introductory econometrics test bank

8/9/2019 Introductory econometrics test bank

1/133

Test Bank –Introductory Econometrics: A Modern Approach, 5th Edition by

Jefrey M. oo!drid"e

ith #E$%E&T '()*TI(+ AAI)AB)E (% A)) &-A#TE$'

&hapter

1. Econometrics is the branch of economics that _____.

a. studies the behavior of individual economic agents in making economic decisions

b. develops and uses statistical methods for estimating economic relationships

c. deals with the performance, structure, behavior, and decision-making of

an economy as a whole

d. applies mathematical methods to represent economic theories and solve

economic problems.

Answer: b

i!culty: Easy"loom#s: $nowledge

A-%ead: &hat is Econometrics'

"()*+:

eedback: Econometrics is the branch of economics that develops and uses

statistical methods for estimating economic relationships.

/. 0oneperimental data is called _____.

a. cross-sectional data

b. time series data

c. observational data

d. panel data

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback:

2. &hich of the following is true of eperimental data'

a. Eperimental data are collected in laboratory environments in the naturalsciences.

b. Eperimental data cannot be collected in a controlled environment.

c. Eperimental data is sometimes called observational data.

d. Eperimental data is sometimes called retrospective data.

Answer: a

i!culty: Easy


2/133

"loom#s: $nowledge


"()*+:

eedback:

3. An empirical analysis relies on _____to test a theory.a. common sense

b. ethical considerations

c. data

d. customs and conventions

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: )teps in Empirical Economic Analysis

"()*+:

eedback: An empirical analysis relies on data to test a theory.

4. 5he term 6u’ in an econometric model is usually referred to as the _____.

a. error term

b. parameter

c. hypothesis

d. dependent variable

Answer: a

i!culty: Easy

"loom#s: $nowledgeA-%ead: )teps in Empirical Economic Analysis

"()*+:

eedback: 5he term u in an econometric model is called the error term or

disturbance term.

7. 5he parameters of an econometric model _____.

a. include all unobserved factors a8ecting the variable being studied

b. describe the strength of the relationship between the variable under study and

the factors a8ecting it

c. refer to the eplanatory variables included in the modeld. refer to the predictions that can be made using the model

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:


3/133

eedback: 5he parameters of an econometric model describe the direction and

strength of the relationship between the variable under study and the factors

a8ecting it.

9. &hich of the following is the rst step in empirical economic analysis'

a. ;ollection of datab. )tatement of hypotheses

c. )pecication of an econometric model

d. 5esting of hypotheses

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he rst step in empirical economic analysis is the specication of the

econometric model.

_____.

a. cross-sectional data set

b. longitudinal data set

c. time series data set

d. eperimental data set

Answer: ai!culty: Easy

"loom#s: $nowledge

A-%ead: 5he )tructure of Economic ata

"()*+:

eedback: A data set that consists of a sample of individuals, households, rms,

cities, states, countries, or a variety of other units, taken at a given point in time, is

called a cross-sectional data set.

?. ata on the income of law graduates collected at di8erent times during the same

year is_____.a. panel data

b. eperimental data

c. time series data

d. cross-sectional data

Answer: d

i!culty: Easy


4/133

"loom#s: Application


"()*+: Analytic

eedback: A data set that consists of a sample of individuals, households, rms,

cities, states, countries, or a variety of other units, taken at a given point in time, is

called a cross-sectional data set. 5herefore, data on the income of law graduates ona particular year are eamples of cross-sectional data.

1@. A data set that consists of observations on a variable or several variables over

time is called a _____ data set.

a. binary

b. cross-sectional

c. time series

d. eperimental

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A time-series data set consists of observations on a variable or several

variables over time.

11. &hich of the following is an eample of time series data'

a. ata on the unemployment rates in di8erent parts of a country during a year.

b. ata on the consumption of wheat by /@@ households during a year.

c. ata on the gross domestic product of a country over a period of 1@ years.d. ata on the number of vacancies in various departments of an organiation on a

particular month.

Answer: c

i!culty: Easy



"()*+: Analytic

eedback: A time-series data set consists of observations on a variable or several

variables overtime. 5herefore, data on the gross domestic product of a country over a period of 1@

years is an eample of time series data.

1/. &hich of the following refers to panel data'

a. ata on the unemployment rate in a country over a 4-year period

b. ata on the birth rate, death rate and population growth rate in developing

countries over a 1@-year period.


5/133

c. ata on the income of 4 members of a family on a particular year.

d. ata on the price of a company#s share during a year.

Answer: b

i!culty: Easy

"loom#s: ApplicationA-%ead: 5he )tructure of Economic ata

"()*+: Analytic

eedback: A panel data set consists of a time series for each cross-sectional

member in the data set. 5herefore, data on the birth rate, death rate and infant

mortality rate in developing countries over a 1@-year period refers to panel data.

12. &hich of the following is a di8erence between panel and pooled cross-sectional

data'

a. A panel data set consists of data on di8erent cross-sectional units over a given

period of time while a pooled data set consists of data on the same cross-sectional

units over a given period of time.

b. A panel data set consists of data on the same cross-sectional units over a given

period of time while a pooled data set consists of data on di8erent cross-sectional

units over a given period of time

c. A panel data consists of data on a single variable measured at a given point in

time while a pooled data set consists of data on the same cross-sectional units over

a given period of time.

d. A panel data set consists of data on a single variable measured at a given point in

time while a pooled data set consists of data on more than one variable at a given

point in time.

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A panel data set consists of data on the same cross-sectional units over a

given period of time while a pooled data set consists of data on the same cross-

sectional units over a given period of time.

13. _____ has a causal e8ect on _____.a. BncomeC unemployment

b. %eightC health

c. BncomeC consumption

d. AgeC wage

Answer: c


6/133

i!culty: Doderate


A-%ead: ;ausality and the 0otion of ;eteris *aribus in Econometric Analysis

"()*+: Analytic

eedback: Bncome has a causal e8ect on consumption because an increase in

income leads to an increase in consumption.

14. &hich of the following is true'

a. A variable has a causal e8ect on another variable if both variables increase or

decrease simultaneously.

b. 5he notion of 6ceteris paribus# plays an important role in causal analysis.

c. i!culty in inferring causality disappears when studying data at fairly high levels

of aggregation.

d. 5he problem of inferring causality arises if eperimental data is used for analysis.

Answer: b

i!culty: Doderate

"loom#s: $nowledge


"()*+:

eedback: 5he notion of 6ceteris paribus# plays an important role in causal analysis.

17. Eperimental data are sometimes called retrospective data.

Answer: alse

i!culty: Easy

"loom#s: $nowledgeA-%ead: &hat is Econometrics'

"()*+:

eedback: 0oneperimental data are sometimes called retrospective data.

19. An economic model consists of mathematical euations that describe various

relationships between economic variables.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledgeA-%ead: )teps in Empirical Economic Analysis

"()*+:

eedback: An economic model consists of mathematical euations that describe

various relationships between economic variables.

1


7/133

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:eedback: A time series data set consists of observations on a variable or several

variables over

time.

1?. A time series data is also called a longitudinal data set.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A time series data is also called a longitudinal data set.

/@. 5he notion of ceteris paribus means Fother factors being eual.G

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he notion of ceteris paribus means Fother factors being eual.G

&hapter /

1. A dependent variable is also known as a=n> _____.

a. eplanatory variable

b. control variable

c. predictor variable

d. response variable

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: enition of the )imple +egression Dodel

"()*+:

eedback: A dependent variable is known as a response variable.


8/133

/. Bf a change in variable causes a change in variable y, variable is called the

_____.

a. dependent variable

b. eplained variable

c. eplanatory variable

d. response variable

Answer: c

i!culty: Easy

"loom#s: ;omprehension


"()*+:

eedback: Bf a change in variable causes a change in variable y, variable is

called the independent variable or the eplanatory variable.

