7807
R project
Due by 5/15
There are two sets of questions. Make sure to present your estimation results using the R
package stargazer().
Data
The data set 401ksubs.RData contains information on net financial wealth (nettfa), age of
survey respondent (age), annual family income (inv), family size (fsize), a binary variable
for eligibility in a 401(k) plan (e401k), participation in certain pension plans for people in
the United States and other variables. The wealth and income variables are both recorded in
thousands of dollars.
Part 1
**Use only the data for single-person households, i.e., fsize=1 to answer the questions in
Part 1.
1. How many single-person households are there in the data set?
2. Use OLS to estimate the model
nettf ai = ß0 + ß1inci + ß2agei + ui (1)
and interpret the slope coefficients. Is there any sign contrary to your expectation?
3. Does the intercept from the regression have an interesting meaning? Explain.
4. Find the p-value for the test H0 : ß2 = 1 against H1 : ß2
1% significance level?
5. What is the youngest age of people in this sample? How many people are at that age?
6. Use OLS to estimate the the model
nettf ai = ß0 + ß1inci + ß2agei + ß3age2
i + ui
. (2)
Are you concerned that the coefficient on age is negative? Explain.
7. Because the youngest people in the sample are 25, it makes sense to think that, for
a given level of income, the lowest average amount of net total financial assets is at
age 25. Recall that the partial effect of age on nettfa is ß2 + 2ß3age, so the partial
effect at age 25 is ß2 + 2ß3(25) = ß2 + 50ß3; call this ?2. Find ?b2 and obtain the
two-sided p-value for testing H0 : ?2 = 0. You should conclude that ?b2 is small and
very statistically insignificant. [Hint: One way to do this is to estimate the model
nettf a = a0 + ß1inc + ?2age + ß3(age – 25)2 + u, where the intercept, a0, is different
from ß0. There are other ways, too.]
8. Because the evidence against H0 : ?2 = 0 is very weak, set it to zero an estimate the
model
nettf ai = a0 + ß1inci + ß3(agei – 25)2 + ui
. (3)
In terms of goodness-of-fit, does this model fit better than that the model in (2)?
9. For the estimated equation in (3), set inc = 30 and graph the relationship between
nettfa and age, but only for age = 25. Describe your finding.
Attachments:
Project.pdf
401ksubs–1-.zip
