Scribd
Upload
39 views2 pages

Answer 1

Uploaded by

Rahul Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
39 views2 pages

Answer 1

Uploaded by

Rahul Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Dependent Variable: LOG(PER_CAPITA_CONSUMPTION_OF_ATTA_LB__

        Y_)
Method: Least Squares
Date: 10/14/20 Time: 15:31
Sample: 1960 1982
Included observations: 23

Variable Coefficient Std. Error t-Statistic Prob.  

C 2.432539 0.161811 15.03316 0.0000


LOG(REAL_DISPOSABLE_INCOME_PER_C
APITA__X2_) 0.346465 0.071798 4.825530 0.0002
LOG(REAL_RETAIL_PRICE_OF_ATTA_PER
_LB__X3_) -0.588074 0.100524 -5.850108 0.0000
LOG(RETAIL_PRICE_OF_MILLET_PER_LB_
_X5_) 0.340339 0.127057 2.678642 0.0159
LOG(WEIGHTED_AVERAGE_RETAIL_PRIC
E_OF_ATTA_SUBSTITUTES_PER_LB__X6_
) -0.453193 0.168669 -2.686874 0.0156
LOG(RETAIL_PRICE_OF_RICE_PER_LB__
X4_) 0.365333 0.117870 3.099451 0.0065

R-squared 0.987585    Mean dependent var 3.663887


Adjusted R-squared 0.983934    S.D. dependent var 0.187659
S.E. of regression 0.023786    Akaike info criterion -4.419967
Sum squared resid 0.009618    Schwarz criterion -4.123751
Log likelihood 56.82962    Hannan-Quinn criter. -4.345469
F-statistic 270.4698    Durbin-Watson stat 2.173348
Prob(F-statistic) 0.000000

Part A
In this, the non-linear equation is given so, we have to convert it in a linear form. If the model is
Power Function, then we have to taken the log on both sides to convert it into linear function.

That is, Log Y = Log b1 + b2 log X1 + b3 Log X3 + b4 log X4 + b5 log X4

Part B
In this the transformed regression is

Y = 2.432 + 0.346 X1 – 0.588 X2 + 0.340 X3 – 0.453 X4 + 0.365 X5

If the REAL_DISPOSABLE_INCOME_PER_CAPITA__X2_ goes up by 1 unit on an average, then


Per Capita Consumption of Atta lb (Y) would do up by 0.34 unit provided other independent variables
are constant.

If the REAL_RETAIL_PRICE_OF_ATTA_PER_LB__X3_ goes up by 1 unit on an average, then Per


Capita Consumption of Atta lb (Y) would do down by 0.588 unit provided other independent
variables are constant.

If the RETAIL_PRICE_OF_MILLET_PER_LB__X5_ goes up by 1 unit on an average, then Per


Capita Consumption of Atta lb (Y) would do up by 0.34 unit provided other independent variables are
constant.
If the WEIGHTED_AVERAGE_RETAIL_PRICE_OF_ATTA_SUBSTITUTES_PER_LB__X6_
goes up by 1 unit on an average, then Per Capita Consumption of Atta lb (Y) would do down by 0.45
unit provided other independent variables are constant.

If the RETAIL_PRICE_OF_RICE_PER_LB__X4_ goes up by 1 unit on an average, then Per Capita


Consumption of Atta lb (Y) would do up by 0.36 unit provided other independent variables are
constant.

Part C

Breusch-Godfrey Serial Correlation LM Test:

F-statistic 1.731190    Prob. F(2,17) 0.2069


Obs*R-squared 3.891764    Prob. Chi-Square(2) 0.1429

Test Equation:
Dependent Variable: RESID
Method: Least Squares
Date: 10/14/20 Time: 17:11
Sample: 1960 1982
Included observations: 23
Presample missing value lagged residuals set to zero.

Variable Coefficient Std. Error t-Statistic Prob.  

LOG(REAL_RETAIL_PRICE_OF_ATTA_PER
_LB__X3_) -0.030264 0.150612 -0.200944 0.8431
LOG(RETAIL_PRICE_OF_MILLET_PER_LB_
_X5_) -0.104788 0.302426 -0.346493 0.7332
LOG(WEIGHTED_AVERAGE_RETAIL_PRIC
E_OF_ATTA_SUBSTITUTES_PER_LB__X6_
) 0.277948 0.470258 0.591055 0.5623
LOG(RETAIL_PRICE_OF_RICE_PER_LB__
X4_) -0.151043 0.245254 -0.615863 0.5461
RESID(-1) 0.409679 0.242643 1.688402 0.1096
RESID(-2) -0.320917 0.257089 -1.248270 0.2289

R-squared 0.169051    Mean dependent var 0.001037


Adjusted R-squared -0.075346    S.D. dependent var 0.077367
S.E. of regression 0.080229    Akaike info criterion -1.988403
Sum squared resid 0.109424    Schwarz criterion -1.692187
Log likelihood 28.86663    Hannan-Quinn criter. -1.913906
Durbin-Watson stat 1.959509

Null hypothesis for this test is no serial correlation at up to 2 lags. If the value is less than 0.05, null
hypothesis will be rejected and if the value is grater than 0.05, then null hypothesis would be
accepted. We can say that there is no problem of auto correlation.

Now we can see that there is no impact of past two years on the current year because RESID (-1) is
greater than 0.05, hence RESID (-2) is also greater than 0.05, hence in both cases null hypothesis will
be accepted.

You might also like