Marketing Research, 8e (Burns/Bush)
Chapter 15 Understanding Regression Analysis Basics
1) What is the predictive analysis technique in which one or more variables are used to predict
the level of another by use of the straight-line formula?
A) Regression analysis
B) Correlation
C) Analysis of variables
D) Predictive analytics
2) Researchers sometimes refer to bivariate regression as:
A) Dual regression.
B) Simple regression.
C) Complex regression.
D) Non-complex regression.
3) The ________ is the basis of regression analysis.
A) dual-line equation
B) regression equation
C) straight-line equation
D) variable equation
4) Regression is ________ to correlation by the underlying straight-line relationship.
A) indirectly related
B) not related
C) inversely related
D) directly related
5) What is the type of analysis for the case in which only two variables are involved in the
predictive model?
A) Bivariate regression analysis
B) Multivariate regression analysis
C) Analysis of variables
D) Predictive correlation
6) What variable is customarily termed y in the regression straight-line equation?
A) Null variable
B) Dependent variable
C) Controlled variable
D) Independent variable
7) What variable is customarily termed x in the regression formula?
A) Null variable
B) Dependent variable
C) Independent variable
D) Controlled variable
8) The ________ is that which is predicted in the regression formula.
A) null variable
B) independent variable
C) controlled variable
D) dependent variable
9) To compute a (intercept) and b (slope), you must work with a number of ________ of the
various levels of the dependent variable paired with different levels of the independent variable.
A) observations
B) large samples
C) small samples
D) survey responses
10) What is a way of guaranteeing that the straight line that runs through the points on the scatter
diagram is positioned so as to minimize the vertical distances away from the line of the various
points?
A) Use of the maximum squares criterion
B) Use of the least squares criterion
C) Use of the greatest squares criterion
D) Use of the minimum squares criterion
11) What is a satisfactory method for improving a regression analysis?
A) Use a spiral diagram to identify outlier pairs of points
B) Use a pie chart to identify outlier pairs of points
C) Use a scatter diagram to identify outlier pairs of points
D) Use a cluster diagram to identify outlier pairs of points
12) A ________ model identifies independent and dependent variables and shows their expected
basic relationships to one another.
A) specific statistical
B) general statistical
C) specific conceptual
D) general conceptual
13) The researcher and the manager identify, measure, and analyze specific variables that pertain
to the ________ model in mind.
A) general conceptual
B) specific conceptual
C) statistical
D) analytical
14) ________ is an expansion of bivariate regression analysis in that more than one independent
variable is used in the regression equation.
A) Analyses of variables
B) Multiple regression analysis
C) Correlation analysis
D) Chi-square analysis
15) With multiple regression, you work with a ________ rather than a line.
A) scatter plot
B) bivariate plane
C) regression plane
D) elliptical plane
16) ________ is a very powerful tool because it tells us what factors are related to the dependent
variable, how each factor influences the dependent variable (the sign), and how much each factor
influences it (the size of bi).
A) Chi-square analysis
B) Analysis of variables
C) Correlation analysis
D) Multiple regression
17) The multiple regression analysis model assumes that a straight-line (plane) relationship exists
among the variables, just as in:
A) Bivariate regression analysis.
B) Correlation.
C) Chi-square analysis.
D) Analysis of variables.
18) Multiple R ranges from ________ and represents the amount of the dependent variable
“explained,” or accounted for, by the combined independent variables.
A) -1.0 to +1.0
B) 0 to +1.0
C) 0 to +10
D) 1.0 to 100.00
19) What is the primary term for “coefficient of determination,” a handy measure of the strength
of the overall linear relationship?
A) Multiple T
B) Multiple L
C) Multiple C
D) Multiple R
20) ________ is like a lead indicator of the multiple regression analysis findings since it is one of
the first pieces of information provided in a multiple regression output.
A) Multiple R
B) Multiple C
C) Multiple L
D) Multiple T
21) High multiple R values indicate what?
A) That the regression plane does not apply well to the scatter of points
B) That the regression plane applies well to the scatter of points
C) That the regression plane contains multiple errors
D) That the regression analysis should be rerun
22) Low multiple R values signal what?
A) That the regression plane contains multiple errors
B) That the regression analysis should be rerun
C) That the straight-line model does not apply well
D) That the straight-line model applies well
23) A multiple regression result is an estimate of the population multiple regression equation
and, just as is the case with other estimated population parameters, it is necessary to test for
what?
A) The size of the population
B) Statistical significance.
