Deck 13: Additional Topics in Regression Analysis

Question 1

If the Durbin-Watson statistic d has values between 0 and d_L,this indicates:

A)a positive first-order autocorrelation.
B)a negative first-order autocorrelation.
C)no first-order autocorrelation at all.
D)an inconclusive test.

Answer 1

a positive first-order autocorrelation.

Question 2

The range of the values of the Durbin-Watson statistic,d is:

A)-4 ≤ d ≤ 4
B)-2 ≤ d ≤ 2
C)0 ≤ d ≤ 4
D)0 ≤ d ≤ 2

Answer 2

0 ≤ d ≤ 4

Question 3

Suppose that the sample regression equation of a model is = 10 + 2x₁ + 3x₂ - x₁x₂.If we examine the relationship between x₁ and y for four different values of x₂,we observe that the:

A)four equations have different coefficients of x₁.
B)four equations produced differ only in the intercept term.
C)coefficient of x₂ remains unchanged.
D)coefficient of x₁ remains unchanged.

Answer 3

four equations have different coefficients of x₁.

Question 4

In regression models,multicollinearity arises when the:

A)dependent variables are highly correlated with one another.
B)independent variables are highly correlated with one another.
C)independent variables are highly correlated with the dependent variable.
D)error terms do not have the same variance.

Question 5

Suppose the following scatter plot shows the relationship between X and Y.How might you model Y?

A)with dummy variables
B)with the log normal specification
C)with dummy variables and interactive terms
D)with a correction for heteroscedasticity

Question 6

For the following regression equation = 100 - 12x₁ + 5x₂ - 4x₁x₂,a unit increase in x₁,while holding x₂ constant at a value of 2,decreases the value of y on average by:

A)90
B)15
C)20
D)30

Question 7

Which of the following is not an indicator of multicollinearity?

A)Regression coefficients do differ considerably from values indicated by theory or experience including having incorrect signs.
B)Coefficients of variables believed to be a strong influence have small Student's t statistics indicating that their values do not differ from 0.
C)All the coefficient student t statistics are small,indicating no individual effect.
D)High correlations between individual independent variables.

Question 8

Which of the following is expected to occur in multiple regression analysis if an important variable is omitted from the list of independent variables?

A)It will lead to unbiased least squares estimators.
B)It will lead to biased least squares estimators.
C)It will lead to biased estimators of the variance.
D)It will lead to multicollinearity between predictor variables.

Question 9

Suppose you want to estimate the model Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄.However,you cannot measure X₄,so you estimate Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ instead.This is an example of regression result that will be subject to:

A)autocorrelation.
B)heteroscedasticity.
C)multicollinearity.
D)specification bias.

Question 10

Consider the following plot of residuals from a regression.This pattern suggests which of the following problems?

A)autocorrelation
B)specification bias
C)multicollinearity
D)heteroscedasticity

Question 11

In reference to the Durbin-Watson statistic d and the critical values d_Land d_υ,which of the following statements is false?

A)If d < d_L,we conclude that positive first-order autocorrelation exists
B)If d > d_U,we conclude that there is not enough evidence to show that positive first-order autocorrelation exists
C)If d > 4 - d_L,we conclude that there is negative autocorrelation.
D)If d lies in between d_L and d_U,we conclude that there is no evidence of first-order autocorrelation.

Question 12

Suppose you are interested in examining the determinants of earnings.You have information on the age of the individual as well as their level of education: high school graduate,college graduate or graduate degree.Let Y = earnings,X₁ = age,X₂ = 1 if the person has only a high school degree and 0 otherwise,X₃ = 1 if the person has a college degree and 0 otherwise,X₄ = 1 if the person has a graduate degree and 0 otherwise.Which of the following model specifications would work for this data?

A)Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃
B)Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄
C)Y =
D)Y = β₁ + β₂ + β₃ + β₄ + X₁+ X₂ + X₃ + X₄

Question 13

If a categorical independent variable,such as gender,contains exactly two categories,then how many dummy variable(s)will be needed to uniquely represent these categories?

