1
Chapter 18: Multivariate Data Analysis
Multiple Choice
1. Which type of multivariate analysis should be used when a researcher wants to estimate
the utility that consumers associate with different product features?
a. Conjoint analysis
b. Cluster analysis
c. Multiple regression analysis
d. Factor analysis
e. Multiple discriminant analysis
2. Which type of multivariate analysis should be used when a researcher wants to identify
subgroups of individuals that are homogeneous within subgroups and different from other
subgroups?
a. Conjoint analysis
b. Cluster analysis
c. Multiple regression analysis
d. Factor analysis
e. Multiple discriminant analysis
3. Which type of multivariate analysis should be used when a researcher wants predict
group membership on the basis of two or more independent variables?
a. Conjoint analysis
b. Cluster analysis
c. Multiple regression analysis
d. Factor analysis
e. Multiple discriminant analysis
4. Which type of multivariate analysis should be used when a researcher wants to reduce a
set of variables to a smaller set of composite variables by identifying underlying
dimensions of the data?
a. Conjoint analysis
b. Cluster analysis
c. Multiple regression analysis
d. Factor analysis
e. Multiple discriminant analysis
5. Which type of multivariate analysis should be used when a researcher wants to predict a
dependent variable based on the levels of more than one independent variable?
a. Conjoint analysis
b. Cluster analysis
c. Multiple regression analysis
d. Factor analysis
e. Multiple discriminant analysis
6. What type of analysis fits a plane to observations in a multidimensional space?
a. Simple linear regression
b. Multiple regression analysis
c. Multiple discriminant analysis
d. Dummy variable analysis
e. Collinearity analysis
3
7. For which statistical analysis is the following formula used?
Y = a + b1X1 + b2X2 + b3X3 + … + bn Xn
a. Correlation analysis
b. Chi-square analysis
c. Multiple regression
d. Conjoint analysis
e. Factor analysis
8. If “R squared” in a regression analysis is found to be .65, this means that ________
percent of the variation in the dependent variable can be explained by variation in the
independent variable.
a. 35
b. 85
c. 65
d. 54
e. 45
9. In regression analysis, when males are coded as “0” and females are coded as “1”, what
type of variables are being used?
4
a. Bivariate variables
b. Dummy variables
c. Collinear variables
d. Discriminant variables
e. Conjoint variables
10. In multiple discriminant analysis, the dependent variable must be ________ , while in
multiple regression analysis, the dependent variable must be ________ .
a. nominal; nominal
b. nominal; metric
c. ordinal; nominal
d. metric; metric
e. metric; nominal
11. In multiple discriminant analysis, the discriminant score is typically identified as a(n)
________ score.
a. t
b. R
c. Z
d. R squared
e. square root of R
12. In discriminant analysis, the classification matrix is also called a(n):
a. diagonal matrix.
b. collinear matrix.
c. dummy matrix.
d. confusion matrix.
e. scaling matrix.
13. In factor analysis, a linear combination of variables that are correlated with one another is
called a(n):
a. discriminant factor.
b. underlying factor.
c. factor.
d. overlying factor.
e. dummy factor.
14. Which type of statistical analysis is used to determine what features a new car should
have and how this car should be priced?
a. Bivariate analysis
b. Chi-square analysis
c. One-group t-test
d. Conjoint analysis
e. Two-group t-test
15. In data mining, which task deals with using regression to predict subgroup membership
with high predictive accuracy?
a. Modeling
b. Clustering
c. Factoring
d. Classification
e. Application
True/False
16. Multivariate statistical analysis procedures are a logical extension of both univariate and
bivariate statistical procedures.
17. Regression analysis can be used to prove causation between variables.
18. The goal of discriminant analysis is to predict a categorical variable.
19. Cluster analysis is used to identify people who are similar to one another in regard to
specific variables.
20. In factor analysis, there is no dependent variable.