Deck 24: Appendix: Multivariate Supplement

Question 1

Which of the following statistical techniques is appropriate when the variables to be analyzed are interrelated without designations as to whether they are criterion and predictor variables?

A) Multiple regression
B) Multivariate analysis of variance
C) Discriminant analysis
D) Factor analysis
E) Path analysis

Answer 1

D

Question 2

Which of the following statistical techniques uses two or more independent,metric variables to classify observations into categories of a nominal,dependent variable?

A) Factor analysis
B) Multivariate analysis of variance
C) Multiple regression
D) Multidimensional scaling
E) Discriminant analysis

Answer 2

E

Question 3

What value in a regression equation indicates the level of influence X exerts on Y?

A)
B) Y
C)
D)
E) F test

Answer 3

C

Question 4

In which of the following situations could a research analyst use multiple regression?

A) A real estate development company wants to estimate the probable sales of construction services on the basis of marriage rates, population movement in the region, and interest rates on construction loans
B) A psychologist wants to understand the underlying personality factors associated with materialism in consumers
C) A firm wants to identify segments of the market to pursue
D) The brand manager for Tide laundry detergent wants to understand how consumers perceive Tide relative to other laundry detergents
E) All of the above

Question 5

Which of the following statistical techniques predicts or explains the value for a dependent variable using the values of independent variables?

A) Factor analysis
B) Multivariate analysis of variance
C) Multiple regression
D) Multidimensional scaling
E) Discriminant analysis

Question 6

Which of the following measures is useful for detecting the presence of multicollinearity in a regression equation?

A) Variable inflation factor
B) Standard error
C) Correlation coefficient
D) Beta
E) Alpha

Question 7

Statistical techniques that focus upon and bring out the structure of simultaneous relationships among three or more variables are called _____ analysis.

A) bivariate
B) multivariate
C) parametric
D) nonparametric
E) ratio

Question 8

At what level does the variable inflation factor (VIF)index suggest the presence of collinearity?

A) 10
B) 20
C) 40
D) 50
E) 80

Question 9

All of the following types of techniques are useful for data reduction except _____.

A) factor analysis
B) multivariate analysis of variance
C) cluster analysis
D) multidimensional scaling
E) all are useful for data reduction

Question 10

An examination of differences across groups lies at the heart of the basic concept of _____.

A) regression analysis
B) discriminant analysis
C) conjoint analysis
D) factor analysis
E) structural equations modeling

Question 11

Multiple regression is a statistical technique that _____.

A) identifies homogeneous subgroups
B) identifies patterns underlying combinations of the original variables capable of summarizing the original set
C) develops a perceptual map of the locations of some objects relative to others
D) predicts or explains the value for a dependent variable using the values of independent variables
E) uses two or more independent, metric variables to classify observations into categories of a nominal, dependent variable

Question 12

A research analysis should deal with multicollinearity among variables in a regression analysis by _____.

A) choosing one of the variables and eliminating the others
B) creating a new composite variable based on the intercorrelated variables for use in the regression analysis
C) indicating that multicollinearity exists in the limitations section of the research report
D) eliminating all of the intercorrelated variables from the analysis
E) both a and b

Question 13

_____ variables are nominal variables that may be used as predictors or independent variables in regression analysis by coding them with the values 0 and 1.

A) Interval
B) Categorical
C) Coefficient
D) Dummy
E) Beta

Question 14

What is reflected by the adjusted R²?

A) The standard error of the model
B) The significance of the equation
C) The number of variables used in the model
D) The model's goodness of fit
E) The analysis of variance

Question 15

Which of the following is NOT a problem associated with multicollinearity?

A) Estimated regression coefficients can fluctuate widely
B) It is difficult to assess the relative importance of the independent variables in explaining the variation in the dependent variables
C) Predictor variables may be incorrectly included or removed in stepwise regression
D) It becomes difficult to compute the correct test statistic
E) All of the above are problems caused by multicollinearity

Question 16

Which of the following statistical techniques identifies patterns underlying combinations of the original variables capable of summarizing the original set?

A) Factor analysis
B) Multivariate analysis of variance
C) Cluster analysis
D) Multidimensional scaling
E) Discriminant analysis

Question 17

_____ is a regression procedure in which the predictor variables enter or leave the regression equation one at a time.

A) Forward selection
B) Backward elimination
C) Stepwise selection
D) Ad hoc selection
E) Random elimination

Question 18

In which of the following situations could a research analyst use discriminant analysis?

A) A real estate development company wants to estimate the probable sales of construction services on the basis of marriage rates, population movement in the region, and interest rates on construction loans
B) A psychologist wants to understand the underlying personality factors associated with materialism in consumers
C) An airline wants to classify its customers into groups based on their relative profitability
D) The brand manager for Tide laundry detergent wants to understand how consumers perceive Tide relative to other laundry detergents
E) A retail store wants to determine if there are differences in shopping frequency associated with gender

Question 19

Which of the following statistical techniques identifies homogenous subgroups?

