Академический Документы
Профессиональный Документы
Культура Документы
TRUE/FALSE
1. Multivariate statistical analysis permit the researcher to consider the effects of three or more variables
at the same time.
2. The variate is a mathematical way in which a set of variables can be represented with one equation.
3. The basic types of multivariate techniques are metric methods and nonmetric methods.
ANS: F
The two basic types of mulitvariate techniques are dependence methods and interdependence methods.
5. The type of measurement scales used will determine which multivariate statistical techniques are
appropriate for the data.
ANS: F
These are nonmetric scales.
8. Multiple regression analysis includes a single independent variable but several dependent variables.
ANS: F
Multiple regression analysis is an extension of simple regression analysis allowing a metric dependent
variable to be predicted by multiple independent variables.
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
9. Mulitvariate dependence techniques are variants of the general linear model (GLM).
11. In multiple regression, dummy variables are those that have no effect on the dependent variable.
ANS: F
A dummy variable uses 0 and 1 to code the different levels of a dichotomous variable.
12. In a regression equation, the beta coefficients indicate the effect on the dependent variable of a 1-unit
increase in any of the independent variables.
13. Partial correlations measure the variance inflation among independent variables.
ANS: F
Partial correlation is the correlation between two variables after taking into account the fact that they
are correlated with other variables too.
14. In multiple regression, the coefficient of multiple determination indicates the percentage of the
variation in Y that can be explained by all independent variables.
15. Multicollinearity in regression analysis refers to how strongly interrelated the independent variables in
a model are.
16. MANOVA predicts multiple continuous dependent variables with multiple continuous independent
variables.
ANS: F
The independent variables are categorical.
17. Discriminant analysis predicts a categorical dependent variable based on a linear combination of
independent variables.
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
ANS: T PTS: 1 REF: p. 590
NAT: AACSB: Reflective Thinking
18. To determine whether the discriminant analysis can be used as a good predictor, information provided
in the “confusion matrix” is used.
19. The purpose of factor analysis is to summarize the information contained in a large number of
variables into as large a number of factors as possible.
ANS: F
Factor analysis is a multivariate interdependence technique that statistically identifies a reduced
number of factors from a larger number of measured variables.
20. A factor loading indicates how strongly a measured variable is correlated with a factor.
21. The most common rule for extracting factors in factor analysis is to base the number of factors on the
number of eigenvalues greater than 5.0
ANS: F
The rule is an eigenvalue greater than 1.0.
23. In factor analysis, "communality" is a measure of the percentage of a variable's variation that can be
explained by the factors.
24. In cluster analysis, each cluster should have low internal homogeneity and high external heterogeneity.
ANS: F
The cluster should have high internal (within-cluster) homogeneity and external (between-cluster)
heterogeneity.
25. Multidimensional scaling provides a means for placing objects in multidimensional space on the basis
of respondents’ judgments of the similarity of objects.
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
ANS: T PTS: 1 REF: p. 599
NAT: AACSB: Reflective Thinking
MULTIPLE CHOICE
2. Which of the following is a mathematical way in which a set of variables can be represented with one
equation?
a. structuralism
b. variate
c. ANOVA
d. synergy
ANS: B PTS: 1 REF: p. 581
NAT: AACSB: Reflective Thinking
4. When a multivariate statistical technique is used to predict a dependent variable from several
independent variables, the researcher is studying:
a. dependence
b. independence
c. interdependence
d. segments
ANS: A PTS: 1 REF: p. 583
NAT: AACSB: Reflective Thinking
9. Nominal and ordinal scales are examples of _____ scales, while interval and ratio scales are examples
of _____scales.
a. metric; co-metric
b. nonmetric; metric
c. nonmetric; advanced
d. metric; continuous
ANS: B PTS: 1 REF: p. 583
NAT: AACSB: Reflective Thinking
10. If the analysis contains only one dependent variable and that variable is metric, the appropriate
statistical analysis is:
a. multiple discriminant analysis
b. conjoint analysis
c. multivariate ANOVA
d. multiple regression
ANS: D PTS: 1 REF: p. 584
NAT: AACSB: Reflective Thinking
11. Which of the following is an appropriate technique when the inputs are metric?
a. cluster analysis
b. metric multidimensional scaling
c. factor analysis
d. all of the above
ANS: D PTS: 1 REF: p. 584
NAT: AACSB: Reflective Thinking
12. Mulitvariate dependence techniques are variants of the _____, which is a way of modeling some
process based on how different variables cause fluctuations from the average dependent variable.
