Deck 18: Measures of Association

Question 1

Bill wants to write the equation that demonstrates the model for explaining mid-life crisis.He is using optimism,locus of control,income,and years since completing college as explanatory variables.Which of the following equations is most appropriate?

A)
B)
C)
D)
E) none of the above

Answer 1

C

Question 2

Which of the following questions would be best answered using simple regression?

A) Are consumers' perceptions of quality related to their perceptions of prices when the effect of brand image is controlled?
B) Can the variation in market share be accounted for by the size of the sales force?
C) Do retailers, wholesalers, and agents differ in their attitudes toward the firm's distribution policies?
D) How do advertising levels (high, medium, and low) interact with price levels (high, medium, and low) to influence brand sales?
E) What factors can be thought of as being related to service quality as opposed to product satisfaction?

Answer 2

B

Question 3

The _____ is the change in Y for a 1-unit change in X.

A) regression coefficient
B) slope
C) intercept
D) constant
E) error term

Answer 3

B

Question 4

The _____ measures the association between two variables after controlling or adjusting for the effects of one or more additional variables.

A) regression analysis
B) partial correlation
C) ANOVA
D) product moment correlation
E) gamma

Question 5

The assumption that data can be described by a straight line passing through the data array is called _____.

A) resistance
B) normality
C) significance
D) linearity
E) association

Question 6

Which of the following is possible when r = 0?

A) No pattern is evident that can be described with a single line
B) Variables are related but the relationship is nonlinear
C) The pattern is linear such that a straight line passes through the data array
D) The pattern is three-dimensional
E) Both a and b

Question 7

Which of the following is a measure of non-metric correlation?

A) Pearson product moment correlation
B) Bivariate linear regression
C) Kendall's tau
D) Partial correlation
E) All of the above

Question 8

The question of 'How strongly are sales related to price when the effect of brand loyalty is controlled?' is best answered using _____.

A) regression analysis
B) partial correlation
C) ANOVA
D) product moment correlation
E) gamma

Question 9

Which of the following hypotheses is best examined with a correlation analysis?

A) Men differ from women on average yearly clothing expenditures
B) Income level is related to average yearly clothing expenditures
C) Clothing expenditures are higher in northern states and lower in southern and southwestern states
D) Income, geographic location, and gender are predictive of yearly clothing expenditures
E) More retail clothing stores are located in the northeast than in the southwest

Question 10

The _____ is a statistic summarizing the strength of association between two metric variables.

A) regression analysis
B) partial correlation coefficient
C) ANOVA
D) product moment coefficient
E) gamma

Question 11

What does the sign of the correlation coefficient signify?

A) The magnitude of the relationship
B) The significance of the relationship
C) The importance of the relationship
D) The direction of the relationship
E) The p value associated with the relationship

Question 12

It is possible for a correlation coefficient of .12 to be statistically significant when _____.

A) the variables have a positive covariance
B) the variables have a negative covariance
C) the sample is large
D) the sample is small
E) it is meaningful

Question 13

What does r² measure

A) The proportion of variation in one variable that is explained by the other
B) The proportion of error variation
C) The proportion of variation in Y related to the variation of the categories of X
D) The proportion of variation in Y due to the variation within each of the categories of X
E) The significance of the relationship between X and Y

Question 14

Which of the following is true of the association between brand loyalty and attitude toward the brand if the product moment correlation coefficient between brand loyalty and attitude toward the brand is .65 with a p value of .01?

A) As brand loyalty increases, attitude toward the brand increases
B) There is a moderately strong relationship between the two variables
C) The relationship can be attributed to more than simply random fluctuations
D) There is a linear relationship between the two variables
E) All of the above

Question 15

What is the meaning of a significant correlation coefficient?

A) It reflects the probability of the relationship occurring in the population
B) It reflects the magnitude of the relationship
C) It reflects the direction of the relationship
D) It reflects the importance of the finding
E) It refers to the meaningfulness of the result

Question 16

Which of the following is true of the intercept,β₀?

