What is Econometrics? Why Study Econometrics? Steps in an The Nature of Econometrics and Economic Data Empirical Analysis The Structure of Economic Data Caio Vigo Causality and the Notion of Ceteris The University of Kansas Paribus Department of Economics Fall 2019 These slides were based on Introductory Econometrics by Jeffrey M. Wooldridge (2015) 1 / 38 Topics What is Econometrics? Why Study Econometrics? Steps in an Empirical 1 What is Econometrics? Analysis Why Study Econometrics? The Structure of Economic Data 2 Steps in an Empirical Analysis Causality and the Notion of Ceteris Paribus 3 The Structure of Economic Data 4 Causality and the Notion of Ceteris Paribus 2 / 38 What is Econometrics? What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis • Econometrics is the set of tools by which economists, and others in the social The Structure of Economic sciences, analyze data. We can use econometrics to: Data • Causality and Estimate economic relationships; the Notion of Ceteris • Test economic theories; Paribus • Evaluate government and business policy. 3 / 38 What is Econometrics? What is Econometrics? Why Study Econometrics? Econometrics focuses on problems inherent in analyzing data generated by Steps in an Empirical individuals, firms, and other entitities acting strategically, and interacting with one Analysis another. The Structure of Economic Data Causality and • For example: the Notion of Ceteris Paribus • Does higher school spending is related with higher SAT/ACT scores? • What are the effects to the US economy if we raise our tariffs? • What is the effect of a 20-week training program on worker’s hourly wage? • What are the effects on crime rates if we legalize marijuana? 4 / 38 What is Econometrics? What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis • A simple correlation analysis might not be sufficient because causality can be The Structure difficult to infer. of Economic Data • In economics, theory and empirical analysis are both important. Causality and the Notion of Ceteris Paribus • An empirical analysis uses data to test a theory, estimate an economic relationship, or determine the effects of a policy or intervention. Econometrics allows us to analyze data using formal statistical methods. 5 / 38 What is Econometrics? What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis The Structure of Economic Data Causality and the Notion of Ceteris Paribus 6 / 38 Is Econometrics = Statistics? What is Econometrics? Why Study Econometrics? Steps in an Empirical • Econometrics is its own discipline (separate from statistics) mainly because there Analysis The Structure exists the following difference: of Economic Data Causality and the Notion of Ceteris Paribus Experimental Data 6= Nonexperimental Data 7 / 38 Is Econometrics = Statistics? What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis • Experimental data: The Structure of Economic Data • Data from controlled experiments; Causality and the Notion of • Common in the natural sciences (physics, chemistry, ...) and in the biomedical Ceteris Paribus fields; • However, harder to find or generate in the social sciences (although some exist). 8 / 38 Is Econometrics = Statistics? What is Econometrics? Why Study Econometrics? • Nonexperimental data Steps in an Empirical Analysis • The Structure These are data sets collected in a passive manner, after we observe outcomes on of Economic Data individuals, firms, schools, and so on. Causality and the Notion of Ceteris • We just “observe” the data without having any control over it,i.e., we simply Paribus act as “observers”of what has happened and then try to learn from what we observe. • Other names for nonexperimental data: observational or retrospective data. 9 / 38 Why Study Econometrics? What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis • Important to be able to apply economic theory to real world data. The Structure of Economic Data • Theory may be ambiguous as to the effect of some policy change, and in any case Causality and theory rarely tells us how large the effect might be. the Notion of Ceteris Paribus • Forecasting economic variables (inflation, interest rates, housing starts, and so on) is important, too. 10 / 38 Topics What is Econometrics? Why Study Econometrics? Steps in an Empirical 1 What is Econometrics? Analysis Why Study Econometrics? The Structure of Economic Data 2 Steps in an Empirical Analysis Causality and the Notion of Ceteris Paribus 3 The Structure of Economic Data 4 Causality and the Notion of Ceteris Paribus 11 / 38 Steps for a Successful Empirical Study What is Econometrics? Why Study Econometrics? Steps for a Successful Empirical Study Steps in an Empirical Analysis The Structure Step 1: Carefully pose a question. of Economic Data Step 2: Specify an economic or conceptual model. Causality and the Notion of Ceteris Paribus Step 3: Turn the economic model into an econometric model. Step 4: Collect data on the variables and use statistical methods to estimate the parameters, construct confidence intervals for the parameters, and test hypotheses. 