NAME:

NAME: HINA COURSE: ECONOMETRICS

COURSE: ECONOMETRICS

STUDENT ID: 16255 PROGRAM: MBA (R)

STUDENT ID: PROGRAM: MBA (R)

Q.1

ANSWER
a) Model 1 is linear regression model and model 2 is quadratic regression model.
b) Model 1 can be used when there is a linear relationship between independent variable and
dependent variable, otherwise model 2 will be used.

m
er as
Explanation:

co
eH w
a) Model 1: Yt = β0 + β1t

o.
rs e
Model 1 is a linear econometric model. Since it has only one independent variable, it is a simple
ou urc
linear regression model. This model states that sales of automobiles is a linear function of time t.

On differentiating the model, we get dYt/dt = β1. This implies that the rate of change of sales of
o

automobiles does not depend on time t and it is constant over time.

aC s
vi y re

Model 2: Yt=α0+α1t+α2t2
Model is a quadratic model. It states that the sales of automobiles is a quadratic function of time.
ed d

On differentiating the model, we get dYt/dt = α1+2α2t. This implies that the rate of change of sales
ar stu

of automobiles depends on time t and it is not constant over time.

B) Model 1 is useful when we want to predict the effect of a variable on another variable. It is used
when the scatter plot is linear. If we can fit a particular type of curve in our data, then we can use
is

linear regression, i.e., model 1.

Th

But if the linear regression fails to provide an adequate fit, then we can use quadratic model or
model 2. When the relationship between independent and dependent variable is not linear, then
sh

we use non-linear regression.

This study source was downloaded by 100000830545516 from CourseHero.com on 11-13-2021 12:29:51 GMT -06:00

https://www.coursehero.com/file/74313839/Econometrics-paperdocx/
 Q.2

ANSWER

(a) The EViews3 output is as follows:

m
er as
co
eH w
o.
rs e
ou urc
o
aC s
vi y re
ed d
ar stu

(b)
is

One would expect β2, β3 and β6 to be positive and β4 and β5 to be negative.

Th

(c)
β2, β3 and β4 meet the expectations; the others do not.
sh

This study source was downloaded by 100000830545516 from CourseHero.com on 11-13-2021 12:29:51 GMT -06:00

https://www.coursehero.com/file/74313839/Econometrics-paperdocx/
 (d)
As the regression results show, X3, X4 and X6 are significant at the 5% level, X2 is significant at
the 10 % level, but X5 is statistically insignificant.
(e)
The overall model is statistically significant because the p-value is less than 5%.
(f)
Variance Inflation Factors
Date: 10/06/20 Time: 06:55
Sample: 1968 1983
Included observations: 16

m
er as
Coefficient Uncentered Centered

co
Variable Variance VIF VIF

eH w
C 1.436197 255.4541 NA

o.
X2_____GNP_ 1.44E-06 431.6878 6.905160
X3__HOUSING_START
S_ rs e
1.63E-07 76.17619 4.344945
ou urc
X4__UNEMPLOYEMEN
T_ 0.008047 62.36313 3.967917
X5__PRIME_RATE_LA
G__6_MOS 0.004938 96.26802 14.68305
o

X6__CUSTOMER_LINE
aC s

_GAINS___ 0.019492 57.98717 5.423499

vi y re

We need to drop X5 because of its higher value.

ed d
ar stu

Variance Inflation Factors

Date: 10/06/20 Time: 07:07
Sample: 1968 1983
Included observations: 16
is

Coefficient Uncentered Centered

Th

Variable Variance VIF VIF

C 1.693627 226.2412 NA
X2_____GNP_ 6.22E-07 139.8008 2.236216
X3__HOUSING_START
sh

S_ 7.96E-08 28.01037 1.597658

X4__UNEMPLOYEMEN
T_ 0.009458 55.05291 3.502797
X6__CUSTOMER_LINE
_GAINS___ 0.018194 40.64973 3.801940

This study source was downloaded by 100000830545516 from CourseHero.com on 11-13-2021 12:29:51 GMT -06:00

https://www.coursehero.com/file/74313839/Econometrics-paperdocx/
 (g)
Breusch-Godfrey Serial Correlation LM Test:
Null hypothesis: No serial correlation at up to 2 lags

F-statistic 5.424089 Prob. F(2,8) 0.0325

Obs*R-squared 9.208892 Prob. Chi-Square(2) 0.0100

Test Equation:
Dependent Variable: RESID
Method: Least Squares
Date: 10/06/20 Time: 09:11
Sample: 1968 1983

m
Included observations: 16

er as
Presample missing value lagged residuals set to zero.

co
eH w
Variable Coefficient Std. Error t-Statistic Prob.

o.
C -6299.476 2708.034 -2.326218 0.0484
X2_____GNP_
rs e -3.466299 2.125389 -1.630901 0.1416
ou urc
X3__HOUSING_STARTS_ 1.584787 0.781285 2.028437 0.0770
X4__UNEMPLOYEMENT_ 532.7084 211.8445 2.514620 0.0361
X5__PRIME_RATE_LAG__6_MOS 241.5931 129.8562 1.860467 0.0999
X6__CUSTOMER_LINE_GAINS___ 660.8688 295.0722 2.239685 0.0555
o