A) It is the value of the dependent variable
B) It is the change in Y for a 1-unit change in X
C) It is the estimate of X when Y = 0
D) It is the estimate of Y when X = 0
E) It is also called the rise over run

Question 17

Which statement is NOT true about the constant b in the bivariate regression equation = a + bX_i?

A) It is usually referred to as the non-standardized regression coefficient
B) It indicates the expected change in Y when X is changed by one unit
C) It is the intercept of the regression line
D) It indicates the value of X when Y is zero
E) It may be computed as b = COV_xy/S_x²

Question 18

The issue of _____ is reflected in the correlation between the number of sunny days in the year and the gains in the New York Stock Exchange.

A) statistical significance
B) practical significance
C) covariance
D) error
E) artifact correlations

Question 19

In a regression analysis,the actual values of Y may be found above or below the regression line.These deviations are called the _____.

A) standard deviation
B) error term
C) variance
D) standard error of the mean
E) slope

Question 20

Regression analysis seeks to _____.

A) predict Y using X values
B) evaluate differences between X and Y
C) determine whether X and Y are part of the same construct
D) determine whether the means of X and Y are significantly different
E) all of the above

Question 21

When a researcher needs a correction to chi-square appropriate for large tables,_____ is an appropriate measure.

A) Cramer's V
B) r²
C)
D)
E)

Question 22

Which of the following measures is used to assess the strength of relationships in cross-classification tables?

A) Nonparametric measures of association
B) Parametric measures of association
C) ANOVA
D) Regression
E) R-test

Question 23

Which procedure for finding a regression line keeps errors of estimate to a minimum?

A) Method of least squares
B) Elaboration likelihood method
C) General linear model
D) Goodness of fit
E) Standardized residual effect

Question 24

Which term below refers to the difference between the regression line value of Y and the real Y value?

A) Least squares
B) Variance
C) Residual
D) Error
E) Slope

Question 25

What size of cross-tabulation table is best for applying phi?

A) 2 x 2
B) 2 x 3
C) 3 x 3
D) 3 x 4
E) Any size

Question 26

The primary advantage of the contingency coefficient C is _____.

A) it can only be used on 2 x 2 tables
B) that it can accommodate skewed data
C) it is comparable to phi
D) it replaced chi-square
E) it is asymmetrical

Question 27

Which measure of association for nominal variables attempts to correct X² proportionately to N?

A) Phi
B) Cramer's V
C) Contingency coefficient C
D) F ratio
E) Scheffe's S

Question 28

Which of the following measures is used to detect the strength of a relationship between nominal variables?

A) Z score
B) t-test
C) X²
D) r²
E) β

Question 29

Which statistic below is a measure of association that uses table marginals to reduce prediction errors?

A) τ
B) r²
C)
D)
E)

Question 30

When a subject that ranks higher on one variable also ranks higher on the other variable,the pairs of observations are said to be _____.

A) correlated
B) causal
C) concordant
D) discordant
E) ordinal

Question 31

What measure supports how well the regression equation is able to predict Y?

A) F test
B) Goodness of fit
C) R²
D) Alpha
E) P value

Question 32

Proportional reduction in error statistics are used with _____.

A) interval data
B) ratio data
C) regression analysis
D) contingency tables
E) all of the above

Question 33

In bivariate regression,which statement is true concerning the coefficient of determination,r²?

A) r² is the square of the simple correlation coefficient obtained by correlating the two variables
B) r² varies between 0 and 1
C) r² signifies the proportion of the total variation in Y accounted for by the variation in X
D) all of the above
E) none of the above

Question 34

Which statistic below is a measure of how well the frequencies of one nominal variable predict the frequencies of another variable?

A) Cramer's V
B) r²
C)
D)
E)

Question 35

When concordant pairs exceed discordant pairs in a P-Q relationship,Kendall's tau b reports a(n)_____ association between the variables under study.

A) inverse
B) positive
C) negative
D) weak
E) strong

Question 36

To estimate the accuracy of predicted values,Y,found in bivariate regression,it is useful to calculate the _____,the standard deviation of the actual Y values for the predicted Y values.

