Posted: February 5th, 2015

USE OF ECONOMIC DATA

Paper, Order, or Assignment Requirements

Please follow the requirements and analysis all parts

ECON 3210A: USE OF ECONOMIC DATA

FALL 2014

ASSIGNMENT # 2

Prof. Sadia M. Malik

Date Assigned: Nov 17, 2014

Due Date: Dec 3, 2014

Total Possible Points: 80

Total Weight in Grade Evaluation: 10%

Question 1: : http://www.pearsonhighered.com/stock_watson

In assignment # 1, you used the data file Earnings_and_Height, and estimated a relatively large and statistically significant effect of a worker’s height on his or her earnings. One explanation for this result is the omitted variable bias. Height is correlated with an omitted factor that affects earnings. Some researchers suggest that cognitive ability (or intelligence) is the omitted factor. The mechanism they describe is straightforward: Poor nutrition and other harmful environmental factors in utero and early childhood development, have on average, deleterious effects on both cognitive and physical development. Cognitive ability affects earnings later in life and thus is an omitted variable in the regression. Unfortunately, there is no direct way to measure cognitive ability. However, the years of education may serve as a control variable for cognitive ability.

Suppose that the mechanism described above is correct. Explain how this leads to omitted variable bias in the OLS regression of Earnings on Height. Does this bias lead the estimated slope to be too large or too small?

How would you test for the presence of omitted variable bias on the coefficient of earnings? Suggest one way to do so and show the presence or absence of this bias using the statistical software that you have chosen to do your assignment.

Now include the variable measuring the years of education (educ) as an additional regressor in the regression of earnings on height. Comment on the size of the coefficient on height (Does it support your theoretical answer in (a)?

Check for the omitted variable bias now after including the education variable. Has the bias been eliminated or accentuated?

Question # 2: Using the same data as question #1, use the years of education variable (educ) to construct four indicator variables for whether a worker has less than a high school diploma (LT_HS=1 if educ<12, 0 otherwise); a high school diploma (HS=1 if educ=12, 0 otherwise); some college (Some_Col=1 if 12<educ<16, 0 otherwise); or a bachelor’s degree or higher (College=1 if educ≥16, 0 otherwise). Focussing

Run a regression of earnings on height including LT_HS, HS, and Some_Col as control variables. Interpret the coefficients on the indicator (dummy/binary) variables.

Why is the coefficient in LT_HS more negative than the coefficient on HS, which in turn is more negative than Some_Col? What do the coefficients on dummy variables measure in this example?

The regression omits the control variable College. Why?

Test the joint null hypothesis that the coefficients on the education variables are equal to zero.