A) Factor analysis
B) Multivariate analysis of variance
C) Cluster analysis
D) Multidimensional scaling
E) Discriminant analysis

Question 20

Multidimensional scaling is a statistical technique that _____.

A) identifies homogeneous subgroups
B) identifies patterns underlying combinations of the original variables capable of summarizing the original set
C) develops a perceptual map of the locations of some objects relative to others
D) predicts or explains the value for a dependent variable using the values of independent variables
E) uses two or more independent, metric variables to classify observations into categories of a nominal, dependent variable

Question 21

The technique used to provide a more simple and interpretable picture of the relationships between factors and variables is called _____.

A) rotation
B) regression
C) resistance
D) principal components
E) residual analysis

Question 22

What type of data is used with conjoint analysis?

A) Interval
B) Ratio
C) Metric
D) Nonmetric
E) All of the above

Question 23

Which of the following statements is NOT true concerning conjoint analysis?

A) The underlying assumption is that any set of stimuli, such as products, brands, or stores, is evaluated as a bundle of attributes
B) It relies on respondent's subjective evaluations
C) It seeks to develop the part-worth or utility scores describing the importance of each aspect of a product or service in the subject's overall preference ratings
D) The stimuli in conjoint analysis are products or brands
E) Utility scores are computed from the subjects' rankings of a set of cards

Question 24

_____ are simple correlations between the variables and the factors.

A) Eigenvalues
B) Factor loadings
C) Principal components
D) Communalities
E) Betas

Question 25

The linear combinations of independent variables developed by discriminant analysis that will best discriminate between the categories of the dependent variable are _____.

A) discriminant functions
B) discriminant scores
C) characteristic profiles
D) correlation coefficients
E) beta weights

Question 26

The _____ represents the proportion of total variance in all the variables that is accounted for by a factor.

A) eigenvalue
B) percentage of variance
C) residual
D) marginal
E) principal component

Question 27

It is recommended that the factors extracted should account for at least _____% of the total variance of the original set of variables.

A) 50
B) 60
C) 70
D) 80
E) 90

Question 28

Which technique is useful for discovering patterns among the variables in order to determine if an underlying combination of the original variables can summarize the original set?

A) Multidimensional scaling
B) Factor analysis
C) Conjoint analysis
D) Discriminant analysis
E) MANOVA

Question 29

Which of the following questions is best addressed using MANOVA?

A) A real estate development company wants to estimate the probable sales of construction services on the basis of marriage rates, population movement in the region, and interest rates on construction loans
B) A psychologist wants to understand the underlying personality factors associated with materialism in consumers
C) An airline wants to classify its customers into groups based on their relative profitability
D) The brand manager for Tide laundry detergent wants to understand how consumers perceive Tide relative to other laundry detergents
E) A retail store wants to determine if there are differences in perceptions of service quality associated with gender and income level categories

Question 30

The mean scores in a MANOVA are called _____.

A) mu
B) centroids
C) ku
D) lambda
E) beta

Question 31

Which of the following statements is not an objective of discriminant analysis?

A) Examination of whether significant differences exist among the groups, in terms of the criterion variables
B) Determination of which predictor variables contribute to most of the intergroup differences
C) Classification of cases to one of the groups based on the values of the predictor variables
D) Evaluation of the accuracy of classification
E) All of the above are objectives of discriminant analysis

Question 32

The most widely used structural equation modeling software program is _____.

A) LISREL
B) EQS
C) Bartlett's VISIO
D) AMOS
E) JUMP

Question 33

The amount of variance a variable shares with all other variables included in the factor analysis is referred to as _____.

A) communality
B) total variance
C) shared variance
D) percentage of variance
E) eigenvalue

Question 34

A score in conjoint analysis used to represent each aspect of a product or service in a participant's overall preference ratings is called a _____ score.

A) Z
B) error
C) factor
D) utility
E) mean

Question 35

Which statistical technique uses analysis of covariance structures to explain causality among constructs?

A) Regression analysis
B) Factor analysis
C) Discriminant analysis
D) MANOVA
E) Structural equation modeling

Question 36

_____ is a technique that attempts to determine the relative importance consumers attach to salient attributes and the utilities they attach to the levels of attributes.

A) Discriminant analysis
B) Regression
C) MANOVA
D) Conjoint analysis
E) Factor analysis

Question 37

Which statistical technique examines differences between groups by simultaneously testing all dependent variables and their interrelationships?

A) Cross-tabulation
B) MANOVA
C) ANOVA
D) Multiple regression
E) Factor analysis

Question 38

For which of the following reasons can factor analysis be used?

A) To identify underlying dimensions among a set of variables
B) To identify a smaller set of variables to replace an original set for use in subsequent multivariate analysis
C) To identify product preferences for a specific target market
D) To group people into one or more categories of a nominal, dependent variable
E) Both a and b

Question 39

Structural equation modeling (SEM)relies upon _____ to present predictive and associative relationships among constructs and indicators in a model.