A)1
B)2
C)3
D)4

Question 14

Suppose you were to run a regression of leisure travel expenditures by households on household income.We would expect that households with low incomes do not travel much.High-income households may or may not travel much,depending on the household's preferences for travel.The results from this regression will be subject to:

A)multicollinearity.
B)specification bias.
C)autocorrelation.
D)heteroscedasticity.

Question 15

Suppose you are interested in estimating the regression: Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃.Using a sample of 40 observations,we get y = 13.2 + 18.4x₁ + 0.033x₂ + 1732.4x₃,R² = 0.88,s
= 6)3,s
= 15.2,s
= )0025,and s
= 1443.2.These results suggest that this model is affected by:

A)autocorrelation.
B)specification bias.
C)multicollinearity.
D)heteroscedasticity.

Question 16

Suppose you are interested in modeling the amount of money a household spends for a house.We would expect income to be a determining factor.In addition,the income tax rate for a household might be important since there are tax advantages to home ownership.If you were to run a regression of home purchase price on income and marginal tax rate,your results might be subject to:

A)multicollinearity.
B)heteroscedasticity.
C)specification bias.
D)autocorrelation.

Question 17

Which of the following regression diagnostic tools is used to study the possible presence of multicollinearity?

A)heteroscedasticity
B)residual plot
C)scatter diagram
D)correlation matrix

Question 18

If the Durbin-Watson statistic has a value close to 0 or 4,which assumption is violated?

A)normality of the errors
B)independence of errors
C)homoscedasticity
D)variance of errors

Question 19

Which of the following is considered one of the most common concerns with time-series data?

A)heteroscedasticity
B)autocorrelation
C)multicollinearity
D)specification bias

Question 20

Suppose we estimate the regression Y_t = β₀ + β₁X_1t + β₂X_2t + β₃X_3t + β₄X_4t + ε_t using 36 months of data.Using the residuals from this regression,we run another regression of on the predicted values
_t.From this regression we get a coefficient of determination R² of 0.09.Let H₀ be that there is no heteroscedasticity.What can you conclude?

A)Reject H₀ at α = 0.05.
B)Reject H₀ at α= 0.10.
C)Reject H₀ at α = 0.01.
D)Unable to reject H₀ at α > 0.10.

Question 21

Suppose the following scatter plot shows the relationship between X and Y.How might you model Y?

A)with a correction for heteroscedasticity
B)with the log normal specification
C)with dummy variables and interactive terms
D)with dummy variables

Question 22

What does the following plot of residuals from a regression analysis suggest?

A)heteroscedasticity
B)specification bias
C)multicollinearity
D)autocorrelation

Question 23

Suppose that the estimated regression equation of a College of Business graduates is given by: = 32,000 + 4,000x + 1,800D,where y is the starting salary,x is the grade point average and D is a dummy variable which takes the value of 1 if the student is a finance major and 0 if not.An accountancy major graduate with a 3.5 grade point average would have an average starting salary of:

A)$47,800
B)$46,000
C)$37,800
D)$32,000

Question 24

In multiple regression analysis,when the independent variables are highly correlated,this situation is called:

A)autocorrelation.
B)homoscedasticity.
C)multicollinearity.
D)linearity.

Question 25

Suppose after running the regression Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄ and examining a plot of the residuals,you have reason to suspect that there is heteroscedasticity in your model.Assume that the heteroscedasticity is directly proportional to the square of the expected value of the dependent variable.How might you transform your dependent variable to correct for this heteroscedasticity?

A)Y_i /
_i
B)Y_i - Y_i-1
C)Y_i - ρY_i-1
D)(Y_i - ρY_i-1)/
_i

Question 26

The Durbin-Watson test is used to detect:

A)heteroscedasticity.
B)specification bias.
C)autocorrelation.
D)multicollinearity.

Question 27

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γY_t-1.Suppose we increase X₁ by one unit in time period t,with all other independent variables in the model held fixed.
What is the expected increase in the dependent variable in time period (t + 2)?

A)β₁γ³
B)β₁γ²
C)β₁γ
D)β₁ + β₀

Question 28

When measuring experimental outcomes,a(n)________ variable represents a variable whose effect is crucial in estimating using minimum variance.

