This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 1 / 21 Introduction to Econometrics Econ 322 Fall, 2010 Lecture 9: Simple Linear Regression October 3, 2010 Topics Covered triangleright Topics Covered An Empirical Question The Regression Equation Estimators of β and β 1 Why OLS? Predicted values and residuals Our Earnings Example Statistical Properties of Our Estimator Probability framework for the SLRM 2 / 21 1. The Simple Linear Regression Model 2. Estimation of the Parameters of the SLRM 3. Interpretation of the estimates An Empirical Question Topics Covered triangleright An Empirical Question The Regression Equation Estimators of β and β 1 Why OLS? Predicted values and residuals Our Earnings Example Statistical Properties of Our Estimator Probability framework for the SLRM 3 / 21 square How does education affect earnings? – how do we measure education? triangleright triangleright triangleright square the answer to above question is usually determined by the data that we have square first two are easy to observe, the last one is hard. How do we quantify onthe job training? – how do we measure earnings? triangleright triangleright triangleright An Empirical Question (cont) Topics Covered triangleright An Empirical Question The Regression Equation Estimators of β and β 1 Why OLS? Predicted values and residuals Our Earnings Example Statistical Properties of Our Estimator Probability framework for the SLRM 4 / 21 Consider the following table: An Empirical Question (cont) Topics Covered triangleright An Empirical Question The Regression Equation Estimators of β and β 1 Why OLS? Predicted values and residuals Our Earnings Example Statistical Properties of Our Estimator Probability framework for the SLRM 5 / 21 square what do we observe from the table? – mean schooling is 13.5 years – mean hourly earnings is $15.51 per hour – looking at percentiles we see triangleright hourly earnings increase together with years of schooling triangleright maybe there is a relationship here? square we next look at a scatter plot between years of schooling and hourly earnings – we see clumping in years of education data – there appears to be a positive relationship between schooling and earnings The Regression Equation Topics Covered An Empirical Question triangleright The Regression Equation Estimators of β and β 1 Why OLS? Predicted values and residuals Our Earnings Example Statistical Properties of Our Estimator Probability framework for the SLRM 7 / 21 square it appears that there is a relationship between earnings and education square how do we formally model this relationship?...
View
Full Document
 Fall '11
 LANDONLANE
 Econometrics, Linear Regression, Regression Analysis, OLS, empirical question, statistical properties, Probability framework

Click to edit the document details