Question 1

Phi is based on an inferential statistic; that statistics is

Accepted Answer

A) Analysis of Variance 
B) t-test 
C) Chi-square 
D) Fisher's Exact Test 
A) Analysis of Variance 
B) t-test 
C) Chi-square 
D) Fisher's Exact Test C

Question 2

A Phi coefficient of .6 means that the percent of explained variance is 36%.

Accepted Answer

A) True 
 B)False  True

Question 3

Phi is designed to be used with square tables.

Accepted Answer

A) True 
 B)False  False

Question 4

Phi is sensitive to unequal marginal distributions.

Accepted Answer

A) True 
 B)False

Question 5

Under which of these circumstances would you prefer NOT to use Phi?

Accepted Answer

A) the number of cases is large 
B) the relationship is small 
C) the coefficient produces a value less than .50 
D) the table marginals are very different 
A) the number of cases is large 
B) the relationship is small 
C) the coefficient produces a value less than .50 
D) the table marginals are very different

Question 6

Assumptions made by the Phi statistic include

Accepted Answer

A) normal distributions 
B) equal variances 
C) variables are natural dichotomies 
D) all of the above 
A) normal distributions 
B) equal variances 
C) variables are natural dichotomies 
D) all of the above

Question 7

If you explained 25% of the variance in the dependent variable using the Phi statistic,what would the Phi coefficient be?

Accepted Answer

A) .25 
B) .40 
C) .50 
D) none of the above 
A) .25 
B) .40 
C) .50 
D) none of the above

Question 8

You can't tell the direction of a relationship by looking only at its Phi coefficient.

Accepted Answer

A) True 
 B)False

Question 9

Phi is a correlation statistic for which level of measurement below?

Accepted Answer

A) nominal 
B) ordinal 
C) interval 
D) nominal and ordinal 
A) nominal 
B) ordinal 
C) interval 
D) nominal and ordinal

Question 10

Which of the variables below would be interpreted as a natural dichotomy?

Accepted Answer

A) age measured by "young" and "old" 
B) gender measured by "male" and "female" 
C) income measured by "low" and "high" 
D) type of crime measured by "nonserious" and "serious" 
A) age measured by "young" and "old" 
B) gender measured by "male" and "female" 
C) income measured by "low" and "high" 
D) type of crime measured by "nonserious" and "serious"

Question 11

Any variable that can be split into two equal parts is,by definition,a natural dichotomy.

Accepted Answer

A) True 
 B)False

Question 12

The nominal-level concept of association is that

Accepted Answer

A) as the number of cases in the table cells of one of the values increases,the corresponding number should decrease in cells of the other values 
B) as the number of cells in the row of the independent variable increases,the corresponding number of cells should decrease in cells of the other rows 
A) as the number of cases in the table cells of one of the values increases,the corresponding number should decrease in cells of the other values 
B) as the number of cells in the row of the independent variable increases,the corresponding number of cells should decrease in cells of the other rows

Question 13

Smaller tables,on the whole,are easier to interpret at the nominal level than larger tables.

Accepted Answer

A) True 
 B)False

Question 14

If a two-variable table creates problems for Chi-square,there will also be problems with Phi.

Accepted Answer

A) True 
 B)False

Question 15

A Phi value of .40 would be interpreted as having explained

Accepted Answer

A) 4% of the variance in the dependent variable 
B) 40% of the variance in the dependent variable 
C) 1.6% of the variance in the dependent variable 
D) 16% of the variance in the dependent variable 
A) 4% of the variance in the dependent variable 
B) 40% of the variance in the dependent variable 
C) 1.6% of the variance in the dependent variable 
D) 16% of the variance in the dependent variable

Question 16

The Uncertainty Coefficient is possible statistic to use with nominal level variables when there are serious table problems.

Accepted Answer

A) True 
 B)False

Question 17

There are alternatives to the use of Phi; two of them are:

Accepted Answer

A) Gamma and Lambda 
B) Uncertainty Coefficient and Spearman's Rho 
C) Chronbach's Alpha and McNemar's Q 
D) none of the above 
A) Gamma and Lambda 
B) Uncertainty Coefficient and Spearman's Rho 
C) Chronbach's Alpha and McNemar's Q 
D) none of the above

Question 18

One of the reasons that Phi is a popular statistic is that it has both symmetric and asymmetric versions.

Accepted Answer

A) True 
 B)False

Question 19

Correlation coefficients for Phi range between zero and 1.0.

Accepted Answer

A) True 
 B)False

Exam 15: Testing for Association: Phi

Phi is based on an inferential statistic; that statistics is

A Phi coefficient of .6 means that the percent of explained variance is 36%.

Phi is designed to be used with square tables.

Phi is sensitive to unequal marginal distributions.

Under which of these circumstances would you prefer NOT to use Phi?

Assumptions made by the Phi statistic include

If you explained 25% of the variance in the dependent variable using the Phi statistic,what would the Phi coefficient be?

You can't tell the direction of a relationship by looking only at its Phi coefficient.

Phi is a correlation statistic for which level of measurement below?

Which of the variables below would be interpreted as a natural dichotomy?

Any variable that can be split into two equal parts is,by definition,a natural dichotomy.

The nominal-level concept of association is that

Smaller tables,on the whole,are easier to interpret at the nominal level than larger tables.

If a two-variable table creates problems for Chi-square,there will also be problems with Phi.

A Phi value of .40 would be interpreted as having explained

The Uncertainty Coefficient is possible statistic to use with nominal level variables when there are serious table problems.

There are alternatives to the use of Phi; two of them are:

One of the reasons that Phi is a popular statistic is that it has both symmetric and asymmetric versions.

Correlation coefficients for Phi range between zero and 1.0.

Introduction to Statistics

Levels of Measurement

Graphical Statistics

Measures of Central Tendency

Measures of Dispersion

Curves and Distributions

Frequency Distributions

Elementary Relationships: Crosstabulation Tables

Hypotheses and Sampling Distributions

Statistical Significance

Testing for Significance: the Chi-Square Test

Testing for Significance in Two Groups: the T-Test

Testing for Significance in Multiple Groups: the Analysis of Variance Statistic

The Concept of Association

Testing for Association: Pearsons R and Regression

Doing Real Research: Elementary Multivariate Relationships

Box Plots

Skewness and Kurtosis

Ordinal-Level Tests of Significance

Multiple Comparison Tests

Nominal Level Tests of Association

Ordinal Level Tests of Association

Addendum Probability

Filters