lecture-11

lecture-11 - ECON 103, Lecture 11: Functional Form and...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ECON 103, Lecture 11: Functional Form and Dummy Variables Maria Casanova February 18th (version 0) Maria Casanova Lecture 11 Requirements for this lecture: Chapter 8 of Stock and Watson Maria Casanova Lecture 11 1. Functional Form of Regression Models In this course we cover linear regressions . By linear we mean that they are linear in parameters They may or may not be linear in the X s The Y variable does not need to be linear either. Maria Casanova Lecture 11 1.1 Linear Model Ex1: Linear Model It is linear in variables Y = + 1 X + 1 gives the increase in Y given a unit increase in X Maria Casanova Lecture 11 1.2 Log-Linear Model Ex2: Log-Linear Model It is not linear in X Y = AX 1 However, we can linearize it by taking the natural ln on both sides: ln Y = ln ( AX 1 ) = ln A + 1 ln X ln Y = + 1 ln X If the least squares assumptions are satisfied, we can estimate and 1 by OLS from a regression like: ln Y = + 1 ln X + Maria Casanova Lecture 11 1.2 Log-Linear Model In the log-linear model 1 measures the percentage change in Y for a given percentage change in X (that is, the the elasticity of Y with respect to X ). For example, in the following model 1 is the price-elasticity of demand : ln Y = + 1 ln X + , where: Y = quantity demanded X = price 1 = d ln Y d ln X = dY / Y dX / X = p Y Y X X = % increase in Y % increase in X ! In this model, when we conduct hypothesis tests about 1 we are testing hypothesis about the price-elasticity of demand. Maria Casanova Lecture 11 1.3 Semilog Model Ex3: Semilog Model Only one variable appears in log form. ln Y = + 1 X + In this model 1 measures the percentage change in Y given a unit change in X : 1 = d ln Y dX = dY / Y dX Y Y X = % increase in Y Increase in X ! When are we interested in computing the percentage change in one variable (e.g. Y ) per unit increase of other variable (e.g. X )? Maria Casanova Lecture 11 1.3 Semilog Model 1 Example: wage equation ln wage = + 1 educ + , where educ is measured in years. In this case, 1 measures the percentage change in income for a one year increase in education. Maria Casanova Lecture 11 1.3 Semilog Model 2 Example: demand equation ln Q = + 1 P + We know that 1 = d ln Q dP = dQ / Q dP Remember that the price elasticity of demand was: p = dQ / Q dP / P In this case the elasticity of demand is: p = 1 P that is, the elasticity varies for different price levels....
View Full Document

This note was uploaded on 03/15/2010 for the course ECON 103 taught by Professor Sandrablack during the Winter '07 term at UCLA.

Page1 / 31

lecture-11 - ECON 103, Lecture 11: Functional Form and...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online