Lecture_12_Slides_933909009.pdf

Lecture_12_Slides_933909009.pdf - I NTRODUCTORY E...

Info icon This preview shows pages 1–11. Sign up to view the full content.

I NTRODUCTORY E CONOMETRICS Lecture 12 Spring 2017, Tsinghua University Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 1 / 45
Image of page 1

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

Dummy Variables Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 2 / 45
Image of page 2
O UTLINE 1 Binary Categorical Variables 2 Categorical Variables with More than Two Categories 3 Multiple Categorical Variables Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 3 / 45
Image of page 3

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

C ATEGORICAL V ARIABLES Think about the difference in average wages between men and women. Suppose you want to test whether men make more money than women That is you have the following null hypothesis H 0 : E ( W | Male ) = E ( W | Female ) where W is hourly earnings. How do you do this? Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 5 / 45
Image of page 4
You could take means for each group and calculate ¯ W m - ¯ W f se ( ¯ W m - ¯ W f ) 2 It turns out that there is an easier way. Suppose we have data on men’s and women’s wages. We want to run a regression, but how do we do that? 1 “Man” and “Woman” are categories, not numbers 2 To run a regression we can only take numerical variables. Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 6 / 45
Image of page 5

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

Solution: Turn it into a dummy variable . Define m i = ( 1 Person is male ; 0 Person is female. Now let’s see if regression analysis can be useful. We will think of this in a “ descriptive ” way. Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 7 / 45
Image of page 6
Let E ( W i | m i ) = β 0 + β 1 m i . Now notice that E ( W i | Male ) = E ( W i | m i = 1 ) = β 0 + β 1 E ( W i | Female ) = E ( W i | m i = 0 ) = β 0 Solving out this means that β 0 = E ( W i | Female ) β 1 = E ( W i | Male ) - E ( W i | Female ) Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 8 / 45
Image of page 7

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

Consequently, testing H 0 : E ( W | Male ) = E ( W | female ) is equivalent to testing H 0 : β 1 = 0 We already know how to do this. Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 9 / 45
Image of page 8
A DDING C ONDITIONING V ARIABLES But that isn’t all. We might be worried that women have less labor market experience than men. Therefore, we suspect that the potential difference in average wages between men and women may be due to the difference in experience . An interesting null hypothesis might be H 0 : E ( W | Male, Experience ) = E ( W | Female, Experience ) That is, comparing men and women with the same level of experience, do they earn the same amount of money? Shengjie Hong (SEM, Tsinghua) [email protected] Lecture 12 10 / 45
Image of page 9

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

This is easy to do, we just write the model as E ( W i | m i , Exp i ) = β 0 + β 1 m i + β 2 Exp i . Now notice that E ( W i | Male, Experience ) = E ( W i | m i = 1 , Experience ) = β 0 + β 1 + β 2 Exp i E ( W i | Female, Experience ) = E ( W i | m i = 0 , Experience ) = β 0 + β 2 Exp i Solving out this means that β 1 = E ( W i | Male, Experience ) - E ( W i | Female, Experience ) Again, testing whether H 0 : β 1 = 0 tests exactly what we want.
Image of page 10
Image of page 11
This is the end of the preview. Sign up to access the rest of the document.
  • Spring '16
  • Hong Shengjie

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern