ECN6540 Econometric Methods Autumn Semester 2021/22
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
Autumn Semester 2021/22
ECN6540 Econometric Methods
1. The saving behaviour of individuals is modelled using UK cross sectional data for 2017 from Understanding Society based upon 18,117 employees. The table below describes the variables in the data.
Variable Definitions
-----------------------------------------------------------------------------------------------------
saver = 1 if saved last month, 0 otherwise
lsaved = natural logarithm of the amount saved last month
work_fin = 1 if employed in financial sector, 0 otherwise
ghealth = 1 if currently in good or excellent health, 0 otherwise
sex = 1 if male, 0=female
lincome = natural logarithm of income last month
age = age of individual in years
agesq = age squared
degree = 1 if university degree, 0 = below degree level education
-----------------------------------------------------------------------------------------------------
a. The following Stata output shows an analysis of modelling the probability that an individual saved in the previous month using a Logit regression. Summary statistics on variables used in the analysis are also provided.
logit saver work_fin ghealth sex lincome |
|
|
|
Logistic regression |
Number of obs LR chi2(4) Prob > chi2 |
= = = |
18,117 868.37 0.0000 |
Log likelihood = -11932.135 |
Pseudo R2 |
= |
0.0351 |
saver | + |
Coef. |
Std. Err. |
z |
P> |z | |
[95% Conf. |
Interval] |
|
.4358358 |
.0798033 |
5.46 |
0.000 |
.2794242 |
.5922474 |
||
work_fin ghealth sex lincome _cons |
| | | | | |
||||||
.4841934 |
.0309071 |
15.67 |
0.000 |
.4236166 |
.5447701 |
||
-.308088 |
.0319239 |
-9.65 |
0.000 |
-.3706578 |
-.2455182 |
||
.5105422 |
.0249364 |
20.47 |
0.000 |
.4616678 |
.5594165 |
||
-4.296774 |
.1867008 |
-23.01 |
0.000 |
-4.662701 |
-3.930848 |
sum work_fin ghealth sex lincome
Variable | Obs Mean Std. Dev. Min Max
-------------+---------------------------------------------------------
work_fin | |
18,117 |
.0388033 |
.1931313 |
0 |
1 |
ghealth | |
18,117 |
.5189601 |
.4996542 |
0 |
1 |
sex | |
18,117 |
.4681791 |
.4990002 |
0 |
1 |
lincome | |
18,117 |
7.563981 |
.7368259 |
.0861777 |
9.847781 |
i) Showing your calculations in full, find the marginal effects evaluated at the mean from the above output.
ii) Provide an economic interpretation of the marginal effects found in (a(i)).
b. Using the same data the amount saved is estimated by a Tobit regression censoring on zero savings. The Stata output is shown below.
tobit lsaved age agesq lincome sex degree, ll(0)
Tobit regression
Limits: lower = 0
upper = +inf
Number of obs =
Uncensored = Left-censored = Right-censored =
18,117
7,744
10,373
0
|
LR chi2(5) Prob > chi2 |
= = |
1016.22 0.0000 |
Log likelihood = -30557.612 |
Pseudo R2 |
= |
0.0164 |
-------------------------------------------------------------------------------
lsaved | Coef. Std. Err. t P> |t | [95% Conf. Interval]
--------------+----------------------------------------------------------------
age |
| |
-.2763257 |
.0261007 |
-10.59 |
0.000 |
-.3274857 |
-.2251658 |
agesq |
| |
.0030572 |
.0003117 |
9.81 |
0.000 |
.0024463 |
.0036681 |
lincome |
| |
1.878912 |
.0749269 |
25.08 |
0.000 |
1.732048 |
2.025775 |
sex |
| |
-.847986 |
.0922964 |
-9.19 |
0.000 |
-1.028896 |
-.6670763 |
degree |
| |
1.033757 |
.0996813 |
10.37 |
0.000 |
.8383718 |
1.229142 |
_cons |
| |
-8.708358 |
.6246082 |
-13.94 |
0.000 |
-9.932649 |
-7.484066 |
--------------+----------------------------------------------------------------
/sigma | 5.240645 .0493397 5.143935 5.337355
-------------------------------------------------------------------------------
i) Calculate the predicted monthly savings for the following individual: aged 40, gross income last month was £4,000, female, highest educational qualification degree level. [5 marks]
ii) For the individual described in b(i) what is the probability that they saved between £10 and £1,000 per month? [20 marks]
c. An alternative approach to modelling the amount saved per month is to use the Heckman sample selection estimator. The Stata output is shown below.
heckman lsaved age agesq lincome sex degree, select(saver = work_fin ghealth sex lincome)
Heckman selection model
(regression model with sample selection)
Log likelihood = -22844.85
Number of obs
Selected
Wald chi2(5)
Prob > chi2
18,117
7,744
10,373
728.69
0.0000
| + |
Coef. |
Std. Err. |
z |
P> |z |
|
[95% Conf. |
Interval] |
lsaved | age | -.1023551 agesq | .0011838 lincome | .3701998 sex | .21111 degree | .27608 _cons | 4.84605 |
.0066568 .0000795 .0284069 .0276236 .0247392 .2602918 |
-15.38 14.89 13.03 7.64 |
2023-01-14