2. Bn the euation y H β

0 I β

1 I u, β

0 is the _____.

a. dependent variable

b. independent variable

c. slope parameter

d. intercept parameter

Answer: d

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Bn the euation y H β

0 I β

1 I u, β

0 is the intercept parameter.

3. Bn the euation y H β

0 I β

1 I u, what is the estimated value of β

0 '

a. ´ y−^ β1 ´ x

b.´ y+ β

1´ x

c.

y

yi−¿́¿¿

( x i−´ x)¿

∑i=1

n

¿

¿


9/133

d. ∑i=1

n

xy

Answer: a


A-%ead: eriving the rdinary Jeast )uares Estimates

"()*+:

eedback: 5he estimated value of β

0 is ´ y−^ β1 ´ x .

4. Bn the euation c H β0 I β1 i I u, c denotes consumption and i denotes

income. &hat is the residual for the 4th observation ifc5 HK4@@ and

ĉ5 HK394'

a. K?94b. K2@@

c. K/4

d. K4@

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he formula for calculating the residual for the ith

observation isûi= y i− ̂y i . Bn this case, the residual is û5=c5−ĉ5 HK4@@ -K394H K/4.

7. &hat does the euation ̂y=^ β0+^ β1 x denote if the regression euation is y H L@

I L11 I u'

a. 5he eplained sum of suares

b. 5he total sum of suares

c. 5he sample regression function

d. 5he population regression function

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:


10/133

eedback: 5he euation ̂y=^ β0+^ β1 x denotes the sample regression function of the

given regression model.

9. ;onsider the following regression model: y H L@ I L11 I u. &hich of the following

is a property of rdinary Jeast )uare =J)> estimates of this model and theirassociated statistics'

a. 5he sum, and therefore the sample average of the J) residuals, is positive.

b. 5he sum of the J) residuals is negative.

c. 5he sample covariance between the regressors and the J) residuals is positive.

d. 5he point = ´ x , ´ y > always lies on the J) regression line.

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: *roperties of J) on Any )ample of ata"()*+:

eedback: An important property of the J) estimates is that the point = ´ x , ´ y >

always lies on the J) regression line. Bn other words, if x=´ x , the predicted value

of y is ́y .


11/133

"()*+:

eedback: 5he eplained sum of suares is dened as ∑i=1

n

( y i− ̂y )2

?. Bf the total sum of suares =))5> in a regression euation is is /4, what is the eplained sum of suares =))E>'

a. 73

b. 47

c. 2/

d. 1<

Answer: b

i!culty: Doderate


A-%ead: *roperties of J) on Any )ample of ata

"()*+: Analytic

eedback: 5otal sum of suares =))5> is given by the sum of eplained sum of

suares =))E> and residual sum of suares =))+>. 5herefore, in this case, ))EH in a regression analysis is 77 and the total

sum of suares =))5> is eual to ?@, what is the value of the coe!cient of

determination'

a. @.92

b. @.44

c. @./9d. 1./

Answer: c

i!culty: Doderate



"()*+: Analytic

eedback: 5he formula for calculating the coe!cient of determination is

R2=1−

SSR

SST . Bn this case, R

2=1−66

90

=0.27

11. &hich of the following is a nonlinear regression model'

a. y H L@ I L11M/ I u

b. log y H L@ I L1log Iu

c. y H 1 M =L@ I L1> I u

d. y H L@ I L1 I u


12/133

Answer: c

i!culty: Doderate



"()*+:eedback: A regression model is nonlinear if the euation is nonlinear in the

parameters. Bn this case, yH1 M =L@ I L1> I u is nonlinear as it is nonlinear in its

parameters.

1/. &hich of the following is assumed for establishing the unbiasedness of rdinary

Jeast )uare =J)> estimates'

a. 5he error term has an epected value of 1 given any value of the eplanatory

variable.

b. 5he regression euation is linear in the eplained and eplanatory variables.

c. 5he sample outcomes on the eplanatory variable are all the same value.

d. 5he error term has the same variance given any value of the eplanatory

variable.

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: Epected Nalues and Nariances of the J) Estimators

"()*+:

eedback: 5he error u has the same variance given any value of the eplanatory

variable.

12. 5he error term in a regression euation is said to ehibit homoskedasticty if

_____.

a. it has ero conditional mean

b. it has the same variance for all values of the eplanatory variable.

c. it has the same value for all values of the eplanatory variable

d. if the error term has a value of one given any value of the eplanatory variable.

Answer: b

i!culty: Easy

"loom#s: $nowledgeA-%ead: Epected Nalues and Nariances of the J) Estimators

"()*+:

eedback: 5he error term in a regression euation is said to ehibit homoskedasticty

if it has the same variance for all values of the eplanatory variable.

13. Bn the regression of y on , the error term ehibits heteroskedasticity if _____.

a. it has a constant variance


13/133

b. Nar=yO> is a function of

c. is a function of y

d. y is a function of

Answer: b



"()*+:

eedback: %eteroskedasticity is present whenever Nar=yO> is a function of

because Nar=uO> H Nar=yO>.

14. &hat is the estimated value of the slope parameter when the regression

euation, y H L@ I L11 I u passes through the origin'

a. ∑i=1

n

y i

b.

y¿¿¿

∑i=1

n

¿

>

c.

∑i=1

n

x i y i

∑i=1

n

x i2

d. ∑i=1

n

( y i− ́ y )2

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: +egression through the rigin and +egression on a ;onstant"()*+:


14/133

eedback: 5he estimated value of the slope parameter when the regression

euation passes through the origin is

∑i=1

n

x i y i

∑i=1

n

x i2

.

17. A natural measure of the association between two random variables is the

correlation coe!cient.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A natural measure of the association between two random variables is

the correlation coe!cient.

19. 5he sample covariance between the regressors and the rdinary Jeast )uare

=J)> residuals is always positive.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:eedback: 5he sample covariance between the regressors and the rdinary Jeast

)uare =J)> residuals is ero.

1 residuals is ero.

1?. 5here are n-1 degrees of freedom in rdinary Jeast )uare residuals.

Answer: alse


15/133

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5here are n-/ degrees of freedom in rdinary Jeast )uare residuals.

/@. 5he variance of the slope estimator increases as the error variance decreases.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he variance of the slope estimator increases as the error variance

increases.

&hapter 0

1. Bn the euation, y= β

0+ β

1 x

1+ β

2 x

2+u

, β

2 is a=n> _____.

a. independent variable

b. dependent variable

c. slope parameter

d. intercept parameter

Answer: ci!culty: Easy

"loom#s: $nowledge

A-%ead: Dotivation for Dultiple +egression

"()*+:

eedback: Bn the euation, y= β

0+ β

1 x

1+ β

2 x

2+u

, β

2 is a slope parameter.

/. ;onsider the following regression euation: y= β

1+ β

2 x

1+ β

2 x

2+u

. &hat does L1

imply'

a. β1 measures the ceteris paribus e8ect of x1 on x2 .

b. β

1 measures the ceteris paribus e8ect of y on x

1 .

c. β

1 measures the ceteris paribus e8ect of x

1 on y .

d. β


1 on u .


16/133

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: β


1 on y .

2. Bf the eplained sum of suares is 24 and the total sum of suares is 3?, what is

the residual sum of suares'

a. 1@

b. 1/

c. 1<

d. 13

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: Dechanics and Bnterpretation of rdinary Jeast )uares

"()*+: Analytic

eedback: 5he residual sum of suares is obtained by subtracting the eplained

sum of suares from the total sum of suares, or 3?-24H13.

3. &hich of the following is true of +/'

a. +/ is also called the standard error of regression.

b. A low +/ indicates that the rdinary Jeast )uares line ts the data well.c. +/ usually decreases with an increase in the number of independent variables in a

regression.

d. +/ shows what percentage of the total variation in the dependent variable, P, is

eplained by the eplanatory variables.