A) coefficient of determination
B) standard error of the estimate
C) covariance
D) standard error
E) sum of squares

Question 37

Which of the following measures is not used as a measure of association for nominal,nonparametric variables?

A) Chi-square
B) Phi
C) Cramer's V
D) Contingency coefficient C
E) Z score

Question 38

Which of the following statistics is not based on the concept of concordant and discordant pairs?

A) Kendall's tau b
B) Somers's d
C) Kendall's tau c
D) Gamma
E) Spearman's rho

Question 39

Statistics used to assess the strength of relationships for nominal data may be sensitive to all of the following except _____.

A) table shape
B) number of cells in the table
C) type of sample
D) sample size
E) marginals

Question 40

Which of the following is true of relationships among nominal measures?

A) When there is no relationship at all, the coefficient should be 1
B) When there is no relationship at all, the coefficient should be 0
C) When there is complete dependency, the coefficient should be negative
D) When there is complete dependency, the coefficient should be positive
E) None of the above

Question 41

What are the assumptions made by the regression model in estimating the parameters and in significance testing?

Question 42

Briefly explain how a researcher can benefit from using scatterplots.

Question 43

When the number of discordant pairs and concordant pairs in a P-Q relationship is equal,the interpretation is that the variables _____.

A) are perfectly correlated
B) have a weak but significant relationship
C) are normally distributed
D) have no relationship
E) have a negative association

Question 44

Which of the following symbols is used to reflect Goodman and Kruskal's gamma?

A)
B)
C)
D)
E)

Question 45

What type of measure is Spearman's rho?

A) Chi-square statistic
B) Correlation coefficient
C) Measure of variance
D) Measure of error
E) Measure of skewness

Question 46

Which ordinal measure is a refinement of gamma for ordinal data that considers "tied" pairs?

A)
B)
C)
D)
E)

Question 47

When we take the observed values of X to estimate or predict corresponding Y values,the process is called ____.

A) Chi-square statistic
B) simple prediction
C) multiple regression
D) proportional reduction in error
E) prediction and confidence bands

Question 48

Briefly explain how an analyst should interpret the r² value in a regression analysis.

Question 49

Which of the following ordinal measures is a measure of association that compensates for tied ranks and adjusts for direction of the independent variable?

A) Kendall's tau b
B) Gamma
C) Phi
D) Lambda
E) Somers's d

Question 50

Artifact correlations describe a situation ______.

A) to be welcomed
B) where correlation calculations for two separate subsets of the data show correlation differences that are masked by combining the data
C) where the data are related but represented by a nonlinear function
D) All of the above
E) None of the above

Question 51

Which ordinal measure is a statistic that compares concordant and discordant pairs and then standardizes the outcome by maximizing the value of the denominator?

A)
B)
C)
D)
E)

Question 52

A _____ occurs when subjects have the same value on the X variable,on the Y variable,or on both.

A) correlation
B) resistant statistic
C) tied pair
D) proportional reduction in error
E) positive relationship

Question 53

A visual depiction of the interaction of two variables,showing both direction and shape of the relationship is called _______.

A) a Chi-square statistic
B) a scatterplot
C) a box plot
D) a positive correlation
E) a negative correlation

Question 54

For a given sample size,how many pairs of observations will be present?

A) n(n - 1)/2
B) n/2
C) n - 2/2 + n
D) P - Q/P + Q
E) none of the above

Question 55

Explain how a researcher should interpret a correlation coefficient.

Question 56

When discordant pairs exceed concordant pairs in a P-Q relationship,Kendall's tau reports a(n)_____ association between the variables under study.

A) inverse
B) positive
C) negative
D) weak
E) strong

Question 57

Which of the following symbols is used to reflect the measure,lambda?

A)
B)
C)
D)
E)

Question 58

Zero slopes result when _______.

A) Y is completely unrelated to X, and no systematic pattern is evident
B) there are constant values of Y for every value of X
C) the data are related but represented by a nonlinear function
D) All of the above
E) None of the above