C) Standard deviation
D) Statistical non-significance
24) Before running a multiple regression, researchers must keep in mind that the independence
assumption stipulates that the independent variables must be:
A) Statistically independent and uncorrelated with one another.
B) Statistically dependent and uncorrelated with one another.
C) Statistically independent and correlated with one another.
D) Statistically dependent and correlated with one another.
25) The presence of correlations among the independent variables in multiple regression is
termed:
A) Independence assumption.
B) Multicollinearity.
C) Regression plane.
D) Multicorrelation.
26) The way to avoid multicollinearity is to use warning statistics issued by most statistical
analysis programs to identify this problem. One commonly used method is the:
A) Deflation factor (DF).
B) Regression factor (RF).
C) Variance inflation factor (VIF).
D) Standard variance factor (SVF).
27) Of the following, which ONE variance inflation factor (VIF) would be a cause for concern?
A) 7
B) 4
C) 1
D) 12
28) If VIF is ________, the researcher should remove that variable from the independent
variable set and rerun the multiple regression.
A) greater than 10
B) equal to 10
C) less than 10
D) approximately 10
29) What does a researcher do with the mixed significance results he or she may have found in a
multiple regression analysis?
A) Leave the nonsignificant independence variable and rerun the multiple regression
B) Eliminate the nonsignificant independence variable and rerun the regression
C) Expand the nonsignificant independence variable and rerun the regression
D) Ignore the mixed significance results since they are meaningless
30) The ________ enables the marketing researcher to think in terms of fewer dimensions within
which the dependent variable relationship operates.
A) trimming process
B) analysis of variance process
C) screening device process
D) mixed significance test
31) A researcher might be seeking market segmentation bases and could use regression to spot
which demographic variables are related to the consumer behavior variable under study. What
type of special use of regression analysis is this considered?
A) Standardized beta
B) “Dummy” independent variable
C) A screening device
D) “Dummy” dependent variable
32) A marketing researcher may be faced with a large number and variety of prospective
independent variables in a general conceptual model, and may use ________ as a way of spotting
the salient independent variables for the dependent variable at hand.
A) bivariate regression
B) analysis of variables
C) correlation analysis
D) multiple regression
33) There are instances in which a marketing researcher may want to use an independent variable
that:
A) Embodies interval-scaling assumptions.
B) Does not embody ordinal-scaling assumptions.
C) Embodies a ratio variable assumption.
D) Does not embody interval-scaling assumptions.
34) The interval–at-minimum scaling assumption requirement of multiple regression may be
relaxed by use of a:
A) Dummy variable.
B) Null variable.
C) Substitute variable.
D) Dependent variable.
35) When a researcher standardizes independent variables through a quick operation that
involves dividing the difference between each independent variable value and its mean by the
standard deviation of that independent variable, it results in the:
A) Beta coefficient.
B) Standardized beta coefficient.
C) Non-standardized beta coefficient.
D) Standardized alpha coefficient.
36) The larger the absolute value of a standardized beta coefficient, the more relative importance
it assumes in:
A) The standardized beta coefficient.
B) Predicting the independent variable.
C) Predicting the dependent variable.
D) Assuming a role as a screening device.
37) Standardized betas indicate the relative importance of:
A) Standardized predictor variables.
B) Formal predictor variables.
C) Non-alternative predictor variables.
D) Alternative predictor variables.
38) Because independent variables are often measured with different units, it is erroneous to
make ________ between the calculated betas.
A) direct comparisons
B) indirect comparisons
C) multiple comparisons
D) objective comparisons
39) When a researcher has many independent variables and wants to narrow the set down to a
smaller number, which form of regression is useful?
A) Variance inflation regression
B) Variance deflation regression
C) Forward multiple regression
D) Stepwise multiple regression
40) When using SPSS to run stepwise multiple regression, there is:
A) No need to trim and rerun the regression analysis.
B) A need to leave the nonsignificant independence variable and rerun the multiple regression.
C) A need to expand the nonsignificant independence variable and rerun the regression.
D) No compelling need to examine the mixed significance results.
41) With ________, the statistically significant independent variable that explains the most
variance in the dependent variable is determined and entered into the multiple regression
equation.
A) standard multiple regression
B) stepwise multiple regression
C) linear regression
D) polynomial regression
42) The final output in stepwise multiple regression contains:
A) Only statistically significant dependent variables.
B) Only statistically insignificant independent variables.
C) Only statistically significant independent variables.
D) Only statistically insignificant dependent variables.
43) Regression analysis springs from ________, which is a measure of the linear association and
not the causal relationship between two variables.
A) bivariate analysis
B) analysis of variance
C) multivariate analysis
D) correlation analysis