Answer: d

i!culty: Easy

"loom#s: $nowledge


"()*+:eedback: +/ shows what percentage of the total variation in P is eplained by the

eplanatory variables.

4. 5he value of +/ always _____.

a. lies below @

b. lies above 1

c. lies between @ and 1


17/133

d. lies between 1 and 1.4

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: Dechanics and Bnterpretation of rdinary Jeast )uares"()*+:

eedback: "y denition, the value of +/ always lies between @ and 1.

7. Bf an independent variable in a multiple linear regression model is an eact linear

combination of other independent variables, the model su8ers from the problem of

_____.

a. perfect collinearity

b. homoskedasticity

c. heteroskedasticty

d. omitted variable bias

Answer: a

i!culty: Easy

"loom#s: $nowledge

A-%ead: 5he Epected Nalue of the J) Estimators

"()*+:

eedback: Bf an independent variable in a multiple linear regression model is an

eact linear combination of other independent variables, the model su8ers from the

problem of perfect collinearity.

9. 5he assumption that there are no eact linear relationships among theindependent variables in a multiple linear regression model fails if _____, where n is

the sample sie and k is the number of parameters.

a. nQ/

b. nHkI1

c. nQk

d. nRkI1

Answer: d

i!culty: Easy

"loom#s: $nowledgeA-%ead: 5he Epected Nalue of the J) Estimators

"()*+:

eedback: 5he assumption of no perfect collinearity among independent variables

fails if nRkI1.


18/133


19/133

b. β

2 R@ and 1 and / are positively correlated

c. β

2 H@ and 1 and / are negatively correlated

d. β

2 H@ and 1 and / are negatively correlated

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: &hen the variable / is omitted from the regression, the bias in~ β

1 is

negative if β

2 R@ and 1 and / are positively correlated.

11. )uppose the variable / has been omitted from the following regression

euation, y= β0+ β1 x1+ β2 x2+u .~ β

1 is the estimator obtained when / is omitted

from the euation. Bf E=~ β

1 > QL1,~ β

1 is said to _____.

a. have an upward bias

b. have a downward bias

c. be unbiased

d. be biased toward ero

Answer: a

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: &hen the variable / is omitted from the following regression euation,

y= β0+ β

1 x

1+ β

2 x

2+u , , β1 has an upward bias if E= β1 > QL1.

1/. %igh =but not perfect> correlation between two or more independent variables is

called _____.

a. heteroskedasticty

b. homoskedasticty

c. multicollinearity

d. micronumerosity

Answer: c


20/133

i!culty: Easy

"loom#s: $nowledge

A-%ead: 5he Nariance of the J) Estimators

"()*+:

eedback: %igh, but not perfect, correlation between two or more independent

variables is called multicollinearity.

12. 5he term _____ refers to the problem of small sample sie.

a. micronumerosity

b. multicollinearity

c. homoskedasticity

d. heteroskedasticity

Answer: a

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he term micronumerosity refers to the problem of small sample sie.

13. ind the degrees of freedom in a regression model that has 1@ observations and

9 independent variables.

a. 19

b. /

c. 2

d. 3

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+: Analytic

eedback: 5he degrees of freedom in a regression model is computed by

subtracting the number of parameters from the number of observations in a

regression model. )ince, the number of parameters is one more than the number of

independent variables, the degrees of freedom in this case is 1@-=9 I 1> H /.

14. 5he auss-Darkov theorem will not hold if _____.

a. the error term has the same variance given any values of the eplanatory

variables

b. the error term has an epected value of ero given any values of the independent

variables

c. the independent variables have eact linear relationships among them


21/133

d. the regression model relies on the method of random sampling for collection of

data

Answer: c

i!culty: Easy

"loom#s: $nowledgeA-%ead: E!ciency of J): 5he auss-Darkov 5heorem

"()*+:

eedback: 5he auss-Darkov theorem will not hold if the independent variables

have eact linear relationships among them.

17. 5he term FlinearG in a multiple linear regression model means that the euation

is linear in parameters.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he term FlinearG in a multiple linear regression model means that the

euation is linear in parameters.

19. 5he key assumption for the general multiple regression model is that all factors

in the unobserved error term be correlated with the eplanatory variables.

Answer: alse



"()*+:

eedback: 5he key assumption of the general multiple regression model is that all

factors in the unobserved error term be uncorrelated with the eplanatory variables.

1 decreases when an independent variable is

added to a multiple regression model.

Answer: alsei!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he coe!cient of determination =+/> never decreases when an

independent variable is added to a multiple regression model.


22/133

1?. An eplanatory variable is said to be eogenous if it is correlated with the error

term.

Answer: alse

i!culty: Easy

"loom#s: $nowledgeA-%ead: 5he Epected Nalue of the J) Estimators

"()*+:

eedback: An eplanatory variable is said to be endogenous if it is correlated with

the error term.

/@. A larger error variance makes it di!cult to estimate the partial e8ect of any of

the independent variables on the dependent variable.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A larger error variance makes it di!cult to estimate the partial e8ect of

any of the independent variables on the dependent variable.

&hapter 1

1. 5he normality assumption implies that:

a. the population error u is dependent on the eplanatory variables and is normally

distributed with mean eual to one and variance S/

.b. the population error u is independent of the eplanatory variables and is normally

distributed with mean eual to one and variance S.

c. the population error u is dependent on the eplanatory variables and is normally

distributed with mean ero and variance S.

d. the population error u is independent of the eplanatory variables and is normally

distributed with mean ero and variance S/.

Answer: d

i!culty: Doderate

"loom#s: $nowledge

A-%ead: )ampling istributions of the J) Estimators

"()*+:

eedback: 5he normality assumption implies that the population error 6u’ is

independent of the eplanatory variables and is normally distributed with mean

ero and variance S/.

/. &hich of the following statements is true'


23/133

a. 5aking a log of a nonnormal distribution yields a distribution that is closer to

normal.

b. 5he mean of a nonnormal distribution is @ and the variance is S/.

c. 5he ;J5 assumes that the dependent variable is una8ected by unobserved

factors.

d. J) estimators have the highest variance among unbiased estimators.

Answer: a

i!culty: Doderate

"loom#s: $nowledge

A-%ead: )ampling istribution of the J) Estimators

"()*+:

eedback: 5ransformations such as logs of nonnormal distributions, yields

distributions which are closer to normal.

2. A normal variable is standardied by:

a. subtracting o8 its mean from it and multiplying by its standard deviation.

b. adding its mean to it and multiplying by its standard deviation.

c. subtracting o8 its mean from it and dividing by its standard deviation.

d. adding its mean to it and dividing by its standard deviation.

Answer: c

i!culty: Doderate

"loom#s: $nowledge


"()*+:

eedback: A normal variable is standardied by subtracting o8 its mean from it anddividing by its standard deviation.

3. &hich of the following is a statistic that can be used to test hypotheses about a

single population parameter'

a. statistic

b. t statistic

c. T/ statistic

d. urbin &atson statistic

Answer: bi!culty: Easy

"loom#s: $nowledge

A-%ead: 5esting %ypotheses about a )ingle *opulation *arameter: 5he t 5est

"()*+:

eedback: 5he t statistic can be used to test hypotheses about a single population

parameter.


24/133

4. ;onsider the euation, P H L1 I L/U/ I u. A null hypothesis, %@: L/ H @ states that:

a. U/ has no effect on the epected value of L/.

b. U/ has no e8ect on the epected value of P.

c. L/ has no e8ect on the epected value of P.

d. P has no e8ect on the epected value of U/.

Answer: b

i!culty: Doderate



"()*+:

eedback: Bn such an euation, a null hypothesis, %@: L/ H @ states that U/ has no

effect on the epected value of P. 5his is because L/ is the coe!cient associated

with U/.

