计量经济学-第六章 多元回归分析：虚拟变量.ppt

第六章　多元回归分析：虚拟变量 Dummy Variables A dummy variable is a variable that takes on the value 1 or 0 Examples: male (= 1 if are male, 0 otherwise), south (= 1 if in the south, 0 otherwise), etc. Dummy variables are also called binary variables, for obvious reasons A Dummy Independent Variable Consider a simple model with one continuous variable (x) and one dummy (d) y = b0 + d0d + b1x + u This can be interpreted as an intercept shift If d = 0, then y = b0 + b1x + u If d = 1, then y = (b0 + d0) + b1x + u The case of d = 0 is the base group, then d0=E(y|x, d=1)-E(y|x, d=0) Dummies for Multiple Categories We can use dummy variables to control for something with multiple categories Wage determinations: wage=-1.57 - 1.81female+0.572educ+0.025exper+0.141tenure (0.72) (0.26) (0.049) (0.012) (0.021) n=526 R2=0.364 The coefficient of female (-1.81) means the wage of female is $1.81 less per hour than male workers after controlling other variables. wage=7.10 - 2.51female (0.21) (0.30) This means that the average male wage per hour is $7.10, and female’s wage is $2.51 less, which is $4.59 per hour. Is there significant wage difference btw men and women? Yes, it indeed is. Because the t-value of female is -2.51/0.30=-8.37 Log form log(wage)=0.501 – 0.301female+0.087educ+0.005exper+0.017tenure (0.102) (0.037) (0.0069) (0.016) (0.0030) n=526 R2=0.3923 Female is 30.1% less than men. The exact difference is log(wageF)-log(wageM)=-0.301, (wageF-wageM)/wageM=exp(-0.301)-1=0.3512=35.12% Example: Effects of Computer Ownership on College GPA Whether a student own a computer effect the performance of the student? colGPA= b0 +d0 PC+b1hsGPA+b2ACT+u colGPA=1.26 +0.157PC+0.447hsGPA+0.0087ACT+u (0.33) (0.057) (0.094) (0.0105) n=141, R2=0.219 This means that a student who owns a computer has a predicted GPA about 0.16 points higher than