QMB 3200 QUIZ 6 WITH COMPLETE
SOLUTIONS
True or False: When plotted, Model 1 (interaction + curvature) should consist of a
sequence of non-parallel curves (one for each level of our qualitative variable).
Note: Assume that y and x1 are quantitative and x2 is qualitative, just like we do for the
printouts for our upcoming exam.
True
False - Correct Answers –True
The reason that we do not include quadratic (i.e., squared) terms for dummy variables
in a multiple linear regression model is that dummy variables consist of 0's and 1's, so
squaring dummy variables will leave their values (0 and 1) unchanged.
True
False - Correct Answers -True
Suppose that we are given the following model, where x1 and x2 are quantitative:
E ( y ) = β0 + β1x1 + β2x2 + β3x1x2
What is the slope for x1 when x2 = 0?
β0
β3
β1
β2 - Correct Answers -β 1
Consider the following two models, where x1 and x2 are quantitative:
Model 1: E ( y ) = β 0 + β 1 x 1 + β 2 x 2 + β 3 x 1 2 + β 4 x 2 2
Model 2: E ( y ) = β 0 + β 1 x 1 + β 2 x 2
To compare these two models using a subset (partial) F-test is equivalent to testing
for...
... curvature in the relationship between both independent variables and the dependent
variable.
... interaction in the relationship between only one independent variable and the
dependent variable.
... interaction and curvature in the relationship between both independent variables and
the dependent variable.
... interaction in the relationship between both independent variables and the dependent
variable.
SOLUTIONS
True or False: When plotted, Model 1 (interaction + curvature) should consist of a
sequence of non-parallel curves (one for each level of our qualitative variable).
Note: Assume that y and x1 are quantitative and x2 is qualitative, just like we do for the
printouts for our upcoming exam.
True
False - Correct Answers –True
The reason that we do not include quadratic (i.e., squared) terms for dummy variables
in a multiple linear regression model is that dummy variables consist of 0's and 1's, so
squaring dummy variables will leave their values (0 and 1) unchanged.
True
False - Correct Answers -True
Suppose that we are given the following model, where x1 and x2 are quantitative:
E ( y ) = β0 + β1x1 + β2x2 + β3x1x2
What is the slope for x1 when x2 = 0?
β0
β3
β1
β2 - Correct Answers -β 1
Consider the following two models, where x1 and x2 are quantitative:
Model 1: E ( y ) = β 0 + β 1 x 1 + β 2 x 2 + β 3 x 1 2 + β 4 x 2 2
Model 2: E ( y ) = β 0 + β 1 x 1 + β 2 x 2
To compare these two models using a subset (partial) F-test is equivalent to testing
for...
... curvature in the relationship between both independent variables and the dependent
variable.
... interaction in the relationship between only one independent variable and the
dependent variable.
... interaction and curvature in the relationship between both independent variables and
the dependent variable.
... interaction in the relationship between both independent variables and the dependent
variable.