QUESTION BANK

B.A(Hons) Business Economics

SEM IV, Paper No. C-9

Subject : Basic Econometrics

Q1. Comment on following. Give reasons in support of your comment.

a) The value of adjusted R2 is always less than R2.

b) R2 and adjusted R2 are always positive.
c) Testing the significance of the slope coefficient in a 2-variable linear regression
model is the same as testing the overall significance of the model.
d) Yi = β1 + β23 xi+ μi and Yi = β1 + β2 (1/xi) + μi are linear regression models
and therefore meet all the assumptions of a CLRM (Investigate separately).
e) The stochastic error term is irrelevant in the regression analysis as its mean value is
always zero.
f) If you have monthly data for a number of years, you need to use 12 dummies to
study seasonal effects if all months are known to exhibit seasonal variation
g) For OLS estimators, we use PRF.
h) The term goodness of fit & coeffecient of determination can be used
interchangeably.
i) OLS estimators are linear functions of ui which follows Chi square distributioGrowth
rate can be depicted through log lin model.

Q2 Given the data on Consumer Price Index(CPI).Y and Wholesale price index (WPI), X for the following

∑Y = 952.1, ∑X= 988.7,∑Y2= 48710.17, ∑X2=53818.43 , ∑XY=51145.55

i) Estimate Yi =β1 + β2X2

Construct the ANOVA table
Q3 Outline the procedure test for normality of the disturbance term for:

Skewness= 0.25 , Kurtosis = 4.5

What would you conclude about the behavior of the disturbance term at 5%
level of significance (State null and alternative hypothesis)

Q4 Prove the variance of the slope coefficient

Q5 A college wants to study the relation between Marks Obtained in Basic Econometrics IV of
BBE Students and Marks Obtained i Mathematics and Statistics studied by the students in the
previous years

Marks in Econometrics t = β1+ β2Marks in Maths t + β3Marks in Statistics t + ut ,

The College also wants to add a two Dummies , attendance in the class & the student’s
involvement in sports. State

(i) How would the college incorporate the above two dummies

ii) If the coefficient of Dummy for attendance is 0.23, how you would interpret the same
assuming computed ‘t’ is insignificant

Q6 The National Highway Authority is wanting to understand the influence of various factors
that effect the number of annual highway fatalities. It tries to regress the number of traffic
fatalities (in hundreds) in a state in a given year on the state’s total population ( in thousands)
X1; the number of days it rained (weather conditions were bad)X2 & the average speed drivers
were driving at for that year X3 (in miles per hour)

The results obtained for 25 states were as follows:

Y = 1.4 +0.029 X1 + 2.4 X2 + 10.3 X3

S.E (32.6) (.003) (0.62) (1.1)

R2=0.782

i) Interpret the model (3)

ii) Test the overall significance of the model (2)
iii) Test whether the partial slope coefficient for population is less than 0.03 (3)
iv) How would the coefficients of X1 and X2 be effected if the Y variable is expressed in
thousands and X1 in hundreds instead of the above mentioned units (4)

Q7 Explain what do you understand by regression on standardized variables. What is its

advantage over the normal simple regression in two variables
Q8 Stock Prices, Y, are assumed to be affected by the annual rate of dividend of stock, X. A
simple linear regression analysis was performed on 20 observations and the results were:

Variable Coefficient Standard Error

INTERCEPT -7.964633 3.11101359

X 12.548580 1.27081204

a) Interpret the regression result

b) Develop confidence interval for both the coefficients at 95% confidence level.
c) Is a dividend affect stock price significantly?
d) Comment upon overall significance of the model.

Q9. Take the following model....

Y = 1000 + 25X1 + 10X2 - 30X3 + 15X4 where;
Y = annual sales dollars generated by an auto parts counter person
X4 = years of experience
X1, X2, & X3 are the dummy variables representing the education level: Base case is primary school, X1
for high School, X2 for higher secondary and X3 for graduate school
(a) If a salesperson has a graduate degree how much will sales change according to this model
compared to a person with a primary education?
(b) How much in sales will a counter person with 10 years of experience and a high school education
generate?
(c) Why did we need three dummy variables to use "education level" in this regression equation?

Q5. 1/Yi= β1+ β2 (1/Xi) X, Y non-zero

a) Is this a linear regression model?

b) How would you estimate the model?

c) What is the behavior of Y as X tends to infinity?

d) In which situation this kind of model could be appropriate?

Q10 Using quarterly consumption and income data for Singapore over the period
1981 to 2004, a researcher has estimated a linear consumption function to be

Yt = 0.59 - 0.54 Xt
 a) Interpret the above result by giving its economic interpretation. (2)
b) Given Standard error of β1 as 0.4506 and of β2 as 0.0456, test the hypothesis
that consumption is independent of income at 1% level of significance. (3)

c) What do you think about the sign of the slope term? What can be the
possible reason for it. (2)

Prepare 99% confidence interval

Q11 In a study of turnover in the labor market, James F. Ragan Jr. obtained the following
results for the U.S. economy for the period of 1950 Quarter 1 to 1979 quarter IV.

lnYt= 4.47 -0.34 lnX2t + 1.22 lnX3t +1.22 lnX4t +0.80 lnX5t -0.0055X6t

(4.28) (-5.31) (3.64) (3.10) (1.10) (-3.09) R2=. 5530

(t statistics in parentheses)

Yt quit rate in manufacturing

X2t adult male unemployment rate

X3t percentage of employees younger than 25 years

X4t ratio of manufacturing employment in (t-1) to (t-4)

X5t percentage of women employees

X6t Time trend 1950 quarter 1=1

a) Interpret the following results

b) Is the observed negative relation between lnYt and lnX2t justifiable priori?
c) Why is the coefficient of X3t positive?
d) What do you infer from the coefficient of time trend?
e) Calculate adjusted R2 and test the overall significance of the model.
f) Can you estimate the standard errors of regression coefficient? If yes then how?

