Bivariate Analysis with Contingency Tables Practice Quiz (15 questions)

All questions and answers

1. A researcher records each customer's preferred payment method and membership tier. In a contingency table, what does the cell at the intersection of “card” and “premium” represent?

The number of customers who prefer card, across all membership tiers
The number of customers who prefer card and have premium membership
The percentage of premium members who prefer card
The number of customers who prefer card or have premium membership

The number of customers who prefer card and have premium membership

Explanation

Each cell counts observations with the particular combination of categories represented by its row and column. A row total combines tiers, a percentage is not the cell count, and “or” includes customers who may match only one category.

2. A table follows the convention that Variable 1 is shown in rows and Variable 2 in columns. If Variable 1 is region and Variable 2 is product type, where should product type appear?

In both the rows and columns
In the columns
In the cell counts
In the rows

In the columns

Explanation

Under this convention, Variable 1 occupies rows and Variable 2 occupies columns, so product type belongs in the columns. Putting it in rows reverses the convention; cell counts are observations, not variable placements; and the variables occupy separate dimensions.

3. A contingency table lists how many customers fall into each region-by-payment-method combination. What does the marginal distribution for region show?

The frequency distribution of region-and-payment pairs
The payment-method distribution within each region
The frequency distribution of region considered by itself
The count for each particular region-and-payment combination

The frequency distribution of region considered by itself

Explanation

A marginal distribution gives the frequency distribution of one variable considered by itself, displayed in the corresponding margin. A within-region breakdown is conditional, a cell is one joint count, and the full set of pairs is the joint distribution.

4. In a table crossing employment status with commute mode, an analyst wants to compare commute modes separately within each employment-status category. Which distribution should the analyst examine?

The joint count for each employment-status and commute-mode pair
The marginal distribution of commute mode across all employees
The conditional distribution of commute mode within employment status
The conditional distribution of employment status within commute mode

The conditional distribution of commute mode within employment status

Explanation

A conditional distribution describes one variable within each category of the other; here, commute mode is examined within employment-status categories. The marginal distribution ignores employment status, the reversed conditional answers a different question, and a joint cell is a count rather than a distribution.

5. A class has 80 students, and 24 are female students who smoke. What is the overall relative frequency of this cell as a percentage of the class?

30% of the class
60% of the class
24% of the class
40% of the class

30% of the class

Explanation

An overall relative frequency divides the cell count by the total count: 24/80×100=30%24/80 \times 100 = 30\%. The 24% choice treats the count as a percentage, while 40% and 60% use category-specific denominators rather than the whole class.

6. In a contingency table, a cell contains 18 people; its column total is 60 and its row total is 45. What are the column percentage and row percentage for that cell, respectively?

18% and 18%
30% and 30%
40% and 30%
30% and 40%

30% and 40%

Explanation

Column percentages divide by the column total, so 18/60=30%18/60=30\%; row percentages divide by the row total, so 18/45=40%18/45=40\%. The 40% and 30% pair reverses the denominators, while equal percentages apply one denominator to both.

7. A researcher compares the distribution of transportation choices across neighborhoods. Which pattern indicates that neighborhood and transportation choice are independent?

Every neighborhood has the same number of residents
The transportation distribution differs in one neighborhood
Each transportation choice occurs in only one neighborhood
The transportation distribution is the same in every neighborhood

The transportation distribution is the same in every neighborhood

Explanation

Two categorical variables are independent when the distribution of one is the same across every category of the other. Equal neighborhood sizes concern sample counts, not conditional distributions; exclusive categories or a differing distribution do not establish independence.

8. A student is preparing a 100% segmented bar chart to compare study preferences across class years. How should the chart represent the data?

Give each study preference a 100% bar segmented by class year
Give each class year a bar segmented by its student count
Give each class year a 100% bar segmented by study preference
Make each class-year bar height proportional to its number of students

Give each class year a 100% bar segmented by study preference

Explanation

A 100% segmented bar chart gives each category of the first variable a bar totaling 100%, then segments it according to the second variable. Bars for study preferences would reverse the variables, and heights proportional to counts would not make every bar total 100%.