a. ordinary linear model (OLM)
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
b. weighted average model (WAM)
c. general linear model (GLM)
d. metric scaling model (MSM)
ANS: C PTS: 1 REF: p. 584
NAT: AACSB: Reflective Thinking
13. When a researcher is attempting to predict sales volume by using building permits, amount of
advertising, and the income levels of residents, the researcher is using:
a. univariate analysis
b. a chi-square analysis
c. multiple regression analysis
d. factor analysis
ANS: C PTS: 1 REF: p. 584
NAT: AACSB: Reflective Thinking
14. Which analysis is portrayed by the equation: Y = bo + b1X1 + b2X2 + b3X3... + bnXn?
a. simple regression
b. multiple regression
c. chi-square
d. factor analysis
ANS: B PTS: 1 REF: p. 584
NAT: AACSB: Reflective Thinking
15. A variable that is coded as either zero or one and that has two distinct levels is called a(n):
a. regression variable
b. dummy variable
c. MANOVA variable
d. ANOVA variable
ANS: B PTS: 1 REF: p. 585
NAT: AACSB: Reflective Thinking
16. The correlation between two variables after taking into account the fact that they are correlated with
other variables too is called:
a. partial correlation
b. standardized correlation
c. raw correlation
d. variant correlation
ANS: A PTS: 1 REF: p. 586
NAT: AACSB: Reflective Thinking
17. If the regression equation is: Y = 98.3 +.35X1 + 22.3X2, the predicted value for Y when X1 = 3 and X2
= 5 is:
a. 118.45
b. 210.85
c. 67.23
d. 98.3
ANS: B PTS: 1 REF: p. 586
NAT: AACSB: Reflective Thinking
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
18. A value of R2 = 0.40 means that _____ percent of the variance in the dependent variable is explained
by the independent variables.
a. 80
b. 64
c. 40
d. 16
ANS: C PTS: 1 REF: p. 586
NAT: AACSB: Reflective Thinking
20. In the formula for the F-test in multiple regression, n - k - 1 stands for:
21. Jeff is analyzing data and is concerned over how strongly interrelated the independent variables in his
model are. Jeff is concerned about:
a. multicollinearity
b. MANOVA
c. degrees of freedom
d. convergence
ANS: A PTS: 1 REF: p. 588
NAT: AACSB: Reflective Thinking
22. Which of the following is computed by most regression programs and provide an indication of how
much multicollinearity exists among a set of independent variables?
a. c2
b. b
c. collinear coefficient
d. variance inflation factor (VIF)
ANS: D PTS: 1 REF: p. 588
NAT: AACSB: Reflective Thinking
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
a. VIF > 5.0
b. b < 3.0
c. Power > 0.8
d. a > 0.8
ANS: A PTS: 1 REF: p. 588
NAT: AACSB: Reflective Thinking
24. If the analysis predicts several continuous dependent variables with several categorical independent
variables, the appropriate statistical technique is:
a. multiple regression
b. multiple discriminant analysis
c. conjoint analysis
d. MANOVA
ANS: D PTS: 1 REF: p. 589
NAT: AACSB: Reflective Thinking
26. If a bank wants to differentiate between successful and unsuccessful credit risks for home mortgage
loans, it should use:
a. factor analysis
b. multidimensional scaling
c. MANOVA
d. discriminant analysis
ANS: D PTS: 1 REF: p. 590
NAT: AACSB: Reflective Thinking
27. In discriminant analysis, a linear combination of independent variables that explains group
memberships is known as a(n):
a. regression equation
b. discriminant function
c. discriminant factor
d. n-way ANOVA
ANS: B PTS: 1 REF: p. 590
NAT: AACSB: Reflective Thinking
28. Which multivariate analysis statistically identifies a reduced number of factors from a larger number of
measured variables?
a. factor analysis
b. regression
c. discriminant analysis
d. logit analysis
ANS: A PTS: 1 REF: p. 593
NAT: AACSB: Reflective Thinking
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
29. Which of the following indicates how strongly a measured variable is correlated with a factor?
a. factor b
b. discriminator
c. factor link
d. factor loading
ANS: D PTS: 1 REF: p. 593
NAT: AACSB: Reflective Thinking
30. A researcher has 57 variables in a large dataset and wishes to summarize the information from them
into a reduced set of variables. Which multivariate technique should be used?
a. factor analysis
b. multidimensional scaling
c. logit analysis
d. regression analysis
ANS: A PTS: 1 REF: p. 593
NAT: AACSB: Reflective Thinking
32. In cluster analysis, the researcher wants clusters to have high ______ within-clusters and high
between-cluster ______.