12 / 38 Step 2. Specify an economic model What is Econometrics? Why Study Step 2. Specify an economic model, or at least a conceptual model, to study the Econometrics? Steps in an phenomenon of interest. Formal economic modeling (such as utility maximizaton) is Empirical often used, but one can get by with careful economic reasoning that is less formal. Analysis The Structure of Economic Example Data To study the effects of job training on worker productivity, where productivity is Causality and the Notion of measured by observed hourly wage, we can start with an equation such as Ceteris Paribus wage = f(educ, exper, training) where educ is a measure of schooling, exper is a measure of workforce experience, and training is a measure of time spent in job training (the variable of most interest). 13 / 38 Step 3: Turn the economic model into an econometric model What is Econometrics? Why Study Econometrics? Example Steps in an Empirical We can specify an econometric model for the wage/job training example as Analysis The Structure of Economic wage = β0 + β1educ + β2exper + β3training + u Data Causality and the Notion of Ceteris Paribus • The constants β0, β1, β2, and β3 (“the betas”) are the parameters of the model, and it is these (especially β3 in this example) that we hope to estimate. • Ideally we will be able to collect data on wage, educ, exper, and training from a large group of working people. 14 / 38 Step 3: Turn the economic model into an econometric model What is Econometrics? Why Study • The last term in the equation Econometrics? Steps in an Empirical wage = β + β educ + β exper + β training + u Analysis 0 1 2 3 The Structure of Economic Data is u. It’s called the error term or disturbance. Causality and the Notion of Ceteris • It plays a very important role in econometrics. Paribus • It represents all other factors that can affects someone’s wage, including native intelligence, motivation, and so on. • The error term can also capture measurement problems in one or more of the variables. 15 / 38 Step 3: Turn the economic model into an econometric model What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis • We will want to use statistical methods, and data, to estimate and test hypotheses The Structure about the parameters. of Economic Data Causality and • For example, the hypothesis that job training has no effect on wage is β3 = 0. the Notion of Ceteris Paribus • The hypothesis that one year of experience is worth one year of education is β1 = β2. 16 / 38 Steps for a Successful Empirical Study What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis Step 1: Carefully pose a question. The Structure of Economic Step 2: Specify an economic or conceptual model. Data Causality and the Notion of Step 3: Turn the economic model into an econometric model. Ceteris Paribus Step 4: Collect data on the variables and use statistical methods to estimate the parameters, construct confidence intervals for the parameters, and test hypotheses. 17 / 38 Topics What is Econometrics? Why Study Econometrics? Steps in an Empirical 1 What is Econometrics? Analysis Why Study Econometrics? The Structure of Economic Data 2 Steps in an Empirical Analysis Causality and the Notion of Ceteris Paribus 3 The Structure of Economic Data 4 Causality and the Notion of Ceteris Paribus 18 / 38 The Structure of Economic Data What is Econometrics? Why Study Econometrics? Steps in an • Economic data sets come in a variety of types. Empirical Analysis Types of Economic Data The Structure of Economic • Cross-Sectional Data Data Causality and the Notion of • Time Series Data Ceteris Paribus • Pooled Cross Sections • Panel or Longitudinal Data 19 / 38 Cross-Sectional Data What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis • Data are collected on individuals, families, firms, schools, or some other units at a The Structure given point in time. of Economic Data Causality and • Time is not important. It does not play a crucial role. the Notion of Ceteris Paribus • We will assume that a cross-sectional data set represents a random sample. What is random sample again? Example 20 / 38 Cross-Sectional Data What is Econometrics? Why Study Econometrics? Steps in an Empirical Analysis The Structure The Importance of Random Sampling of Economic Data • Random sampling (with replacement) generates observations that are i.i.d. Causality and the Notion of Ceteris • Intuitively, a random sample is representative of the population of interest, Paribus and gives us the best chance of learning about the population. 21 / 38 Cross-Sectional Data What is Econometrics? Why Study Econometrics? Steps in an Empirical • Ordering of the individuals is arbitrary and unimportant. Analysis The Structure of Economic • Does not matter whom we label observation 2, or observation 5, or observation Data 136 and so on. Causality and the Notion of Ceteris Paribus • What happens if I shuffle the dataset? Nothing would be lost be if we randomly rearrange the order of the individuals.