7. 5he signicance level of a test is:

a. the probability of reVecting the null hypothesis when it is false.

b. one minus the probability of reVecting the null hypothesis when it is false.

c. the probability of reVecting the null hypothesis when it is true.

d. one minus the probability of reVecting the null hypothesis when it is true.

Answer: c

i!culty: Doderate

"loom#s: $nowledge


"()*+:

eedback: 5he signicance level of a test refers to the probability of reVecting thenull hypothesis when it is in fact true.

9. 5he general t statistic can be written as:

a. t H Hypothesized value

Standard e rror

b. t Hestimate – hypothesized value

¿ >

c. t H

(estimate – hypothesized value)

variance

d. t H(estimate – hypothesized value)

standard error

Answer: d

i!culty: Easy


25/133

"loom#s: $nowledge


"()*+:

eedback: 5he general t statistic can be written as t H =estimate W hypothesied

value>Mstandard error.

[

d. 5he upper bound of the condence interval for a regression coe!cient, say L V, is

given by^ β

X I Y;ritical value Z standard error = ^ β

X>[

Answer: d

i!culty: Doderate

"loom#s: $nowledge

A-%ead: ;ondence Bntervals

"()*+:


26/133

eedback: 5he upper bound of the condence interval for a regression coe!cient,

say L V, is given by^ β

X I Y;ritical value Z standard error = ^ β

X>[.

1@. &hich of the following tools is used to test multiple linear restrictions'

a. t testb. test

c. test

d. (nit root test

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: 5esting Dultiple Jinear +estrictions: 5he test

"()*+:

eedback: 5he test is used to test multiple linear restrictions.

11. &hich of the following statements is true of hypothesis testing'

a. 5he t test can be used to test multiple linear restrictions.

b. A test of single restriction is also referred to as a Voint hypotheses test.

c. A restricted model will always have fewer parameters than its unrestricted model.

d. J) estimates maimie the sum of suared residuals.

Answer: c

i!culty: Doderate

"loom#s: $nowledge

A-%ead: 5esting Dultiple Jinear +estrictions: 5he test"()*+:

eedback: A restricted model will always have fewer parameters than its

unrestricted model.

1/. &hich of the following correctly denes statistic if ))+r represents sum of

suared residuals from the restricted model of hypothesis testing, ))+ur represents

sum of suared residuals of the unrestricted model, and is the number of

restrictions placed'

a. H

(SSR ur−SSRr)/q

SSRur /(n−k −1)

b. H(SSRr−SSRur )/qSSRur /(n−k −1)

c. H(SSRur−SSRr)/q

SSRr /(n−k −1)


27/133

d. H(SSRur−SSRr )/(n−k −1)

SSRur /q

Answer: b

i!culty: Doderate"loom#s: $nowledge


"()*+:

eedback: 5he statistic is given by, H(SSRr −SSRur )/ qSSR ur/(n−k −1)

12. &hich of the following statements is true'

a. Bf the calculated value of statistic is higher than the critical value, we reVect the

alternative hypothesis in favor of the null hypothesis.

b. 5he statistic is always nonnegative as ))+r is never smaller than ))+ur.c. egrees of freedom of a restricted model is always less than the degrees of

freedom of an unrestricted model.

d. 5he statistic is more \eible than the t statistic to test a hypothesis with a

single restriction.

Answer: b

i!culty: Doderate



"()*+:eedback: 5he statistic is always nonnegative as ))+r is never smaller than ))+ur.

13. Bf +/ur H @.7M[ M Y=1-+/ur>Mn W k W 1[.

%ere, represents the number of restrictions. Bn this case it is eual to [email protected][ M Y=1 W @.7M//?[ H Y@.@3?


28/133

14. &hich of the following correctly identies a reason why some authors prefer to

report the standard errors rather than the t statistic'

a. %aving standard errors makes it easier to compute condence intervals.

b. )tandard errors are always positive.

c. 5he statistic can be reported Vust by looking at the standard errors.d. )tandard errors can be used directly to test multiple linear regressions.

Answer: a

i!culty: Dedium


A-%ead: +eporting +egression +esults

"()*+:

eedback: ne of the advantages of reporting standard errors over t statistics is

that condence intervals can be easily calculated using stand errors.

17. &henever the dependent variable takes on Vust a few values it is close to a

normal distribution.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: &henever the dependent variable takes on Vust a few values it cannot

have anything close to a normal distribution. A normal distribution reuires the

dependent variable to take up a large range of values.

19. Bf the calculated value of the t statistic is greater than the critical value, the null

hypothesis, %@ is reVected in favor of the alternative hypothesis, %1.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Bf the calculated value of the t statistic is greater than the critical value,%@ is reVected in favor of %1.

1


29/133

"loom#s: $nowledge


"()*+:

eedback: %1: L V ] @, where L V is a regression coe!cient associated with an

eplanatory variable, represents a two-sided alternative hypothesis.

1?. Bf ^ β

1 and^ β

/ are estimated values of regression coe!cients associated with

two eplanatory variables in a regression euation, then the standard error = ^ β

1 W

^ β/> H standard error =

^ β1> W standard error =

^ β/>.

Answer: alse

i!culty: Easy


A-%ead: 5esting %ypotheses about a )ingle Jinear ;ombinations of the *arameters"()*+:

eedback: Bf ^ β

1 and^ β

/ are estimated values of regression coe!cients

associated with two eplanatory variables in a regression euation, then the

standard error = ^ β

1 W^ β

/> ] standard error = ^ β

1> W standard error = ^ β

/>.

/@. )tandard errors must always be positive.

Answer: 5ruei!culty: Easy

"loom#s: $nowledge

A-%ead: 5esting %ypotheses about a )ingle Jinear ;ombinations of the *arameters

"()*+:

eedback: )tandard errors must always be positive since they are estimates of

standard deviations.

&hapter 5


a. 5he standard error of a regression, σ̂ , is not an unbiased estimator for σ ,

the standard deviation of the error, u, in a multiple regression model.

b. Bn time series regressions, J) estimators are always unbiased.

c. Almost all economists agree that unbiasedness is a minimal reuirement for an

estimator in regression analysis.

d. All estimators in a regression model that are consistent are also unbiased.

Answer: b


30/133

i!culty: Doderate

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: 5he standard error of a regression is not an unbiased estimator for the

standard deviation of the error in a multiple regression model.

/. Bf^ β

V, an unbiased estimator of β

V, is consistent, then the:

a. distribution of^ β

V becomes more and more loosely distributed around β

V as

the sample sie grows.

b. distribution of^ β

V becomes more and more tightly distributed around β

V as

the sample sie grows.

c. distribution of^ β

V tends toward a standard normal distribution as the sample

sie grows.

d. distribution of^ β

V remains una8ected as the sample sie grows.

Answer: b

i!culty: Dedium

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: Bf

^ β V, an unbiased estimator of

β V, is consistent, then the distribution

of^ β

V becomes more and more tightly distributed around β

V as the sample sie

grows.

2. Bf^ β


V, is also a consistent estimator of β

V,

then when the sample sie tends to innity:

a. the distribution of^ β

V collapses to a single value of ero.

b. the distribution of

^

β V diverges away from a single value of ero.

c. the distribution of^ β

V collapses to the single point β

V.

d. the distribution of^ β

V diverges away from β

V.

Answer: c

i!culty: Easy


31/133

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: Bf^ β


V, is also a consistent estimator of

β V, then when the sample sie tends to innity the distribution of^ β V collapses

to the single point β V.

3. Bn a multiple regression model, the J) estimator is consistent if:

a. there is no correlation between the dependent variables and the error term.

b. there is a perfect correlation between the dependent variables and the error

term.

c. the sample sie is less than the number of parameters in the model.

d. there is no correlation between the independent variables and the error term.

Answer: d

i!culty: Doderate

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: Bn a multiple regression model, the J) estimator is consistent if there is

no correlation between the eplanatory variables and the error term.

4. Bf the error term is correlated with any of the independent variables, the J)

estimators are:a. biased and consistent.

b. unbiased and inconsistent.

c. biased and inconsistent.

d. unbiased and consistent.

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: Bf the error term is correlated with any of the independent variables, then

the J) estimators are biased and inconsistent.

7. Bf ^1 H ;ov=1M/> M Nar=1> where 1 and / are two independent variables in a

regression euation, which of the following statements is true'


32/133

a. Bf / has a positive partial effect on the dependent variable, and ^1 Q @, then the

inconsistency in the simple regression slope estimator associated with 1 is

negative.

b. Bf / has a positive partial effect on the dependent variable, and ^1 Q @, then the

inconsistency in the simple regression slope estimator associated with 1 is positive.

c. Bf 1 has a positive partial effect on the dependent variable, and ^1 Q @, then theinconsistency in the simple regression slope estimator associated with 1 is

negative.

d. Bf 1 has a positive partial effect on the dependent variable, and ^1 Q @, then the

inconsistency in the simple regression slope estimator associated with 1 is positive.

Answer: b

i!culty: Doderate

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: iven that ^1 H ;ov=1M/>MNar=1> where 1 and / are two independent

variables in a regression euation, if / has a positive partial e8ect on the

dependent variable, and ^1 Q @, then the inconsistency in the simple regression

slope estimator associated with 1 is positive.

9. Bf J) estimators satisfy asymptotic normality, it implies that:

a. they are approimately normally distributed in large enough sample sies.

b. they are approimately normally distributed in samples with less than 1@

observations.

c. they have a constant mean eual to ero and variance eual to S/.

d. they have a constant mean eual to one and variance eual to S.

Answer: a

i!culty: Easy

"loom#s: $nowledge

A-%ead: Asymptotic 0ormality and Jarge )ample Bnference

"()*+:

eedback: Bf J) estimators satisfy asymptotic normality, it implies that they are

approimately normally distributed in large enough sample sies.

, is not constant, _____.

a. the t statistics are invalid and condence intervals are valid for small sample

sies

b. the t statistics are valid and condence intervals are invalid for small sample

sies

c. the t statistics condence intervals are valid no matter how large the sample sie

is


33/133

c. the t statistics and condence intervals are both invalid no matter how large the

sample sie is

Answer: d

i!culty: Doderate

"loom#s: $nowledgeA-%ead: Asymptotic 0ormality and Jarge )ample Bnference

"()*+:

eedback: Bf variance of the dependent variable conditional on an eplanatory

variable is not a constant the usual t statistics condence intervals are both invalid

no matter how large the sample sie is.

?. Bf^ β

V is an J) estimator of a regression coe!cient associated with one of the

eplanatory variables, such that VH 1, /, ., n, asymptotic standard error of^ β

V

will refer to the:

a. estimated variance of^ β

V when the error term is normally distributed.

b. estimated variance of a given coe!cient when the error term is not normally

distributed.

c. suare root of the estimated variance of^ β

V when the error term is normally

distributed.

d. suare root of the estimated variance of^ β

V when the error term is not normally

distributed.

Answer: d

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Asymptotic standard error refers to the suare root of the estimated

variance of^ β

V when the error term is not normally distributed.

1@. A useful rule of thumb is that standard errors are epected to shrink at a ratethat is the inverse of the:

a. suare root of the sample sie.

b. product of the sample sie and the number of parameters in the model.

c. suare of the sample sie.

d. sum of the sample sie and the number of parameters in the model.


34/133


35/133

"loom#s: $nowledge


"()*+:

eedback: 5he JD statistic follows a χ / distribution.


a. Bn large samples there are not many discrepancies between the outcomes of the

test and the JD test.

b. egrees of freedom of the unrestricted model are necessary for using the JD

test.

c. 5he JD test can be used to test hypotheses with single restrictions only and

provides ine!cient results for multiple restrictions.

d. 5he JD statistic is derived on the basis of the normality assumption.

Answer: a

i!culty: Doderate"loom#s: $nowledge


"()*+:

eedback: Bn large samples there are not many discrepancies between the test

and the JD test because asymptotically the two statistics have the same probability

of a 5ype 1 error.

14. &hich of the following statements is true under the auss-Darkov assumptions'

a. Among a certain class of estimators, J) estimators are best linear unbiased, but

are asymptotically ine!cient.b. Among a certain class of estimators, J) estimators are biased but

asymptotically e!cient.

c. Among a certain class of estimators, J) estimators are best linear unbiased and

asymptotically e!cient.

d. 5he JD test is independent of the auss-Darkov assumptions.

Answer: c

i!culty: Doderate

"loom#s: $nowledge

A-%ead: Asymptotic E!ciency of J)

"()*+:

eedback: (nder the auss-Darkov assumptions, among a certain class of

estimators, J) estimators are best linear unbiased and asymptotically e!cient.


36/133

17. Bf variance of an independent variable in a regression model, say 1, is greater

than @, or Nar=1> Q @, the inconsistency in^ β

1 =estimator associated with 1> is

negative, if 1 and the error term are positively related.

Answer: alsei!culty: Easy

"loom#s: $nowledge

A-%ead: ;onsistency

"()*+:

eedback: Bf variance of an independent variable, say 1, is greater than @, the

inconsistency in^ β

1 =estimator associated with 1> is positive if 1 and the error

term are positively related.

19. Even if the error terms in a regression euation, u1, u/,.., un, are not normally

distributed, the estimated coe!cients can be normally distributed.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Even if the error terms in a regression euation, u1, u/,.., un, are not

normally distributed, the estimated coe!cients cannot be normally distributed.

1, and

more than ?4` of the area under the distribution is within two standard deviations.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A normally distributed random variable is symmetrically distributed about

its mean, it can take on any positive or negative value =but with ero probability>,and more than ?4` of the area under the distribution is within two standard

deviations.

1?. 5he statistic is also referred to as the score statistic.

Answer: alse

i!culty: Easy


37/133

"loom#s: $nowledge


"()*+:

eedback: 5he JD statistic is also referred to as the score statistic.

/@. 5he JD statistic reuires estimation of the unrestricted model only.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he JD statistic reuires estimation of the restricted model only.

&hapter 2

1. A change in the unit of measurement of the dependent variable in a model does

not lead to a change in:a. the standard error of the regression.

b. the sum of suared residuals of the regression.

c. the goodness-of-t of the regression.

d. the condence intervals of the regression.

Answer: c

i!culty: Doderate

"loom#s: $nowledge

A-%ead: E8ects of ata )caling on J) )tatistics

"()*+:eedback: ;hanging the unit of measurement of the dependent variable in a model

does not lead to a change in the goodness of t of the regression.

/. ;hanging the unit of measurement of any independent variable, where log of the

dependent variable appears in the regression:

a. a8ects only the intercept coe!cient.

b. a8ects only the slope coe!cient.

c. a8ects both the slope and intercept coe!cients.

d. a8ects neither the slope nor the intercept coe!cient.

Answer: a

i!culty: Doderate



"()*+:


38/133

eedback: ;hanging the unit of measurement of any independent variable, where

log of the independent variable appears in the regression only a8ects the intercept.

5his follows from the property log=ab> H log=a> I log=b>.

2. A variable is standardied in the sample:

a. by multiplying by its mean.b. by subtracting o8 its mean and multiplying by its standard deviation.

c. by subtracting o8 its mean and dividing by its standard deviation.

d. by multiplying by its standard deviation.

Answer: c

i!culty: Doderate

"loom#s: $nowledge


"()*+:

eedback: A variable is standardied in the sample by subtracting o8 its mean and

dividing by its standard deviation.

3. )tandardied coe!cients are also referred to as:

a. beta coe!cients.

b. y coe!cients.

c. alpha coe!cients.

d. V coe!cients.

