FiltersDone

Question type

Essay

Multiple Choice

Short Answer

True False

Matching

Exam 18: Multivairate Data Analysis: Discriminant Analysis, Factor Analysis, Cluster Analysis, and Multidimensional Scaling

Show Answer

Share

---

All types

Filters

Study Flashcards

Question 21

Multiple Choice

Review LaterAdd Note

Review Later

Once the discriminant function has been produced, the researcher's next step is to:

A) begin interpretation of the function by examining the discriminant coefficients
B) check the statistical significance of the function
C) standardize the discriminant coefficients
D) classify individuals using the discriminant function
E) none of the above

F) B) and C)
G) C) and E)

Correct Answer

verified

Show Answer

Question 22

Multiple Choice

Review LaterAdd Note

Review Later

The following questions focus on Multidimensional Scaling: -Kruskal's stress

A) is an index of variation.
B) is a measure of central tendency.
C) is a lack of fit index.
D) is an index of reproducibility.
E) is an index of dispersion.

F) A) and E)
G) B) and C)

Correct Answer

verified

Show Answer

Question 23

Multiple Choice

Review LaterAdd Note

The following questions focus on Multidimensional Scaling: -Which of the following are not methods for naming underlying dimensions in multidimensional scaling?

-What proportion of the variability in the data is accounted for by the two factor solution?

(Use the information below to answer the next three questions.) In a five variable two group discriminant analysis, the following weights were derived: V₁ = .561, V₂ = .030, V₃ = .049, V₄ = .701, V₅ = -.021. The corresponding pooled standard deviations are S₁ = 4.60, S₂ = 1.23, S₃ = 10.40, S₄ = 13.23, and S₅ = 8.30. For individual 1, the values for the four variables were X₁ = 10, X₂ = 3, X₃ = 25, X₄ = 36, and X₅ = 42. -Individual 1's standardized discriminant score is

To determine the "hit rate" in a matrix of actual vs. predicted classifications, the analyst should focus most of his/her attention on the

Rotation of the original factor analysis solution typically results in

When making a decision as to how many factors to retain in the final factor analysis solution, the researcher should

-For which pair of variables is the estimated original correlation the highest?

Which of the following statements is NOT true regarding cluster analysis?

Which of the following is NOT a key decision that needs to be made when factor analyzing data?

Which of the following is NOT one of the quantities used to assess the relative importance of variables in discriminating between groups in discriminant analysis?

(Use the information below to answer the next three questions.) In a five variable two group discriminant analysis, the following weights were derived: V₁ = .561, V₂ = .030, V₃ = .049, V₄ = .701, V₅ = -.021. The corresponding pooled standard deviations are S₁ = 4.60, S₂ = 1.23, S₃ = 10.40, S₄ = 13.23, and S₅ = 8.30. For individual 1, the values for the four variables were X₁ = 10, X₂ = 3, X₃ = 25, X₄ = 36, and X₅ = 42. -Which variable is least important in discriminating between the two groups?

A factor loading is typically assumed to be significant if its value is in the neighborhood of

The square of a factor loading indicates

To test whether the cluster results offer a reasonable summary of the similarity, correlation, or distance matrix, that is, are the individual clusters sufficiently homogeneous and is the system as a whole consistent with the input similarities, the following procedure(s) can be performed:

The cutting score in a discriminant analysis is the score that

-Use the traditional eigenvalue test to determine the number of factors that should be retained in the factor analysis. How many factors should be retained?

Principal components factor analysis seeks to

Varimax rotation of a factor solution attempts to