A)independent
B)dependent
C)random
D)treatment

Question 29

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in examining the factors that determine the average length of stay in a hospital across states.You collect data on the following variables:
Y = statewide average hospital stay
X₁ = median state income
X₂ = 1 if the state is in the Northeast,0 otherwise
X₃ = 1 if the state is in the South,0 otherwise
X₄ = 1 if the state is in the Midwest,0 otherwise
X₅ = 1 if the state is in the West,0 otherwise
You run the following regression Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄.What is the additional length of stay that can be attributed to being from a state in the South?

A)β₃
B)β₃ + β₀
C)β₃ - β₂ + β₀
D)Cannot determine the answer with this specification

Question 30

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γY_t-1.Suppose we increase X₁ by one unit in time period t,with all other independent variables in the model held fixed.
What is the total expected increase in the dependent variable over time period t and all future time periods?

A)β₁ / (1 - γY_t-1)
B)1 / (1 - γ)
C)β₁ / (1 - γ)
D)(1 - γβ₁)/ (1 - γ)^t

Question 31

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in examining the factors that determine the average length of stay in a hospital across states.You collect data on the following variables:
Y = statewide average hospital stay
X₁ = median state income
X₂ = 1 if the state is in the Northeast,0 otherwise
X₃ = 1 if the state is in the South,0 otherwise
X₄ = 1 if the state is in the Midwest,0 otherwise
X₅ = 1 if the state is in the West,0 otherwise
You run the following regression Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₅X₅.How much longer would we expect to stay in a hospital in the Northeast than in a hospital in the Midwest?

A)β₀
B)β₀ + β₅
C)β₂
D)β₀ - β₄

Question 32

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in determining the number of hours that college students spend studying each week.You identify the following variables:
Y = number of hours spent studying each week
X₁= 1 if the student is a freshman,0 otherwise
X₂ = 1 if the student is a sophomore,0 otherwise
X₃ = 1 if the student is a junior,0 otherwise
X₄ = 1 if the student is a senior,0 otherwise
X₅ = 1 if the student is a business major,0 otherwise
X₆ = 1 if the student is an arts and sciences major,0 otherwise
X₇ = 1 if the student is an engineering major,0 otherwise
Which of the following regression models would work for the indicators provided?

A)Y = β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄ + β₅X₅ + β₆X₆
B)Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄ + β₅X₅ + β₆X₆ + β₇X₇ + ε_i
C)Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₅X₅ + β₆X₆ + ε_i
D)Y = β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄ + β₅X₅ + β₆X₆ + β₇X₇ + ε_i

Question 33

Which of the following will lead to the least squares estimates being biased?

A)exclusion of a relevant variable
B)heteroscedasticity
C)autocorrelated error terms
D)multicollinearity

Question 34

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γY_t-1.Suppose we increase X₁ by one unit in time period t,with all other independent variables in the model held fixed.
What is the expected increase in the dependent variable in time period (t + 1)?

A)β₁γ
B)β₁γ³
C)β₁γ²
D)β₁ + β₀

Question 35

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in examining the factors that determine the average length of stay in a hospital across states.You collect data on the following variables:
Y = statewide average hospital stay
X₁ = median state income
X₂ = 1 if the state is in the Northeast,0 otherwise
X₃ = 1 if the state is in the South,0 otherwise
X₄ = 1 if the state is in the Midwest,0 otherwise
X₅ = 1 if the state is in the West,0 otherwise
You run the following regression: Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₅X₅.What effect does being a state in the Northeast have on the average length of hospital stay?

A)β₀
B)β₀ + β₅
C)β₂
D)β₀ + β₂

Question 36

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in examining the factors that determine the average length of stay in a hospital across states.You collect data on the following variables:
Y = statewide average hospital stay
X₁ = median state income
X₂ = 1 if the state is in the Northeast,0 otherwise
X₃ = 1 if the state is in the South,0 otherwise
X₄ = 1 if the state is in the Midwest,0 otherwise
X₅ = 1 if the state is in the West,0 otherwise
You run the following regression: Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄.What effect does being a state in the West have on the average length of hospital stay?