Answer: a

i!culty: Easy

"loom#s: $nowledgeA-%ead: E8ects of ata )caling on J) )tatistics

"()*+:

eedback: )tandardied coe!cients are also referred to as beta coe!cients.

4. Bf a regression euation has only one eplanatory variable, say 1, its

standardied coe!cient must lie in the range:

a. -/ to @.

b. -1 to 1.

c. @ to 1.

d. @ to /.

Answer: b

i!culty: Easy



"()*+:


39/133

eedback: Bf a regression euation has only one eplanatory variable, say 1, its

standardied coe!cient is the correlation coe!cient between the dependent

variable and 1, and must lie in the range -1 to 1.

7. Bn the following euation, gdp refers to gross domestic product, and B refers to

foreign direct investment.

log=gdp) H /.74 I @.4/9log=bankcredit > I @.///FDI

[email protected]> =@.@//> =@.@19>

&hich of the following statements is then true'

a. Bf gdp increases by 1`, bank credit increases by @.4/9`, the level of B

remaining constant.

b. Bf bank credit increases by 1`, gdp increases by @.4/9`, the level of B

remaining constant.

c. Bf gdp increases by 1`, bank credit increases by [email protected]/9>`, the level of B

remaining constant.

d. Bf bank credit increases by 1`, gdp increases by [email protected]/9>`, the level of B

remaining constant.

Answer: b

i!culty: Doderate


A-%ead: Dore on unctional orm

"()*+:

eedback: 5he euation suggests that if bank credit increases by 1`, gdp increases

by @.4/9`. 5his is known from the value of the coe!cient associated with bankcredit.

9. Bn the following euation, gdp refers to gross domestic product, and B refers to

foreign direct investment.

log=gdp) H /.74 I @.4/9log=bankcredit > I @.///FDI

[email protected]> =@.@//> =@.@19>

&hich of the following statements is then true'

a. Bf B increases by 1`, gdp increases by approimately //./`, the amount of

bank credit remaining constant.b. Bf B increases by 1`, gdp increases by approimately /7.4`, the amount of

bank credit remaining constant.

c. Bf B increases by 1`, gdp increases by approimately /3.


40/133

Answer: c

i!culty: %ard



"()*+:

eedback: 5he euation suggests that if B increases by 1`, gdp increases by1@@=ep=@.///> W 1>`. 5his euals =1./3 H /3.


41/133

1@. &hich of the following models is used uite often to capture decreasing or

increasing marginal e8ects of a variable'

a. Dodels with logarithmic functions

b. Dodels with uadratic functions

c. Dodels with variables in level

d. Dodels with interaction terms

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Dodels with uadratic functions are used uite often to capture

decreasing or increasing marginal e8ects of a variable

11. &hich of the following correctly represents the euation for adVusted +/'

a.´ R / H 1 – [SSR/(n –1)]/[SST/(n+1)]

b.´ R / H 1 – [SSR/(n –k – 1)]/[SST/(n+1)]

c.´ R / H 1 – [SSR/(n –k – 1)]/[SST/(n – 1)]

d.´ R / H 1 – [SSR]/[SST/(n – 1)]

Answer: c

i!culty: Easy

"loom#s: $nowledgeA-%ead: Dore on oodness-of-it and )election of +egressors

"()*+:

eedback:´ R / H 1 – [SSR/(n –k – 1)]/[SST/(n – 1)]

1/. &hich of the following correctly identies an advantage of using adVusted +/

over +/'

a. AdVusted +/ corrects the bias in +/.

b. AdVusted +/ is easier to calculate than +/.

c. 5he penalty of adding new independent variables is better understood throughadVusted +/ than +/.

d. 5he adVusted +/ can be calculated for models having logarithmic functions while

+/ cannot be calculated for such models.

Answer: c

i!culty: Doderate

"loom#s: $nowledge


42/133

A-%ead: Dore on oodness-of-it and )election of +egressors

"()*+:

eedback: 5he penalty of adding new independent variables is better understood

through adVusted +/ than +/ since its calculation is directly dependent on the

number of independent variables included.

12. 5wo euations form a nonnested model when:

a. one is logarithmic and the other is uadratic.

b. neither euation is a special case of the other.

c. each euation has the same independent variables.

d. there is only one independent variable in both euations.

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5wo euations form a nonnested model when neither euation is a

special case of the other.

13. A predicted value of a dependent variable:

a. represents the di8erence between the epected value of the dependent variable

and its actual value.

b. is always eual to the actual value of the dependent variable.

c. is independent of eplanatory variables and can be estimated on the basis of the

residual error term only.

d. represents the epected value of the dependent variable given particular valuesfor the eplanatory variables.

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: *rediction and +esidual Analysis

"()*+:

eedback: A predicted value of a dependent variable represents the epected value

of the dependent variable given particular values for the eplanatory variables.

14. +esidual analysis refers to the process of:

a. eamining individual observations to see whether the actual value of a

dependent variable di8ers from the predicted value.

b. calculating the suared sum of residuals to draw inferences for the consistency of

estimates.


43/133

c. transforming models with variables in level to logarithmic functions so as to

understand the e8ect of percentage changes in the independent variable on the

dependent variable.

d. sampling and collection of data in such a way to minimie the suared sum of

residuals.

Answer: a

i!culty: Doderate

"loom#s: $nowledge


"()*+:

eedback: +esidual analysis refers to the process of eamining individual

observations to see whether the actual value of a dependent variable di8ers from

the predicted value.

17. "eta coe!cients are always greater than standardied coe!cients.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: "eta coe!cients the same as standardied coe!cients.

19. Bf a new independent variable is added to a regression euation, the adVusted +/

increases only if the absolute value of the t statistic of the new variable is greater

than one.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Bf a new independent variable is added to a regression euation, the

adVusted +/ increases only if the absolute value of the t statistic of the new variable

is greater than one in absolute value.

1


44/133

eedback: statistic can be used only to test nested models.

1?. *redictions of a dependent variable are subVect to sampling variation.

Answer: 5rue



"()*+:

eedback: *redictions of a dependent variable are subVect to sampling variation

since they are obtained using J) estimators.

/@. 5o make predictions of logarithmic dependent variables, they rst have to be

converted to their level forms.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Bt is possible to make predictions of dependent variables when they are in

their logarithmic form. Bt is not necessary to convert them into their level forms.

&hapter 3

1. A _____ variable is used to incorporate ualitative information in a regression

model.

a. dependentb. continuous

c. binomial

d. dummy

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: escribing ualitative Bnformation

"()*+:

eedback: A dummy variable or binary variable is used to incorporate ualitativeinformation in a regression model.

/. Bn a regression model, which of the following will be described using a binary

variable'

a. &hether it rained on a particular day or it did not

b. 5he volume of rainfall during a year

c. 5he percentage of humidity in air on a particular day


45/133

d. 5he concentration of dust particles in air

Answer: a

i!culty: Dedium


A-%ead: escribing ualitative Bnformation"()*+:

eedback: A binary variable is used to describe ualitative information in regression

model. 5herefore, such a variable will be used to describe whether it rained on a

particular day or it did not.

2. &hich of the following is true of dummy variables'

a. A dummy variable always takes a value less than 1.

b. A dummy variable always takes a value higher than 1.

c. A dummy variable takes a value of @ or 1.

d. A dummy variable takes a value of 1 or 1@.

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A dummy variable takes a value of @ or 1.

5he following simple model is used to determine the annual savings of an individual

on the basis of his annual income and education.

)avings H L@I@ Edu I L1BncIu 5he variable 6Edu# takes a value of 1 if the person is educated and the variable 6Bnc#

measures the income of the individual.