9. A health survey finds that about 33% of people tattooed at a commercial parlor have Hepatitis C, compared with about 3.5% of people with no tattoo. What does this comparison suggest about tattoo status and Hepatitis C?

Tattooing at a commercial parlor causes Hepatitis C
They are approximately independent because both groups include cases
They are not independent because the conditional rates differ
They are independent because tattoo status cannot determine infection

They are not independent because the conditional rates differ

Explanation

Independence requires the distribution of Hepatitis C status to be similar across tattoo-status categories; the rates of 33% and 3.5% differ substantially. Similarity is not established merely because both groups have cases, and these rates indicate association rather than proving causation.

10. What does the chi-squared statistic assess when applied to a contingency table?

How closely observed counts match a table of perfect association
How strongly category percentages differ without an independence model
How far observed counts differ from counts expected under independence
How far row totals differ from column totals

How far observed counts differ from counts expected under independence

Explanation

The chi-squared statistic compares observed cell counts with the counts expected if the variables were independent. Comparing marginal totals or percentages alone does not define this statistic, and perfect association is not its reference model.

11. A contingency table has a row total of 30, a column total of 20, and a sample size of 100. Under independence, what is the expected count in their intersecting cell?

600
50
20
6

6

Explanation

Under independence, the expected cell count is the row total times the column total divided by the sample size: Eij=30×20100=6E_{ij}=\frac{30\times20}{100}=6. Adding the margins, multiplying without dividing, or substituting the sample size does not apply the expected-count formula.

12. For one cell in a contingency table, the observed count is 8 and the expected count is 10. What contribution does this cell make to the chi-squared statistic?

0.2
4
0.5
0.4

0.4

Explanation

A cell contributes (Oij−Eij)2Eij=(8−10)210=0.4\frac{(O_{ij}-E_{ij})^2}{E_{ij}}=\frac{(8-10)^2}{10}=0.4. Using the unsquared difference gives a different quantity; dividing by the observed count or squaring the expected count also misapplies the formula.

13. A researcher needs a measure of categorical association whose scale runs from 0 for no association to 1 for perfect association. Which measure fits this description?

An expected cell count
Cramér’s V
The chi-squared statistic
A conditional proportion

Cramér’s V

Explanation

Cramér’s V is derived from the chi-squared statistic and measures association on a scale from 0 to 1. The chi-squared statistic is not this bounded coefficient, while an expected count and a conditional proportion serve different roles.

14. A relationship between two variables changes or disappears after observations are divided into groups based on a third variable. What is that third variable called?

An aggregate association
A lurking variable
A response variable
A within-group trend

A lurking variable

Explanation

A lurking variable is the third variable used to divide observations into groups when the relationship between two variables changes or disappears upon combining those groups. A response variable is one of the variables in the relationship, while a within-group trend and an aggregate association describe patterns rather than the grouping variable.

15. A study finds the same directional relationship between two measures in several regions, but the relationship disappears when all regions are combined. What statistical situation does this describe?

A lack of group structure
A consistent pooled association
Simpson’s paradox
A direct causal effect

Simpson’s paradox

Explanation

Simpson’s paradox describes a trend or relationship observed within multiple groups that disappears when the groups are combined according to a third variable. An unchanged pooled trend does not fit, and the pattern alone does not establish either independence or a causal effect.

Study with flashcards

Lock in the answers with 36 flashcards on Bivariate Analysis with Contingency Tables.

What does a contingency table organize?

Counts for two categorical variables.

What does each cell in a contingency table count?

Observations with a particular combination of categories.

What does a marginal distribution show about a variable in a contingency table?

Its frequency distribution considered by itself.

See the flashcards →

Read the study guide

Go over the full study guide for Bivariate Analysis with Contingency Tables.

Read the study guide →

Related classes

Make your own practice quizzes

Upload your class notes and Revizly writes a practice quiz with explained answers in about a minute.

Quiz maker