175k views
2 votes
Intergenerational income mobility

Economists and sociologists often research the extent to which the incomes of parents predict the
income of their children to learn about the intergenerational transmission of economic success.
A standard model is of the form
kidinc, = B + B,mominc, + B₂dadinc, + &,,
where kidinc, is the child's income in adulthood, mo min c, is the mother's income and dadinc,
is the father's income.
Use the following regression output to answer the next few questions. Assume that all of
the income variables are measured in thousands of dollars so that, for example, a value of
10 corresponds to $10,000.
regress kidinc momine dadine;
.
Source I
Total I
Model I 3066.03552
2
Residual I 23864.5269 247
kidinc |
SS
mominc I
dadinc I
cons I
df
Coef.
1533.01776
96.617518
26930.5625 249 108.154869
MS
Std. Err.
.2484074
.1123418
.3421202 .0637471
9.648641 1.734021
t
P>ltl
2.21 0.028
5.37 0.000
5.56 0.000
Number of obs=
F( 2,
247) =
Prob > F
=
R-squared
Adj R-squared =
Root MSE
=
250
15.87
0.0000
0.1138
0.1067
9.8294
[95% Conf. Interval]
.0271373
.216563
6.233287
4696774
4676774
13.06399
1. (10 points) What are the values of B,₁, and for this sample and describe in words their
meanings?
2. (5 points) What is the predicted income for a child whose parents both had zero income?
What calculation would you perform to determine the predicted value of income for someone
whose parents both earned $40,000 per year? You do not need to perform the calculation, just
make it clear which numbers would get added to, subtracted from, multiplied by or divided by
which other numbers.
3. (10 points) Based on the results, is there a statistically significant relationship between father's
income and children's subsequent adult income? How do you know? (Describe the procedure

Intergenerational income mobility Economists and sociologists often research the extent-example-1
User Hedede
by
7.7k points

1 Answer

5 votes

Answer:

The values of B₀, B₁, and B₂ for this sample are as follows:

B₀ (cons): 108.154869 (in thousands of dollars)

B₁ (mominc): 96.617518

B₂ (dadinc): 26930.5625

Interpretation:

B₀ (cons) represents the intercept, which is the child's income in adulthood when both mother's income (mominc) and father's income (dadinc) are zero. In this case, the child's income would be approximately $108,155 (in thousands of dollars).

B₁ (mominc) represents the coefficient for the mother's income. It indicates that for every $1,000 increase in the mother's income, the child's income is expected to increase by approximately $96.62 (in thousands of dollars).

B₂ (dadinc) represents the coefficient for the father's income. It suggests that for every $1,000 increase in the father's income, the child's income is expected to increase by approximately $26.93 million (in thousands of dollars). Please note that there seems to be a typo in the output; the value is likely meant to be $26.93.

Predicted income for a child whose parents both had zero income:

To calculate the predicted income for a child whose parents both had zero income, we substitute mominc = 0 and dadinc = 0 into the regression model:

kidinc = B₀ + B₁ * mominc + B₂ * dadinc

kidinc = 108.154869 + 96.617518 * 0 + 26930.5625 * 0

kidinc = 108.154869 (in thousands of dollars)

The predicted income for this child would be approximately $108,155.

Predicted income for a child with parents earning $40,000 per year:

To determine the predicted value of income for someone whose parents both earned $40,000 per year, we substitute mominc = $40,000 and dadinc = $40,000 into the regression model:

kidinc = B₀ + B₁ * mominc + B₂ * dadinc

kidinc = 108.154869 + 96.617518 * 40 + 26930.5625 * 40

(Note: The values of B₁ and B₂ need to be converted to dollars, not thousands of dollars, since the income variables are measured in thousands of dollars in the model.)

Is there a statistically significant relationship between father's income and children's subsequent adult income?

Yes, based on the results, there is a statistically significant relationship between father's income (dadinc) and children's subsequent adult income (kidinc). We can know this from the t-values and associated p-values for the coefficients in the regression model.

In this case, the t-value for B₂ (dadinc) is 5.56, and the associated p-value is less than 0.001 (given as 0.000 in the output). Since the p-value is below the common significance level of 0.05, we can reject the null hypothesis and conclude that there is a significant relationship between father's income and children's subsequent adult income.

Step-by-step explanation:

User Dzmitry Paliakou
by
8.4k points