a. independence; dependence
b. significance; insignificance
c. heterogeneity; homogeneity
d. homogeneity; heterogeneity
ANS: D PTS: 1 REF: p. 597
NAT: AACSB: Reflective Thinking
33. General Mills would like to “see” a picture of how its brands are perceived by consumers compared to
competitive brands. Which statistical technique can measure brands in multidimensional space on the
basis of respondents’ judgements of the similarity of the brands?
a. structural equations modeling
b. factor analysis
c. multidimensional scaling
d. partial positioning
ANS: C PTS: 1 REF: p. 599
NAT: AACSB: Reflective Thinking
COMPLETION
1. Statistical methods that permit the study of three or more variables at the same time are called
____________________ statistical analysis.
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
ANS: multivariate
ANS:
dependence, interdependence
interdependance, dependance
3. Multivariate techniques that try to group things together are known as ____________________
methods.
ANS: interdependence
4. When an analysis studies the effect of several independent variables on a single dependent variable
that is interval-scaled, this is called ____________________ analysis.
ANS:
general linear model
GLM
6. A ____________________ variable has two distinct levels that are coded as 0 and 1.
ANS: dummy
7. The test used to test statistical significance by comparing variation explained by the regression
equation to the residual error variation is the ____________________.
ANS: F-test
ANS: Multicollinearity
ANS:
Multivariate analysis of variance
MANOVA
10. If the researcher wants to classify objects into two mutually exclusive categories, the researcher should
use ____________________ analysis.
ANS: discriminant
ANS: factor
12. An indication of how strongly a measured variable is correlated with a factor is given by the
____________________.
14. A statistical technique that measures objects in multidimensional space on the basis of respondents’
judgments of the similarity of objects is ____________________.
15. A multivariate interdependence technique that classifies individuals or objects into a small number of
mutually exclusive and exhaustive groups is ____________________.
ESSAY
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
1. Compare and contrast dependence and interdependence techniques. List the statistical techniques for
both.
ANS:
When hypotheses involve distinction between independent and dependent variables, dependence
techniques are needed. Multiple regression analysis, multiple discriminant analysis, multivariate
analysis of variance, conjoint analysis, and structural equations modeling are all dependence
techniques. When researchers examine questions that do not distinguish between independent and
dependent variables, interdependence techniques are used. No one variable or variable subset is to
be predicted from or explained by the others. The most common interdependence methods are factor
analysis, cluster analysis, and multidimensional scaling.
ANS:
Multiple regression models can be interpreted using these steps:
(1) Examine the model F-test for significance.
(2) Examine the individual statistical tests for each parameter estimate.
(3) Examine the model R2.
(4) Examine collinearity diagnostics, such as variance inflation factors (VIF) for each variable to
detect multicollinearity.
ANS:
An ANOVA or MANOVA model represent a form of the general linear model (GLM). ANOVA can be
extended beyond one-way ANOVA to predict a dependent variable with multiple categorical
independent variables. Multivariate analysis of variance (MANOVA) is a multivariate technique that
predicts multiple continuous dependent variables with multiple independent variables. The
independent variables are categorical, although a continuous control variable can be included in the
form of a covariate.
ANS:
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.
Factor analysis is a prototypical multivariate, interdependence technique. It is a technique of
statistically identifying a reduced number of factors from a larger number of measured variables. The
factors themselves are not measured, but instead, they are identified by forming a variate using the
measured variables. Factors are usually latent constructs like attitude or satisfaction or an index like
social class. A researcher need not distinguish between independent and dependent variables to
conduct factor analysis. Factor analysis can be divided into two types: exploratory factor analysis
(EFA) and confirmatory factor analysis (CFA). Exploratory factor analysis reveals how many
factors exist among a set of variables and what variables match up or “load on” which factors. A
factor loading indicates how strongly correlated a factor is with a measured variable. Factor analysis is
considered a data reduction technique that allows a researcher to summarize information from many
variables into a reduced set of variates or composite variables.
ANS:
Cluster analysis is a multivariate approach for identifying objects or individuals that are similar to one
another in some respect. It classifies individuals or objects into a small number of mutually exclusive
and exhaustive groups. Objects or individuals are assigned to groups so that there is great similarity
within groups and much less similarity between groups. The cluster should have high internal (within-
cluster) homogeneity and external (between-cluster) heterogeneity. Cluster analysis facilitates market
segmentation by identifying subjects or individuals who have similar needs, lifestyles, or responses to
marketing mixes.
© 2010 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in
whole or in part.