A) scatterplots
B) path diagrams
C) boxplots
D) pie charts
E) Pareto diagrams

Question 40

Jack is performing a factor analysis on twenty items relevant to perceptions of service quality.Using a principal components approach,the following eigenvalues were produced: 3.45,2.78,1.33,1.24,1.01,.567,.443,and .223.How many factors should Jack retain based on these eigenvalues?

A) 1
B) 2
C) 3
D) 5
E) 8

Question 41

Which approach to cluster analysis involves evaluating the distance between two clusters by first finding the geometric center of each cluster and then computing distances between the two centers?

A) Euclidean distance
B) Average linkage method
C) Maximum likelihood method
D) Principal components analysis
E) Varimax approach

Question 42

Using multidimensional scaling (MDS),objects may be positioned in terms of _____.

A) objective space
B) ideal preferences
C) subjective space
D) all of the above
E) none of the above

Question 43

When multiple regression is used to describe an entire structure of linkages between variables that have been advanced from a causal theory,it is referred to as _____.

A) factor analysis
B) path analysis
C) forward selection
D) conjoint analysis
E) None of the above

Question 44

Principal component analysis describes _____.

A) a method for identifying the variables in multidimensional scaling
B) a method for identifying the variables in path analysis
C) a method for reducing the number of variables in a factor analysis
D) a method for reducing the number of variables in conjoint analysis
E) None of the above

Question 45

Specification error occurs _____.

A) when a researcher fails to use all ratio variables in multiple regression.
B) when a researcher fails to use appropriate variables in path analysis
C) when a researcher fails to consider all important predictor variables in structural equation modeling.
D) when a researcher fails to consider all important predictor variables in conjoint analysis
E) None of the above

Question 46

A _____ is a graphical device for displaying clusters and their relative distances.

A) dendrogram
B) scatterplot
C) Pareto diagram
D) boxplot
E) line graph

Question 47

List and explain the five steps researchers take when using structural equation modeling.

Question 48

Explain the difference between forward selection,backward elimination,and stepwise selection for the imputation of variables in a regression equation.

Question 49

Nonmetric measures refer to data that are _____.

A) Nominal
B) Interval
C) Ordinal
D) Ratio
E) A & C above

Question 50

Which of the following statements is FALSE?

A) In cluster analysis, objects in each cluster tend to be similar to each other and dissimilar to objects in the other clusters
B) Cluster analysis is also called classification analysis or numerical taxonomy
C) Groups or clusters are suggested by the data, not defined a priori
D) Cluster analysis is appropriate when the criterion or dependent variable is categorical and the independent variables are interval
E) All of the above are true

Question 51

Which of the researcher withholds one-fourth to one-third of the data to evaluate how well the regression equation will predict beyond the sample used to calculate the regression equation,it is using _____.

A) cluster analysis
B) a holdout sample
C) factor loadings
D) collinearity
E) None of the above

Question 52

Which of the following multivariate techniques is NOT appropriate if the research question demonstrates an assumption of interdependence?

A) Cluster Analysis
B) Multiple Analysis of variance (MANOVA)
C) Multidimensional Scaling (MDS)
D) Factor Analysis
E) All of the above are appropriate techniques

Question 53

The creation of _____ lie at the heart of multidimensional scaling.

A) perceptual maps
B) pair-wise tables
C) part-worth functions
D) eigenvalues
E) covariance matrices

Question 54

Metric measures refer to data that are _____.

A) Nominal
B) Interval
C) Ordinal
D) Ratio
E) B & D above

Question 55

Which method of rotation should be used when the factors are correlated?

A) Orthogonal rotation
B) Oblique
C) Varimax
D) Syntimax
E) Exploratory

Question 56

In multidimensional scaling,the _____ is a lack of fit measure; higher values indicate poorer fits.

A) beta weight
B) stress index
C) R²
D) X²
E) factor loading

Question 57

Which of the following statements is not true about factor rotation?

A) Through rotation, the factor matrix is transformed into a simpler one that is easier to interpret
B) Rotation affects the communalities and the percentage of total variance explained
C) Preferably, variables should load on only one factor
D) Different rotation methods may identify different factors
E) One rotation method is varimax

Question 58

Which statistical technique identifies homogeneous subgroups of study objects or participants and then studies the data by those subgroups?

A) Multiple regression
B) Cluster analysis
C) Discriminant analysis
D) Factor analysis
E) Multidimensional scaling

Question 59

How does a research analyst determine on which factor a variable is loading?

A) By the p value
B) By assessing the eigenvalues
C) By identifying the highest factor loading
D) By rotating the correlation matrix
E) all of the above

Question 60

Which of the following multivariate techniques is NOT appropriate if the research question demonstrates an assumption of dependence?

A) Multiple Regression
B) Multiple Analysis of variance (MANOVA)
C) Discriminant Analysis
D) Factor Analysis
E) All of the above are appropriate techniques

Question 61

Explain when and how a researcher would go about conducting a factor analysis.

Question 62

List the five steps that are basic to most cluster studies.