Q12. A variant of the wage determination model based on data of 30 years is given below

Wt= 1.073 + 5.288 Vt -0.116 Xt + 0.054Mt +0.046Mt-1

S.E. (0.797) (0.812) (0.111) (0.022) (0.019) R2=0.934

Wt wages and salaries per employee

Vt unfilled job vacancy

Xt GDP per person employed

Mt import Prices

Mt-1 Import prices in the previous time period

a) Interpret the results

b) Which of the estimated coefficients are significant?
c) What is the rationale of using import prices?
d) Which of the variable may be dropped?
e) Test the overall significance of the model.

Q13 CMt=263.6416 – 0.0056 PGNPt- 2.2316 FLRt

S.E. (11.5932) (.0019) (.2099) R2=.7077

CMt=168.3067 – 0.0055 PGNPt- 1.7680 FLRt + 12.8686 TFRt

S.E. (32.8916) (.0018) (.2480) ( ?) R 2=.7474

Both results based on observation for 30 years

CM Child Mortality rate

PGNP Per capita GNP

FLR female literacy rate

TFR Total Fertility Rate

a) How would you interpret the coefficient of TFR? A priori, would you expect a positive or
negative sign between CM and TFR?
b) Have the coefficients of PGNP and FLR changed between the two equations? What
could be the possible reason?
c) Which model you would choose? What can you say about the significance of TFR?

Q14 To assess the effect of Fed’s policy of deregulating interest rates beginning in July 1979
Sidney Langer estimated the following model for the 1975 Quarter III to 1983 Quarter II

Yt= 8.5871-0.1328 Pt -.7102 Unt-.2389 Mt +0.6592 Yt-1 +2.5831 Dumt

S.E. (1.9563) (0.0992) (0.1909) (0.0727) (0.1036) (0.7549) R2=.9156

Y Three month Treasury bill rate

P expected rate of inflation

Un Seasonally adjusted unemployment rate

M change in monetary base

Dum taking values 1 beginning July 1, 1979

a) Interpret the results

b) What has been the impact of interest rate deregulation?
c) Does the result make economic sense?
d) Give rationale behind the sign of coefficients.
e) Test the overall significance of the model
f) Calculate adjusted R2.

Q15 ) To reduce crime, the minister has budgeted more money to put more police force in the
city. A regression to study the effect of police deployment (Y in ‘000) on the number of
reported crimes (X) was studied. From the data pertaining to 8 weeks, following results
were obtained.

ΣXi = 76 ΣYi = 130

Σxi2 = 116 Σyi2 = 241.5

Σxiyi = 155 RSS = 34.38

Where xi, yi are deviations from their respective mean

i) Estimate both the regression coefficients and interpret the regression equation.

ii) Test the significance of the slope coefficient at 5% level of significance

iii) Calculate the value of coefficient of determination and interpret it.

Q16 What are the advantages of the dummy variable technique over the Chow test while
trying to measure structural stability?

Q17 Following is the demand schedule for commodity x.

Dx = f( Px, Py, Y)

Where the Dx is the demand for commodity x, Px is its price, Py is the price of related
commodity y and Y is the income of the consumer.

How do you measure the elasticity of demand with respect to own price and price of related
commodity y if you use a i) double log model ii) linear model.
Q18 Information was collected on daily changes in rupee (distribution A) & daily return on nifty
(Distribution B) for six month period (150 days) & following are summarized results.

Distribution A Distribution B

Mean 39.29 10.53

Standard Deviation 8.17 8.24

Skew ness 0.38 1.78

Kurtosis 2.61 6.24

Determine which of the above distribution is normally distributed.

Q19 Why the error term is always included in regression equation?

Q20 Consider the following equation;

ln Yt = -6.10 + 0.200 ln X2t + 0.110 ln X3t

Se (0.025) (0.050)

R2 = 0.62 R2= 0.48 n=50

where, ln Xt – log of qty of roses sold.

ln X2t – log of prices of roses.

ln X3t – log of prices of sunflowers.

i) Interpret the equation. Make appropriate hypotheses for signs of coefficient & test
your hypotheses.
ii) What is the elasticity of quantity of roses with respect to price of roses & sunflower.
If we run linear regression instead of log linear regression then how would the interpretation
change?

Q21 To study the share of GDP from services , a regression was fitted between GDP of twenty
six states & and services sector’s contribution to GDP , the results of these are given as under :

State GDP t = 27.135 + 0.35 Service Sector GDP t

Std. Error (0.22) (0.012)
 i) Do you suspect any heteroscedasticity . If yes then what is the reason behind your
suspicion

ii) Further using residual sum of the squares , how would you detect hetroscedasticity , state
the formula & null hypothesis
iii) Can we apply OLS regression if heteroscedasticity is proved to exist.

Q22 A regression model was fitted between Personal Consumption Expenditure (PCE)&
Disposable Income(Y) for a family using quarterly data for the last five years, the following are
the results :-

PCE t = 3.813 + 0.83 Y t

Std. Error (0.13) (0.02)

(i) The DW(d) was found to be 0.889. Compute Coefficient of autocorrelation. (3)
(ii) What corrective steps will you take to provide a solution to the problem of
autocorrelation in the above equation . (4)

(Given DL= 1.27 & DU = 1.45 for 24 df)

Q23 Prove that the least square estimators are BLUE?

Q24 Write short notes on the following.

i) JB test.
ii) SRF versus PRF
iii) Influence of level of significance on critical Z values.
iv) Log-Lin versus Lin-Log regression models.
v) Point Estimators
vi) Sample Regression function
vii) ANOVA Table
viii) Multicollinearity