3. +efer to the model above. 5he inclusion of another binary variable in this model

that takes a value of 1 if a person is uneducated, will give rise to the problem of

_____.

a. omitted variable bias

b. self-selection

c. dummy variable trapd. heteroskedastcity

Answer: c

i!culty: Dedium



"()*+: Analytic


46/133

eedback: 5he inclusion of another dummy variable in this model would introduce

perfect collinearity and lead to a dummy variable trap.


on the basis of his annual income and education.

)avings H L@I@ Edu I L1BncIu 5he variable 6Edu# takes a value of 1 if the person is educated and the variable 6Bnc#


4. +efer to the model above. 5he benchmark group in this model is _____.

a. the group of educated people

b. the group of uneducated people

c. the group of individuals with a high income

d. the group of individuals with a low income

Answer: b

i!culty: Doderate


A-%ead: A )ingle ummy Bndependent Nariable

"()*+: Analytic

eedback: 5he benchmark group is the group against which comparisons are made.

Bn this case, the savings of a literate person is being compared to the savings of an

illiterate personC therefore, the group of illiterate people is the base group or

benchmark group.


on the basis of his annual income and education.)avings H L@I@ Edu I L1BncIu

5he variable 6Edu# takes a value of 1 if the person is educated and the variable 6Bnc#


7. +efer to the above model. Bf @ Q @, _____.

a. uneducated people have higher savings than those who are educated

b. educated people have higher savings than those who are not educated

c. individuals with lower income have higher savings

d. individual with lower income have higher savings

Answer: b

i!culty: Doderate



"()*+: Analytic


47/133

eedback: 5he coe!cient @ measures the impact of education on an individual#s

annual savings. Bf it has a positive impact, as in this case, educated people should

have higher savings.

9. 5he income of an individual in "udopia depends on his ethnicity and several other

factors which can be measured uantitatively. Bf there are 4 ethnic groups in"udopia, how many dummy variables should be included in the regression euation

for income determination in "udopia'

a. 1

b. 4

c. 7

d. 3

Answer: d

i!culty: Doderate


A-%ead: (sing ummy Nariables for Dultiple ;ategories

"()*+: Analytic

eedback: Bf a regression model is to have di8erent intercepts for, say, g groups or

categories, we need to include g -1 dummy variables in the model along with an

intercept. Bn this case, the regression euation should include 4-1H3 dummy

variables since there are 4 ethnic groups.

_____

variable.a. dependent variable

b. ordinal variable

c. continuous variable

d. *oisson variable

Answer: b

i!culty: Doderate


A-%ead: (sing ummy Nariables for Dultiple ;ategories

"()*+: Analyticeedback: 5he value of the variable 6+ating# depends on the employer#s rating of

the worker. 5herefore, it incorporates ordinal information and is called an ordinal

variable.

?. &hich of the following is true of ;how test'

a. Bt is a type of t test.

b. Bt is a type of sign test.


48/133

c. Bt is only valid under homoskedasticty.

d. Bt is only valid under heteroskedasticity.

Answer: c

i!culty: Easy

"loom#s: $nowledgeA-%ead: Bnteractions Bnvolving ummy Nariables

"()*+:

eedback: )ince the ;how test is Vust an test, it is only valid under

homoskedasticity.

1@. &hich of the following is true of dependent variables'

a. A dependent variable can only have a numerical value.

b. A dependent variable cannot have more than / values.

c. A dependent variable can be binary.

d. A dependent variable cannot have a ualitative meaning.

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: A "inary ependent Nariable: 5he Jinear *robability Dodel

"()*+:

eedback: A dependent variable is binary if it has a ualitative meaning.

11. Bn the following regression euation, y is a binary variable:

yH L@IL11ILk kI u

Bn this case, the estimated slope coe!cient, ^

β1 measures _____.

a. the predicted change in the value of y when 1 increases by one unit, everything

else remaining constant

b. the predicted change in the value of y when 1 decreases by one unit, everything

else remaining constant

c. the predicted change in the probability of success when 1 decreases by one unit,

everything else remaining constant

d. the predicted change in the probability of success when 1 increases by one unit,

everything else remaining constant

Answer: d

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A binary dependent variable is used when a regression model is used to

eplain a ualitative event. 5he dependent variable takes a value of 1 when the


49/133

event takes place =success> and it takes a value of ero when the event does not

take place. 5he coe!cient of an independent variable in this case measures the

predicted change in the probability of success when the independent variable

increases by one unit.

1/. ;onsider the following regression euation: y H L@IL11ILk kI u Bn which of the following cases, the dependent variable is binary'

a. y indicates the gross domestic product of a country

b. y indicates whether an adult is a college dropout

c. y indicates household consumption ependiture

d. y indicates the number of children in a family

Answer: b

i!culty: Easy



"()*+: Analytic

eedback: 5he dependent variable, y is binary if it is used to indicate a ualitative

outcome.

12. &hich of the following auss-Darkov assumptions is violated by the linear

probability model'

a. 5he assumption of constant variance of the error term.

b. 5he assumption of ero conditional mean of the error term.

c. 5he assumption of no eact linear relationship among independent variables.

d. 5he assumption that none of the independent variables are constants.

Answer: a

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he linear probability model violates the assumption of constant variance

of the error term.

13. &hich of the following problems can arise in policy analysis and program

evaluation using a multiple linear regression model'a. 5here eists homoscedasticity in the model.

b. 5he model can produce predicted probabilities that are less than ero and greater

than one.

c. 5he model leads to the omitted variable bias as only two independent factors can

be included in the model.

d. 5he model leads to an overestimation of the e8ect of independent variables on

the dependent variable.


50/133

Answer: b

i!culty: Easy

"loom#s: $nowledge

A-%ead: Dore on *olicy Analysis and *rogram Evaluation

"()*+:eedback: 5he model can produce predicted probabilities that are less than ero and

greater than one.

14. ;onsider the following regression euation: y H L@IL11ILk kI u

Bn which of the following cases, is 6y# a discrete variable'

a. y indicates the gross domestic product of a country

b. y indicates the total volume of rainfall during a year

c. y indicates household consumption ependiture

d. y indicates the number of children in a family

Answer: d

i!culty: Easy

"loom#s: $nowledge

A-%ead: Bnterpreting +egression +esults with iscrete ependent Nariables

"()*+:

eedback: 5he number of children in a family can only take a small set of integer

values. 5herefore, y is a discrete variable if it measures the number of children in a

family.

17. A binary variable is a variable whose value changes with a change in the

number of observations.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A binary variable is one whose value depends on the event taking place.

19. A dummy variable trap arises when a single dummy variable describes a given

number of groups.

Answer: alse

i!culty: Easy

"loom#s: $nowledge


"()*+:


51/133

eedback: A dummy variable trap arises when too many dummy variables describe

a given number of groups.

1


52/133

c. 5he rdinary Jeast )uare estimators are not the best linear unbiased estimators

if heteroskedasticity is present.

d. Bt is not possible to obtain statistics that are robust to heteroskedasticity of an

unknown form.


"loom#s: $nowledge

A-%ead: ;onseuences of %eteroskedasticity for J)

"()*+:

eedback: 5he rdinary Jeast )uare estimators are no longer the best linear

unbiased estimators if heteroskedasticity is present in a regression model.

/. ;onsider the following regression model: yiHL@IL1 iIui. Bf the rst four auss-

Darkov assumptions hold true, and the error term contains heteroskedasticity, then

_____.

a. Nar=uiOi> H@

b. Nar=uiOi> H1

c. Nar=uiOi> H Si/

d. Nar=uiOi> HS

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: %eteroskedasticity-+obust Bnference after J) Estimation

"()*+:

eedback: Bf the rst four auss-Darkov assumptions hold and the error termcontains heteroskedasticity, then Nar=uiOi> H Si/.

2. 5he general form of the t statistic is _____.

a. t =estimate−hypothesized value

standard error

b. t =hypothesized value−estimate

standard error

c. t =

standard error

estimate−hypothesized value

d. t =estimate−hypothesized value

Answer: a

i!culty: Easy

"loom#s: $nowledge


53/133


"()*+:

eedback: 5he general form of the t statistic is t =estimate−hypothesized value

standard error .