RESID(-1) -1.234815 0.384869 -3.208405 0.0125

RESID(-2) -1.067155 0.383398 -2.783416 0.0238
aC s
vi y re

R-squared 0.575556 Mean dependent var -2.75E-14

Adjusted R-squared 0.204167 S.D. dependent var 512.4336
S.E. of regression 457.1393 Akaike info criterion 15.39471
Sum squared resid 1671811. Schwarz criterion 15.78100
ed d

Log likelihood -115.1577 Hannan-Quinn criter. 15.41449

F-statistic 1.549740 Durbin-Watson stat 2.187470
ar stu

Prob(F-statistic) 0.275582

(h)
is

We use the methodology of restricted least-squares discussed in the chapter. Regressing Y on

Th

X2, X3, and X4 only, we obtain R2R = 0.6012. Including all the regressors, as can be seen from
the regression results given in (a), we have R2UR = 0.8227.
sh

Therefore, using Eq. (8.7.10), we obtain;

F = {(0.8227 – 0.6012) / 2} / {(1-0.8227) / 10} = 6.25

This study source was downloaded by 100000830545516 from CourseHero.com on 11-13-2021 12:29:51 GMT -06:00

https://www.coursehero.com/file/74313839/Econometrics-paperdocx/
 For 2 and 10 df in the numerator and denominator, respectively, the 5% critical F value is 4.10.
Therefore, we reject the hypothesis that the variables X5 and X6 do not belong in the model.

Q.3

ANSWER

(a)
Yes, researcher should use dummy variable. Researcher will use three dummy variables.

(b)

m
Consider the following model;

er as
Yt = α1D1t = α2D2t + α3D3t + α4D4t + ut

co
eH w
FRIG DUR D2 D3 D4 FRIG DUR D2 D3 D4

o.
1317 252.6 0 0 0 943 247.7 0 0 0
1615 272.4 1 rs e
0 0 1175 249.1 1 0 0
ou urc
1662 270.9 0 1 0 1269 251.8 0 1 0
1295 273.9 0 0 1 973 262.0 0 0 1
1271 268.9 0 0 0 1102 263.3 0 0 0
o

1555 262.9 1 0 0 1344 280.0 1 0 0

aC s

1639 270.9 0 1 0 1641 288.5 0 1 0

vi y re

1238 263.4 0 0 1 1225 300.5 0 0 1

1277 260.6 0 0 0 1429 312.6 0 0 0
1258 231.9 1 0 0 1699 322.5 1 0 0
ed d

1417 242.7 0 1 0 1749 324.3 0 1 0

ar stu

1185 248.6 0 0 1 1117 333.1 0 0 1

1196 258.7 0 0 0 1242 344.8 0 0 0
1410 248.4 1 0 0 1684 350.3 1 0 0
is

1417 255.5 0 1 0 1764 369.1 0 1 0

919 240.4 0 0 1 1328 356.4 0 0 1
Th

Where,
FRIF= Refrigerator sales, thousands.
sh

DUR= durable goods expenditure, billions of 1992 dollars.

D2= 1 in the second quarter, 0 otherwise.
D3= 1 in the third quarter, 0 otherwise.
D4= 1 in the fourth quarter, 0 otherwise.

This study source was downloaded by 100000830545516 from CourseHero.com on 11-13-2021 12:29:51 GMT -06:00

https://www.coursehero.com/file/74313839/Econometrics-paperdocx/
 (c)

Dependent Variable: FRIG

Method: Least Squares
Date: 10/06/20 Time: 09:29
Sample: 1 32
Included observations: 32

Variable Coefficient Std. Error t-Statistic Prob.

C 456.2440 178.2652 2.559355 0.0164

DUR 2.773424 0.623285 4.449691 0.0001
D2 242.4976 65.62589 3.695151 0.0010
D3 325.2643 65.81483 4.942112 0.0000
D4 -86.08045 65.84317 -1.307356 0.2021

R-squared 0.729881 Mean dependent var 1354.844

m
er as
Adjusted R-squared 0.689864 S.D. dependent var 235.6719
S.E. of regression 131.2454 Akaike info criterion 12.73462

co
Sum squared resid 465084.7 Schwarz criterion 12.96364

eH w
Log likelihood -198.7539 Hannan-Quinn criter. 12.81053
F-statistic 18.23901 Durbin-Watson stat 0.566015

o.
Prob(F-statistic) 0.000000
rs e
ou urc
This is quantitative X variable in the model. The regression results are as follows;
o

Yt = 456.2440 + 242.4976D2t + 325.2643D3t – 86.0804D4t + 2.7734Xt

aC s
vi y re

T-statistic = (2.5593) * (3.6951) * (4.9421) * (-1.3073) ** (4.4496)*

R2 = 0.7298
ed d

Where * indicates that p-value less than 5% and ** indicates that p-value greater than 5%.
ar stu

We see that the differential intercept coefficients for the second and third quarters are statistically
different from that of the first quarter, but the intercepts of the fourth quarter and the first quarter
is

are statistically about the same. The coefficient of X (durable goods expenditure) of about 2.77 tells
that, allowing for seasonal effects, if expenditure on durable goods goes up by a dollar, on average,
Th

sales of refrigerator go up by about 2.77 units, which is approximately 3 units.

sh

This study source was downloaded by 100000830545516 from CourseHero.com on 11-13-2021 12:29:51 GMT -06:00

https://www.coursehero.com/file/74313839/Econometrics-paperdocx/
Powered by TCPDF (www.tcpdf.org)