring the quality of hospitals or schools, analyzing nonstandard data such as text data, and macroeconomic forecasting with many variables. The three main additions in this edition incorporate the fundamentals of this growing and exciting area of application. First, we have a new chapter (Chapter 14) that focuses on big data and machine learning methods. Within economics, many of the applications to date have focused on the so called many-predictor problem, where the number of predictors is large relative to the sample size—perhaps even exceeding the sample size. With many predictors, ordinary least squares (OLS) provides poor predictions, and other methods, such as the LASSO, can have much lower out-of-sample prediction errors. This chapter goes over the concepts of out-of-sample prediction, why OLS performs poorly, and how shrinkage can improve upon OLS. The chapter introduces shrinkage methods and prediction using principal components, shows how to choose tuning parameters by cross-validation, and explains how these methods can be used to analyze nonstandard data such as text data. As usual, this chapter has a running empirical example, in this case, prediction of school-level test scores given school-level characteristics, for California elementary schools. Second, in Chapter 17 (newly renumbered), we extend the many-predictor focus of Chapter 14 to time series data. Specifically, we show how the dynamic factor model can handle a very large number of time series, and show how to implement the dynamic factor model using principal components analysis. We illustrate the dynamic factor model and its use for forecasting with a 131-variable dataset of U.S. quarterly macroeconomic time series. Third, we now lay out these two uses of regression—causal inference and prediction—up front, when regression is first introduced in Chapter 4. Regression is a statistical tool that can be used to make causal inferences or to make predictions; the two applications place different demands on how the data are collected. When the data are from a randomized controlled experiment, OLS estimates the causal effect. In observational data, if we are interested in estimating the causal effect, then the econometrician needs to use control variables and/or instruments to produce as-if randomization of the variable of interest. In contrast, for prediction, one is not interested in the causal effect so one does not need as-if random variation; however, the estimation (“training”) data set must be drawn from the same population as the observations for which one wishes to make the prediction. 28 Preface A01_STOC4455_04_GE_FM.indd 28 20/12/18 2:06 PM
Preface This edition has several smaller changes.for example.we now introduce realized volatility as a complement to the GARCH model when analyzing time series data with volatility clustering.In addition,we now extend the discussion(in a new general interest box)of the historical origins of instrumental variables regression in Chapter 1Thisremenwnudesfrst-ever of of the IV estimator,which was in a letter from Philip Wright to his son Sewall in the spring of 1926,and a discussion of the first IV regression,an estimate of the elasticity of supply of flaxseed. Solving Teaching and Learning Challenges Introduction to Econometrics differs from other texts in three main ways.First,we integrate real-world questions and data into the development of the theory,and we take seriously the substantive findings of the resulting empirical analysis.Second. our choice of topics theoryand practic Third,we provide theory and assumptions that match the applications.Our aim is to teach students to become sophisticated consumers of econometrics and to do so at a level of mathematics appropriate for an introductory course. Real-World Questions and Data We organize each methodological topic around an important real-world question that demands a specific numerical answer.For example,we teach single-variable regression,multiple regression,and functional form analysis in the context of estimating the effect of school inputs on school outputs.(Do smaller elementary school class sizes produce higher test scores?)We teach panel data methods in the context of analyzing the effect of drunk driving laws on traffic fatalities.We use possible racial discrimination in the market for home loans as the empirical application for teaching regression with a binary dependent variable(logit and reasoning,all can be understood with only a single introductory course in econom- cs.and many can be understood without any previous economics coursework Thus the instructor can focus on teaching econometrics,not microeconomics o macroeconomics. We treat all our empirical applications seriously and in a way that shows stu dents how they can learn from data but at the same time be self-critical and aware of the limitations of empirical analyses.Through each application,we teach stu dents to explore alternative specifications and thereby to assess whether their sub- stantive findings are robust.The questions asked in the empirical applications are mportant,and we provide serious and,we think,credible answers.We encourag students and instructors to disagree,however,and invite them to reanalyze the
This edition has several smaller changes. For example, we now introduce realized volatility as a complement to the GARCH model when analyzing time series data with volatility clustering. In addition, we now extend the discussion (in a new general interest box) of the historical origins of instrumental variables regression in Chapter 12. This treatment now includes a first-ever reproduction of the original derivation of the IV estimator, which was in a letter from Philip Wright to his son Sewall in the spring of 1926, and a discussion of the first IV regression, an estimate of the elasticity of supply of flaxseed. Solving Teaching and Learning Challenges Introduction to Econometrics differs from other texts in three main ways. First, we integrate real-world questions and data into the development of the theory, and we take seriously the substantive findings of the resulting empirical analysis. Second, our choice of topics reflects modern theory and practice. Third, we provide theory and assumptions that match the applications. Our aim is to teach students to become sophisticated consumers of econometrics and to do so at a level of mathematics appropriate for an introductory course. Real-World Questions and Data We organize each methodological topic around an important real-world question that demands a specific numerical answer. For example, we teach single-variable regression, multiple regression, and functional form analysis in the context of estimating the effect of school inputs on school outputs. (Do smaller elementary school class sizes produce higher test scores?) We teach panel data methods in the context of analyzing the effect of drunk driving laws on traffic fatalities. We use possible racial discrimination in the market for home loans as the empirical application for teaching regression with a binary dependent variable (logit and probit). We teach instrumental variable estimation in the context of estimating the demand elasticity for cigarettes. Although these examples involve economic reasoning, all can be understood with only a single introductory course in economics, and many can be understood without any previous economics coursework. Thus the instructor can focus on teaching econometrics, not microeconomics or macroeconomics. We treat all our empirical applications seriously and in a way that shows students how they can learn from data but at the same time be self-critical and aware of the limitations of empirical analyses. Through each application, we teach students to explore alternative specifications and thereby to assess whether their substantive findings are robust. The questions asked in the empirical applications are important, and we provide serious and, we think, credible answers. We encourage students and instructors to disagree, however, and invite them to reanalyze the Preface 29 A01_STOC4455_04_GE_FM.indd 29 06/12/18 10:52 AM