Topic: Gender Earnings Differential in the Financial Industry in Guidelines:
1. First, create dummy variables for Education, Marriage, Immigrant and Occupation in the “2016 HK Fine Industry Micro Data “excel data in order to do Part A, B, C and D.
2. UseanysoftwaretodoPartA,B,CandD.UseresultsPartA,B,Ctodothe decomposition in Part D.
Part A: Generate Sample Statistic (sample means and standard errors of the variables)
Copyright By PowCoder代写 加微信 powcoder
– Follow Sample Paper Page 13
Part B: Mincer Earnings Function (with Ordinary Least Square Method):
– Generate regression result, follow Sample Paper Page 16-17
InY = α + ∑ βm0 Educationm + β Experience + β Experience 2 mmi im1 mm2 m
+ ∑ βm3Marriagem + β Immigrant + ∑ βm5Occupationm + ε
i i m4 m i i m
InY = α + ∑ βf0 Educationf + β Experience + β Experience 2 + ∑ βf3Marriagef f f i i f1 f f2 f i i
Immigrant + ∑ βf5Occupationf + ε f4 f i i f
InYm and InYf αm and αf
Explanations
Male and female respectively
Natural logarithm of monthly income from main employment Intercept of the function
Corresponding vectors of estimated coefficients
βm0, βm3, βm5 and βf0, βf3, βf5 iii iii
βm1, βm2, βm4 and βf1, βf2, βf4
Corresponding estimated coefficients
∑ Educationm and ∑ Educationf ii
Vector of educational dummy variables:
“UPSEC” (Upper secondary level), “POSTSEC” (Post-secondary level), “UNIV” (University level) and “POSTGRAD” (Post-graduate or above)
Reference group: “LOWSEC” (Lower secondary or below)
Experience𝑚 and 2and Experiencef2
Working experience in years
Square of working experience in years
∑ Marriagem and ∑ Marriagef ii
Vector of marital dummy variables:
“MARRIED” (Married), “WIDOWED” (Widowed) and “DIV_SEP”
(Divorced or Separated)
Reference group: “NEV_MARRIED” (Never married)
Immigrantm and Immigrantf
Dummy variable of place of birth
“IMMIGRANT” (Birthplace not in )
Reference group: “LOCAL” (Birthplace in )
∑ Occupationmand ∑ Occupationf ii
Vector of industrial dummy variables:
“MANAGER” (Managers and administrators), “PRO” (Professionals), “ASSOPRO” (Associate professionals), “CLERK” (Clerical support workers), “SER_SALES” (Services and sales workers), and “PLANT” Reference group: “ELEM” (Elementary occupations)
Part C: Generate regression Results of Pooled Sample
Statistical residual (error)
– Pooled sample includes both men and women
– Follow Sample Paper Page 16-17
Part D: Neumark Decomposition Method:
– In this equation, β∗ are the estimated coefficients of returns to those objective i
characteristics of pooled sample while α∗ is the intercept of the pooled sample’s
regression.
– Generate the decomposition result, follow Sample Paper Page 20
̅̅∗̅m̅f ̅mm∗m∗ InYm −InYf =∑βi(Xi −Xi)+[∑Xi (βi −βi)+(α −α )]
̅f ∗ f ∗ f +[∑Xi(βi −βi)+(α −α)]
̅̅ InYm and InYf
̅m ̅f Xi and Xi
βmand βf (β∗) iii
αmand αf (α∗)
Explanations
Male and female respectively
Mean natural logarithm of monthly income from major employment Vector of mean individual objective characteristics (i.e., Education, Experience, Marriage, Immigrant and Occupation)
Vector of returns to objective characteristics (Non-discriminatory benchmark)
Intercept of the function (Non-discriminatory benchmark)
∗̅m ̅f ∑βi(Xi −Xi)
Portion of earnings differential contributed by the gender differences in objective characteristics – “Endowment’ component / Explained portion”
(Evaluate the gender differences at 𝛃∗ ) 𝐢
̅m m ∗ m ∗ [∑Xi (βi −βi)+(α −α )]
Portion of earnings differential contributed by pure male advantage – “Male advantage” component
̅𝐦 (Evaluatethedifferencesat𝐗𝐢 )
̅f ∗ f ∗ f [∑Xi(βi −βi)+(α −α)]
Portion of earnings differential contributed by pure female disadvantage –‘Female disadvantage’ component
̅𝐟 (Evaluate the differences at 𝐗𝐢 )
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com