Scribd
Upload
38 views3 pages

Model Solution - Econ f241 Mid

Uploaded by

Dwayne Neto
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
38 views3 pages

Model Solution - Econ f241 Mid

Uploaded by

Dwayne Neto
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
You are on page 1/ 3

ECONOMETRIC METHODS [ECON F241] MID-SEMESTER EXAMINATION

SEMESTER II 2021-2022
Writing Time: 9:00 AM -10:30 AM TOTAL MARKS: 30
Attempt all questions

1.Consider the model: Sales  1   2 Income  season   i . The data on season corresponds to spring,
summer, autumn, and winter. The analyst proceeds to use a dummy variable ‘S’. That is 0 for spring, 1 for
summer, 2 for autumn, and 3 for winter. That would be, Sales  1   2 Income   3 S   i .
Is it appropriate to represent the seasonal situation by using one dummy variable with four different values?
Verify your claim algebraically. (5)

S  0; Sales  1  B2 Income  0
S  1; Sales  1  B2 Income  3  1
Ans.
....
1  0  2  1  3  2  3

A restrictive assumption.

2. The following estimated equation was obtained by OLS regression using quarterly data for 1960 to 1975
inclusive (n=64). (2+2+1)

Yˆt  2.20  0.104 X 1t  3.48 X 2t  0.34 X 3t


(3.4) (0.005) (2.2) (0.15)

Standard errors are in parentheses, the explained sum of squares was 112.5 and the residual sum of squares
was 19.5.
a) Which of the slope coefficients are statistically significantly different from 0 at 5% level of
significance (write the hypothesis, computed test statistic and the critical values, and the decision).
Slope of X1 and X3 are significant. (critical t value is 2).
b) Calculate the values of R2 and adjusted R2 and interpret.
R2 is 0.8522; adjusted R2 is 0.844
c) Calculate the F-value and interpret it.
F=115.384

3.
I) In the regression of Yi on X1i and X2i, if all values of X2i are identical, then the variance of estimated
coefficient of X2i will be,

a) zero; b) infinite; c) unity.

Choose the correct option and explain your answer. (3)

II) Discuss how you would overcome the multicollinearity problem by following the dropping variable
approach. When is this approach justifiable? (Derivation not required) (2)

Relevance of MSE as discussed in class.


4. How would you examine the relevance of an additional explanatory variable in the context of multiple
regression exercises? Explain the test procedure and the decision rules. (5)

( ESSNEW  ESSOLD ) / 1
F= (in case of two explanatory variables and intercept included).
RSSNEW / n  3

5. Consider the model in the usual regression framework as, (5)

yi  xi  i . If the regressand is binary, it is a LPM. Assuming E (  i )  0, the conditional expectation


E ( yi xi )  xi . This has to be interpreted in this case as the probability that the event will occur given xi .
Using the structure of the LPM, prove that the variance of the error term  i ultimately depends on the values
of x . (Derivation required)
Yi i f(  i )
0 -  xi 1-Pi
1 1-  xi Pi

Show as discussed in class, Var(  i )=E(  i 2)=E(Yi) [1- E(Yi)]

6. Consider the following data set: (5)

Y x2 x3
1 2 4
2 0 2
3 4 0
4 6 12
5 8 16
Y is the dependent variable. x2 and x3 are independent variables. The correlation matrix is given below:

y x2 x3
y 1
x2 0.9 1
x3 0.782488 0.828517 1

The excel output of the regression model (Y on x2 and x3) is given below. Some information is missing
labeled (a) to (f) . Fill in these missing values and comment (write the hypothesis and decision) on the
statistical significance of x2 and x3 at 5% level of significance.

Regression Statistics
Multiple R 0.902399205
R Square 0.814324324
Adjusted R Square 0.628648649
Standard Error 0.963523938
Observations 5
ANOVA
df SS MS F

Regression 2 8.143243 4.071622 (4.385)


Residual 2 1.856757 0.928378
Total 4 10
Standard
Coefficients Error t Stat
Intercept 1.210810811 0.748021 (1.6186)
x2 (0.40135) (0.2720) 1.475204

x3 (0.0270) (0.1252) 0.215822

Coefficient of X2 and X3 not statistically significant.


**************************************

Critical values of t (Two-tailed test)


Degrees of freedom 0.20 0.10 0.05
1 3.078 6.314 12.706
2 1.886 2.920 4.303
3 1.638 2.353 3.182
50 1.299 1.676 2.009
60 1.296 1.671 2.000
70 1.294 1.667 1.994

You might also like