3. &hich of the following is true of the J) t statistics'

a. 5he heteroskedasticity-robust t statistics are Vustied only if the sample sie is

large.

b. 5he heteroskedasticty-robust t statistics are Vustied only if the sample sie is

small.

c. 5he usual t statistics do not have eact t distributions if the sample sie is large.

d. Bn the presence of homoscedasticity, the usual t statistics do not have eact t

distributions if the sample sie is small.

Answer: a



"()*+:

eedback: 5he heteroskedasticity-robust t statistics are Vustied only if the sample

sie is large.

4. 5he heteroskedasticity-robust _____ is also called the heteroskedastcity-robust

&ald statistic.

a. t statistic

b. F statisticc. L statistic

d. statistic

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he heteroskedasticity-robust F statistic is also called the

heteroskedastcity-robust &ald statistic.

7. &hich of the following tests helps in the detection of heteroskedasticity'

a. 5he "reusch-*agan test

b. 5he "reusch-odfrey test

c. 5he urbin-&atson test

d. 5he ;how test


54/133

Answer: a

i!culty: Easy

"loom#s: $nowledge

A-%ead: 5esting for %eteroskedasticity

"()*+:

eedback: 5he "reusch-*agan test is used for the detection of heteroskedasticity ina regression model.

9. &hat will you conclude about a regression model if the "reusch-*agan test results

in a small p-value'

a. 5he model contains homoskedasticty.

b. 5he model contains heteroskedasticty.

c. 5he model contains dummy variables.

d. 5he model omits some important eplanatory factors.

Answer: b

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: 5he "reusch-*agan test results in a small p-value if the regression model

contains heteroskedasticty.


55/133

c. 5he number of regressors used in the &hite test is larger than the number of

regressors used in the "reusch-*agan test.

d. 5he number of regressors used in the "reusch-*agan test is larger than the

number of regressors used in the &hite test.


"loom#s: $nowledge


"()*+:

eedback: 5he &hite test includes the suares and cross products of all

independent variables. 5herefore, the number of regressors is larger for the &hite

test.

1@. &hich of the following is true of the &hite test'

a. 5he &hite test is used to detect the presence of multicollinearity in a linear

regression model.

b. 5he &hite test cannot detect forms of heteroskedasticity that invalidate the usual

rdinary Jeast )uares standard errors.

c. 5he &hite test can detect the presence of heteroskedasticty in a linear regression

model even if the functional form is misspecied.

d. 5he &hite test assumes that the suare of the error term in a regression model is

uncorrelated with all the independent variables, their suares and cross products.

Answer: d

i!culty: Easy

"loom#s: $nowledgeA-%ead: 5esting for %eteroskedasticity

"()*+:

eedback: 5he &hite test assumes that the suare of the error term in a regression

model is uncorrelated with all the independent variables, the suares of

independent variables and all the cross products.


a. Bn ordinary least suares estimation, each observation is given a di8erent weight.

b. Bn weighted least suares estimation, each observation is given an identical

weight.c. Bn weighted least suares estimation, less weight is given to observations with a

higher error variance.

d. Bn ordinary least suares estimation, less weight is given to observations with a

lower error variance.

Answer: c

i!culty: Easy


56/133

"loom#s: $nowledge

A-%ead: &eighted Jeast )uares Estimation

"()*+:

eedback: Bn weighted Jeast )uares estimation, less weight is given to

observations with a higher error variance.

1/. &eighted least suares estimation is used only when _____.

a. the dependent variable in a regression model is binary

b. the independent variables in a regression model are correlated

c. the error term in a regression model has a constant variance

d. the functional form of the error variances is known

Answer: d

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: &eighted Jeast )uares estimation is used only when the functional form

of the error variances is known.

12. ;onsider the following regression euation: y= β

0+ β

1 x

1+u

. &hich of the

following indicates a functional form misspecication in E=yO>'

a. rdinary Jeast )uares estimates eual &eighted Jeast )uares estimates.

b. rdinary Jeast )uares estimates eceed &eighted Jeast )uares estimates by a

small magnitude.

c. &eighted Jeast )uares estimates eceed rdinary Jeast )uares estimates by asmall magnitude.

d. rdinary Jeast )uare estimates are positive while &eighted Jeast )uares

estimates are negative.

Answer: d

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: Bf rdinary Jeast )uare estimates are positive while &eighted Jeast)uares estimates are negative, the functional form of a regression euation is said

to be misspecied.

13. &hich of the following tests is used to compare the rdinary Jeast )uares

=J)> estimates and the &eighted Jeast )uares =&J)> estimates'

a. 5he &hite test

b. 5he %ausman test


57/133

c. 5he urbin-&atson test

d. 5he "reusch-odfrey test

Answer: b

i!culty: Easy

"loom#s: $nowledgeA-%ead: &eighted Jeast )uares Estimation

"()*+:

eedback: 5he %ausman test can be used to formally compare the J) and &J)

estimates to see if they di8er by more than sampling error suggests they should.

14. 5he linear probability model contains heteroskedasticity unless _____.

a. the intercept parameter is ero

b. all the slope parameters are positive

c. all the slope parameters are ero

d. the independent variables are binary

Answer: c

i!culty: Easy

"loom#s: $nowledge

A-%ead: 5he Jinear *robability Dodel +evisited

"()*+:

eedback: 5he linear probability model contains heteroskedasticity unless all the

slope parameters are ero.

17. 5he interpretation of goodness-of-t measures changes in the presence of

heteroskedasticity.

Answer: alse

i!culty: Easy

"loom#s: $nowledge

A-%ead: ;onseuences of %eteroskedasticity for J)

"()*+:

eedback: 5he interpretation of goodness-of-t measures is una8ected by the

presence of heteroskedasticty.

19. Dulticollinearity among the independent variables in a linear regression modelcauses the heteroskedasticity-robust standard errors to be large.

Answer: 5rue

i!culty: Easy

"loom#s: $nowledge


"()*+:


58/133

eedback: Dulticollinearity among the independent variables in a linear regression

model causes the heteroskedasticity-robust standard errors to be large.

1 H L@ I L11 I L/1/

I L22 I u. 5hismodel will su8er from functional form misspecication if _____.

a. L@ is omitted from the model

b. u is heteroskedastic

c. 1/ is omitted from the model

d. 2 is a binary variable

Answer: c


59/133

i!culty: Easy


A-%ead: unctional orm Disspecication

"()*+:

eedback: 5he model su8ers from functional form misspecication if 1/ is omitted

from the model since it is a function of 1 which is an observed eplanatory variable.

/. A regression model su8ers from functional form misspecication if _____.

a. a key variable is binary.

b. the dependent variable is binary.

c. an interaction term is omitted.

d. the coe!cient of a key variable is ero.

Answer: c

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A regression model su8ers from functional form misspecication if an

interaction term is omitted.


a. A functional form misspecication can occur if the level of a variable is used when

the logarithm is more appropriate.

b. A functional form misspecication occurs only if a key variable is uncorrelated

with the error term. .

c. A functional form misspecication does not lead to biasedness in the ordinaryleast suares estimators.

d. A functional form misspecication does not lead to inconsistency in the ordinary

least suares estimators.

Answer: a

i!culty: Easy

"loom#s: $nowledge


"()*+:

eedback: A functional form misspecication can occur if the level of a variable isused when the logarithm is more appropriate.

3. &hich of the following is true of +egression )pecication Error 5est =+E)E5>'

a. Bt tests if the functional form of a regression model is misspecied.

b. Bt detects the presence of dummy variables in a regression model.

c. Bt helps in the detection of heteroskedasticity when the functional form of the

model is correctly specied.

introductory econometrics test bank

Documents