A)β₅
B)β₀β₅
C)β₀
D)Cannot determine the answer with this specification

Question 37

For a sample of 500 college professors,the estimated regression equation is given by = 275 - 3x - 2D,where y is the retirement age,x is pre-retirement annual income (in $1,000s),and D is a dummy variable that takes the value of 0 for male professors and 1 for female professors.Assume that there is a relationship between y,x,and D.For male professors with pre-retirement income of $70,000,the average age of retirement is:

A)75
B)70
C)65
D)60

Question 38

If the Durbin-Watson statistic d has values greater than 4 - d_L,this indicates:

A)a positive first-order autocorrelation.
B)a negative first-order autocorrelation.
C)no first-order autocorrelation at all.
D)an inconclusive test.

Question 39

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in determining the number of hours that college students spend studying each week.You identify the following variables:
Y = number of hours spent studying each week
X₁= 1 if the student is a freshman,0 otherwise
X₂ = 1 if the student is a sophomore,0 otherwise
X₃ = 1 if the student is a junior,0 otherwise
X₄ = 1 if the student is a senior,0 otherwise
X₅ = 1 if the student is a business major,0 otherwise
X₆ = 1 if the student is an arts and sciences major,0 otherwise
X₇ = 1 if the student is an engineering major,0 otherwise
Suppose you model the relationship as Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₅X₅ + β₆X₆.What effect does being a business student have on hours studying each week?

A)β₅ - β₀
B)β₅
C)β₅ + β₀
D)β_{5 *} β₀

Question 40

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
You are interested in examining the factors that determine the average length of stay in a hospital across states.You collect data on the following variables:
Y = statewide average hospital stay
X₁ = median state income
X₂ = 1 if the state is in the Northeast,0 otherwise
X₃ = 1 if the state is in the South,0 otherwise
X₄ = 1 if the state is in the Midwest,0 otherwise
X₅ = 1 if the state is in the West,0 otherwise
Which of the following model specifications would work for the data provided above?

A)Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₄X₄ + β₅X₅
B)Y = β₀ + β₁X₁ + β₂X₂ + β₃X₃ + β₅X₅
C)Y = β₁X₁ + β₂X₂ + β₃X₃ + β₅X₅
D)Y =

Question 41

Suppose you are interested in modeling the amount of money a firm spends on marketing their product.In order to have your results be of interest to a wide audience,you collect data from a variety of firms ranging from those who spend quite little on advertising to those that spend quite a bit.If you model advertising expenditures as a function of gross sales,your results might be subject to:

A)autocorrelation.
B)heteroscedasticity.
C)multicollinearity.
D)specification bias.

Question 42

Which of the following distributions is used in hypothesis testing to investigate the presence of heteroscedasticity?

A)the normal distribution
B)the Student's t distribution
C)the chi-square distribution
D)the F distribution

Question 43

Which of the following tests can be used to test autocorrelation?

A)t-test
B)z-test
C)F-test
D)Durbin-Watson test

Question 44

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γ₃Y_t-1.Using a sample of 36 months,we estimate this model and obtain the following results: y_t = 1.33 + 17.6x_1t + 0.94x_2t + 0.39Y_t-1
What value would we typically expect for γ₃?

A)0 < γ < 1
B)-1 < γ < 1
C)γ > 1
D)γ > 0

Question 45

You are interested in examining the factors that influence the amount of stock a person owns.As explanatory variables,you include both the person's income and also the amount of equity they have in their house.Which of the following problems would most likely affect your model?

A)autocorrelation
B)multicollinearity
C)specification bias
D)heteroscedasticity

Question 46

________ occurs when errors are not independently distributed.

A)Linearity
B)Multicollinearity
C)Autocorrelation
D)Heteroscedasticity

Question 47

Consider the regression model = 50 + 25x₁ - 7x₂ - 6x₁x₂.A 1-unit increase in x₂,while holding x₁ constant at a value of 3,decreases the value of y,on average,by:

A)13
B)25
C)33
D)an amount that depends on the value of x₂

Question 48

When is a dummy variable used as an independent variable in a regression model?

A)when the variable involved is numerical
B)when the variable involved is categorical
C)when the variable involved is continuous
D)when two independent variables interact

Question 49

Consider the regression model = 20 + 8x₁ + 5x₂ + 3x₁x₂.Which combination of x₁ and x₂,respectively,results in the largest average value of y?

