Deck 19: Categorical Data

Question 1

Data on the nominal scale is another way of defining categorical data.

Answer 1

True

Question 2

What type of table is used to summarize purely categorical data?

A)Contingency table
B)Incident table
C)Correlation table
D)Occurrence frequency table

Answer 2

A

Question 3

Attempting to calculate the mean of a categorical variable is what?

A)Useful in determining the overall significance of a correlation
B)A way of overcoming possibly inflated error scores
C)Unrelated to how many members a category has
D)Completely meaningless

Answer 3

D

Question 4

Which test is used to identify whether there is a relationship between two categorical variables?

A)Spearman's rho test
B)Bartlett's method
C)Pearson's chi-square test
D)Draize test

Question 5

The chi-square test assumes which of the following?

A)That data are continuous and normally distributed.
B)That there is no significant error score.
C)That data are independent.
D)The expected frequencies should be less than 5.01.

Question 6

Which of the following are ways in which categorical data can be entered in SPSS?

A)Raw scores
B)Weighted cases
C)Both
D)Neither

Question 7

The expected frequency for this calculation is?

A)274.00
B)583.94
C)616.50
D)129.47

Question 8

How many other expected frequencies can be determined from this data set?

A)0
B)2
C)3
D)An infinite number

Question 9

Categorical data can only derive from quantitative data.

Question 10

What is the odds ratio?

A)A measure of sample size for categorical data
B)A measure of effect size for categorical data
C)A measure of standard deviation for categorical data
D)A measure of variance for categorical data

Question 11

Pearson's chi-square test should never be used on categorical data.

Question 12

The expected frequency based on the table in Q5,for an improved homework and a monetary reward is calculated by:

A)[row total (homework improved)× column total (monetary reward)] / total number of participants
B)[total number of participants / row total (homework improved)] × column total (monetary reward)
C)[row total (homework improved)/ column total (monetary reward)] × total number of participants
D)[row total (homework improved)× row total (homework not improved)] / total number of participants

Question 13

What is Fisher's exact test?

A)A test of the significance of human error in categorical data sets
B)A test to overcome the problem of large sample sizes
C)A method of computing the exact probability of the chi-square statistic that is accurate when sample sizes are large
D)A method for computing the exact probability of the chi-square statistic that is accurate when sample sizes are small

Question 14

An alternative to Pearson's chi-square test to test the relationship between two categorical variables is?

A)Odds ratio
B)Likelihood ratio statistic
C)Ames test
D)Tukey's range test

Question 15

Which of the following tests can be used for the analysis of categorical data?

A)Cronbach's alpha
B)Odds ratio
C)Uncertainty coefficient
D)All of the above

Question 16

McNemar's test is appropriate to use on which type of contingency table?

A)1 × 1
B)3 × 1
C)4 × 2
D)2 × 2

Question 17

What are the two categorical variables in the above study?

A)Homework did improve and homework didn't improve
B)Given a monetary reward and given a merit badge
C)Homework improvement and reward given
D)There are more than two categorical variables present

Question 18

Which of the following is a possible problem with the chi-square test?

A)The sampling distribution of the test statistic has a fixed chi-square distribution.
B)The sampling distribution of the test statistic has an approximate chi-square distribution.
C)The test can only be performed on sample sizes of 600 and under.
D)The result is meaningless.

Question 19

Loglinear analysis can be used to test?

A)When there are three or more categorical variables
B)When there are two or more categorical variables
C)When there are more than four independent variables
D)When there is only one dependent variable

Question 20

How many different categories are there in the above table?

A)1
B)2
C)3
D)4

Question 21

McNemar's test can be used to determine whether the row and column marginal frequencies are equal.

Question 22

If this assumption is broken,then the result is what?

A)Negatively skewed data
B)Positively skewed data
C)A reduction in test power
D)Insignificant and pointless

Question 23

In loglinear analysis with more than two categorical variables,it is possible to have up to 20% of cells with expected frequencies of less than 5,but all cells must have expected frequencies greater than 1.Is this assumption true or false?

Question 24

Loglinear analysis is non-hierarchical.