0% found this document useful (0 votes)
5 views8 pages

Assignment

The document presents a regression analysis on the factors affecting women's log wage using cross-sectional data. Key findings indicate that education, expected wage, and experience significantly increase wages, while age has no significant effect. The overall regression model is statistically significant, explaining approximately 35.08% of the variation in log wage.

Uploaded by

s2110442120
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
5 views8 pages

Assignment

The document presents a regression analysis on the factors affecting women's log wage using cross-sectional data. Key findings indicate that education, expected wage, and experience significantly increase wages, while age has no significant effect. The overall regression model is statistically significant, explaining approximately 35.08% of the variation in log wage.

Uploaded by

s2110442120
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

ASSIGNMENT

ON
Subject : Economics

Course name : Computer Applications on Economics


Course No: ECO 424
Submitted By Submitted To
Name: Afroja Parvin Nitu Name: Nazmullah Bin Tariq
Roll no: 2112042206 Department of: Economics
Semester: 8th semester University of Rajshahi
Session: 2020-21
. Regression Result (Cross-Section Data:
MROZ)
My estimated regression model is:

lwage=β0+𝛽 1hours+β2age+β3educ+β4repwage+β5exper+β6expersq+u

Source SS df MS Number of obs = 428


F(5, 422) = 40.83
Model 72.8195825 5 14.5639165 Prob > F = 0.0000
Residual 150.507858 422 .356653693 R-squared = 0.3261
Adj R-squared = 0.3181
Total 223.327441 427 .523015084 Root MSE = .5972

lwage Coefficient Std. err. t P>|t| [95% conf. interval]

age .0046221 .0043663 1.06 0.290 -.0039602 .0132045


educ .0744174 .0130886 5.69 0.000 .0486904 .1001444
repwage .1298976 .0126184 10.29 0.000 .1050949 .1547003
exper .0250978 .0119148 2.11 0.036 .001678 .0485175
expersq -.0006294 .0003581 -1.76 0.080 -.0013333 .0000745
_cons -.5391775 .2486937 -2.17 0.031 -1.02801 -.0503448
Estimated Regression Equation

Lwage=−0.3014−0.0001598(hours)+0.0033(age)+0.0676(educ)+0.1418(repwage)+
0.0325(exper)−0.0007221(expersq)

2. Hypothesis Testing
(A) Individual Coefficient Tests
For each explanatory variable:

General Hypothesis

• Null Hypothesis (H₀): coefficient = 0


(the variable has no significant effect on log wage)
• Alternative Hypothesis (H₁): coefficient ≠ 0
(the variable significantly affects log wage)

(i) Hours Worked


• H₀: β₁ = 0
• H₁: β₁ ≠ 0

p-value = 0.0001

Decision:
Reject H₀.

Conclusion:

Hours worked significantly affects wage. The negative coefficient implies that an increase in
working hours slightly decreases log wage.

(ii) Age
• H₀: β₂ = 0
• H₁: β₂ ≠ 0

p-value = 0.4436

Decision:

Fail to reject H₀.

Conclusion:

Age has no statistically significant effect on wage.

(iii) Education
• H₀: β₃ = 0
• H₁: β₃ ≠ 0

p-value = 0.0000

Decision:

Reject H₀.

Conclusion:

Education significantly increases wage.

(iv) Expected Wage (repwage)


• H₀: β₄ = 0
• H₁: β₄ ≠ 0

p-value = 0.0000

Decision:

Reject H₀.

Conclusion:

Expected wage has a strong positive impact on actual wage.

(v) Experience
• H₀: β₅ = 0
• H₁: β₅ ≠ 0

p-value = 0.0064

Decision:

Reject H₀.

Conclusion:

Experience positively affects wage.

(vi) Experience Squared


• H₀: β₆ = 0
• H₁: β₆ ≠ 0

p-value = 0.0412

Decision:

Reject H₀.

Conclusion:
Experience squared is significant, indicating diminishing returns to experience.

(B) Overall Significance of the Model


Hypothesis

• H₀: β₁ = β₂ = β₃ = β₄ = β₅ = β₆ = 0
(all explanatory variables jointly have no effect)
• H₁: At least one β ≠ 0

Test Result

• F(6, 421) = 37.92


• Prob > F = 0.0000

Decision:

Reject H₀.

Conclusion:

The overall regression model is statistically significant.

3. Interpretation of Regression Results


Goodness of Fit
• R² = 0.3508

This means that about 35.08% of the variation in women’s log wage is explained by hours
worked, age, education, expected wage, and experience.

• Adjusted R² = 0.3416

This indicates the model has moderate explanatory power.

Variable Interpretation
Hours Worked

Coefficient = -0.0001598

Holding other variables constant, a one-hour increase in work reduces log wage by 0.016%.

This may indicate that women working longer hours are in lower-paying jobs.

Age

Coefficient = 0.0033

Age has a positive but statistically insignificant effect.

Thus, age alone does not meaningfully affect wage.

Education

Coefficient = 0.0676

A one-year increase in education raises log wage by approximately 6.76%, ceteris paribus.

This shows education improves earning capacity.

Expected Wage (repwage)

Coefficient = 0.1418

A one-unit increase in expected wage increases log wage by about 14.18%.

This indicates strong wage expectations are associated with higher earnings.

Experience

Coefficient = 0.0325

Initially, experience increases wage by about 3.25%.


This means more labor market experience improves productivity and wage.

Experience Squared

Coefficient = -0.0007221

The negative sign suggests diminishing returns to experience.

After some point, additional experience contributes less to wage growth.

You might also like