A)3 and 5
B)5 and 3
C)6 and 3
D)3 and 6

Question 50

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γ₃Y_t-1.Using a sample of 36 months,we estimate this model and obtain the following results: y_t = 1.33 + 17.6x_1t + 0.94x_2t + 0.39Y_t-1
If X₁ were to increase by 1-unit in time t,by how much would we expect Y to change in period (t + 1)?

A)17.6
B)14.94
C)6.86
D)10.73

Question 51

Consider the regression model = 30 + 15x₁ - 10x₂ + 5x₁x₂.A 1-unit increase in x₂,while holding x₁ constant at 1,changes the value of y,on average,by:

A)-5
B)-10
C)+10
D)+5

Question 52

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γ₃Y_t-1.Using a sample of 36 months,we estimate this model and obtain the following results: y_t = 1.33 + 17.6x_1t + 0.94x_2t + 0.39Y_t-1
If X₁ were to increase by 1-unit in time t,by how much would we expect Y to change in period t?

A)17.6(0.39)
B)17.6 + 1.33
C)17.6 - 0.39
D)17.6

Question 53

Which of the following is true of the error term used in linear regression?

A)It represents the joint influence of all the dependent variables in the regression model.
B)It represents the joint influence of factors,other than the dependent and independent variables,on the regression model.
C)It represents the joint influence of all the independent variables in the regression model.
D)It represents the combined effect of the dependent,independent,and non-represented factors on the regression model.

Question 54

Suppose we estimate the following regression using 48 months of data: Y_t = β₀ + β₁X_1t + β₂X_2t + β₃X_3t + β₄X_4t + ε_t
Using the residuals from this regression,we run another regression of
On the predicted values
_t. From this regression we get an R² of 0.14.Let H₀ be that there is no heteroscedasticity.What can you conclude?

A)Reject H₀ at α = 0.05,but not 0.025
B)Reject H₀ at α = 0.01,but not 0.005
C)Reject H₀ at α = 0.005
D)Unable to reject H₀ at α ≤ 0.10

Question 55

THE NEXT QUESTIONS ARE BASED ON THE FOLLOWING INFORMATION:
Consider the following model: Y = β₀ + β₁X_1t + β₂X_2t + γ₃Y_t-1.Using a sample of 36 months,we estimate this model and obtain the following results: y_t = 1.33 + 17.6x_1t + 0.94x_2t + 0.39Y_t-1
If X₁ were to increase by 1-unit in time t,by how much would we expect Y to change over all current and future time periods as a result of this increase?

A)45.13
B)28.85
C)17.99
D)34.59

Question 56

Consider the regression model = 10 + 6x₁ + 2x₂.A 1-unit increase in x₂,while holding x₁ constant,increases the value of y,on average,by:

A)2
B)8
C)18
D)an amount that depends on the value of x₁

Question 57

You are interested in modeling the after-tax profits for your firm over the past 36 months.Which of the following problems would most likely affect your model?

A)autocorrelation
B)multicollinearity
C)specification bias
D)heteroscedasticity

Question 58

Consider the first-order model = 50 - 10x₁ + 8x₂ - 2x₁x₂.A 1-unit increase in x₁,while holding x₂ constant at a value of 4,decreases the value of y,on average,by:

A)42
B)40
C)18
D)an amount that depends on the value of x₁

Question 59

When does multicollinearity occur in a multiple regression model?

A)when the dependent variables are highly correlated
B)when the independent variables are minimally correlated
C)when the independent variables are highly correlated
D)when the independent variables have no correlation at all

Question 60

In a regression model with two predictors x₁ and x₂,an interaction term may be used when:

A)the effect of x₁ on the dependent variable is influenced by x₂.
B)both the variables are independent variables.
C)both variables are influential to each other.
D)the effect of x₂ on the dependent variable is not influenced by x₁.

Question 61

A regression model with three independent variables was constructed to analyze certain data: y = β₀ + β₁X₁ + β₃X₃ + β₂X₂ + ε.But while estimating the coefficient,the following regression model was mistakenly used: y = α₀ + α₁x₁ + μ.From the second formula,which of the following can be deduced to be affecting the regression model?

