Scribd
Upload
19 views3 pages

SVKM'S Nmims Anil Surendra Modi School of Commerce Academic Year: 2020-2021

Uploaded by

goel.animesh105
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
19 views3 pages

SVKM'S Nmims Anil Surendra Modi School of Commerce Academic Year: 2020-2021

Uploaded by

goel.animesh105
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

SVKM’s NMIMS

ANIL SURENDRA MODI SCHOOL OF COMMERCE


Academic Year: 2020-2021

Program: B.Sc.Finance Year: III Semester: VI


Subject: Econometrics Batch: 2018-21
Date: Time:
Marks: 25 No. of pages:

Answer all questions

Each question carries 5 marks

1.

You want to predict sales of hand sanitizers, for which you have data on number bottles of sanitizers
sold by different companies. The independent variables are the percentage of market share of the
company and whether the brand is local or an established FMCG brand, which is measured by the
variable Owner, which is equal to 1 if the brand is local, equal to zero if the brand is an established
FMCG brand. Market share is measured as total sales by volume of a company out of total sales in
the market. You have estimated a Poisson regression, the results of which are given below:

intercept 0.2992

Market share 0.1161

Owner 0.6507

Write the equation of the Poisson model (1)

Interpret the coefficients of Market Share and Owner (2)

Predict the average number of sales when Market Share=20.78 and the company is an established
FMCG brand. (2)

2.

a. You have a data with Y as the dependent variable and X1, X2 and X3 as independent variables. The
R squared obtained from running a regression of X2 on X1 and X3 is 0.767. Calculate the variance
inflation factor for X2. (1)
b. In a time series data, the correlation between error at time t and error at time t-1 turns out be
0.56. Compute the Durbin-Watson statistic and comment whether there is significant
autocorrelation in errors. [dL=1.44, dU=1.67] (2)

c. You hypothesize that the residuals are autoregressive of order 3. Given the number of
observations n=80, and the R squared obtained from the regression of residuals on the independent
variables and 3 lagged residuals is .038, compute BG stat. Are the residuals autoregressive of order
3? [critical Chi squared=0.9970] (2)

3.

a. Consider the following regression equation:

Y=30.87+12.68ln(X1)+ 0.11D+ .05X2+ .04X2*D

Where Y=share of gross fixed capital formation (GFCF) out of GDP, measured as GFCF/GDP

X1: FDI inflows measured in millions of dollars

X2: percentage of public savings

D: dummy variable indicating whether the country is developed or developing.

D=1 if developing,

=0, otherwise

Interpret the coefficient of ln(X1) and X2*D (2)

b. Consider a dependent variable Y and an independent variable X. You have performed a Box-Cox
transformation on Y and X. The transformation parameter value turns out to be 0 for Y and 1 for X.

Write the regression equation for the given transformation parameter values for Y and X. Interpret
the coefficient of X. (2)

c. Consider a logit regression model where the variables are defined as follows:

Y=1 if the person is a credit card defaulter

=0, if not

X= Income

The coefficient of X from the logit regression turns out to be -1.2. For a person whose income level is
75 , the probability of this person being a credit card defaulter is 0.38. If income of this person
decreases by 1 unit, then calculate the change in the probability of being a credit card defaulter. (1)
4.

a. Consider the given plot of US WTI and UK Brent oil prices. Explain how would you test whether the
two series are cointegrated or not? (3)

b. Assuming the two series are cointegrated, write the regression equation of the error correction
model with US WTI as the dependent variable and UK Brent as the independent variable. (1)

c. Post estimation of the error correction model, the coefficient of the error correction term turns
out be -0.77. Interpret the coefficient value. (1)

5.

a. You are using ARIMA(p,d,q) model to forecast stock prices of a company with daily data on stock
prices. Write the equation of the ARIMA model. Explain your answer. (2)

b. Explain the procedure to determine the orders of p, d and q. (2)

c. You have estimated an ARCH(6) model to analyse volatility of asset price over time. You have daily
data with 1800 observation. The R squared from the ARCH(6) model turns out to be 0.09. Test
whether there is significant ARCH effect. [Chi squared: 12.59 ] (1)

You might also like