A)specification bias
B)autocorrelation
C)heteroscedasticity
D)sampling error

Question 62

Heteroscedasticity is more likely to arise in the log linear regression model.

Question 63

Model specification includes selection of the dependent and independent variables and the algebraic form of the model.

Question 64

When all the coefficient student t statistics are small,indicating no individual effect,and yet the overall F statistic indicates a strong effect for the total regression model,the model is said to be affected by:

A)heteroscedasticity.
B)homoscedasticity.
C)multicollinearity.
D)sampling error.

Question 65

For which of the following values of the Durbin-Watson statistic,d,would negative correlation be concluded?

A)between d_L ans d_U
B)> 4 - d_L
C)> 4 - d_U
D)< 4 - d_L

Question 66

Considering r to be the sample estimate,which of the following is the formula for calculating the Durbin-Watson test statistic,d?

A)d = r² -1
B)d = r -1
C)d = 1 - r
D)d = 2(1 - r)

Question 67

Which of the following is the similarity between how heteroscedasticity and autocorrelations occur?

A)Both of them occur due to biased coefficient estimates.
B)Both of them occur due to highly correlated independent variables.
C)Both of them occur due to uniform variances across dependent variables.
D)Both of them occur due to assumptions in the distribution of error terms.

Question 68

From a statistical perspective,the regression model objectives can be divided into either a prediction of the mean of the dependent variable,or an estimation of one or more of the individual coefficients.

Question 69

If an analyst is regressing individual independent variables on all other independent variables of a regression model,he or she is testing for:

A)specification bias.
B)sampling error.
C)heteroscedasticity.
D)multicollinearity.

Question 70

Models in which the error terms do not all have the same variance are said to exhibit:

A)heteroscedasticity.
B)autocorrelation.
C)specification bias.
D)multicollinearity.

Question 71

What does the following plot of residuals from a regression analysis suggest?

A)autocorrelation
B)multicollinearity
C)heteroscedasticity
D)specification bias

Question 72

Kurt is trying to regress a model that studies market prices between similar products from different companies.During his study he realized that one of the independent variables,the competitor's price,was causing multicollinearity issues with the model.If Kurt removes the variable from the model,which of the following statistical phenomenon could affect Kurt's model?

A)specification bias
B)heteroscedasticity
C)sampling error
D)autocorrelation

Question 73

Which of the following is true of the value of the Durbin-Watson statistic,d,when there is positive correlation?

A)The value of d would always be a number less than 0.
B)The value of d would be approximately 0.
C)The value of d would be more than 4.
D)The value of d would be between 0 and 4

Question 74

If the Durbin-Watson statistic,d,is found to be 2,which of the following would be considered true?

A)The correlation between errors close-by in time is strong.
B)The errors are not independent.
C)The errors are not autocorrelated.
D)The regression model is not based on a time-series.

Question 75

Correlations between first-order errors through time are defined as:

A)autocorrelation.
B)cross-correlation.
C)heteroscedasticity.
D)multicollinearity.

Question 76

When computing the Durbin-Watson statistic,what value will the sample estimate,r,have if the errors are not autocorrelated?

A)0
B)1
C)< 0
D)2

Question 77

In a regression model such as y = β₀ + β₁X₁ + β₂X₂ + ε,if changes in x₁ and x₂ happen simultaneously,the model is said to be affected by:

A)specification bias.
B)heteroscedasticity.
C)multicollinearity.
D)autocorrelation.

Question 78

If ε_t is the error in time t,ε_t-1 is the error in the previous time period,ρ is the correlation coefficient,and μ_t a random variable with autocorrelation,which of the following is the first-order autoregressive model of autocorrelated behavior?

A)ε_t = ρε_t-1μ_t
B)ε_t =
C)ε_t = ρε_t-1 + μ_t
D)ε_t = ρε_t-1 - μ_t

Question 79

Calculate the d_U value when k = 5,n = 17,and α is taken to be 0.01

A)5.85
B)1.85
C)1.63
D)2.37

Question 80

Which of the following can cause specification bias in a regression model?

A)omission of variables uncorrelated to the independent variables
B)omission of variables correlated to the independent variables
C)inclusion of autocorrelated variables
D)inclusion of an error term