Conditional relative frequencies help you focus on one group at a time in a two-way table, so you can describe proportions within that group rather than within the full data set.

What Conditional Relative Frequencies Measure

In a contingency table, each cell records the count for one category of one variable together with one category of a second variable.

This reference diagram depicts the structure of an $r\times c$ contingency table, emphasizing how counts are organized into cells formed by row–column intersections. It supports the idea that conditional relative frequencies come from choosing a condition (a row or column) and comparing a cell count to that row/column total. Source

A conditional relative frequency focuses on one part of that table after fixing a condition. Instead of comparing a cell to the total number of observations, you compare it to the total for the group named in the condition.

This idea is built around the word given. If a question asks for the proportion of individuals in one category given that they belong to another category, the second category becomes the condition. That group provides the denominator.

The role of the condition

The condition tells you which group becomes the reference group. Common wording includes:

• given that

• among

• out of those who

• for the group

• within the category

Each of these phrases signals that you are restricting attention to one row or one column.

Once that restriction is made, the conditional relative frequency describes a part of that restricted group, not a part of the entire table.

How to Calculate a Conditional Relative Frequency

To calculate a conditional relative frequency, first identify the cell of interest. Then identify the total for the row or column named in the condition. Only after the denominator is fixed should you divide.

A conditional relative frequency can be written as a decimal, fraction, or percent. In AP Statistics, the most important feature is not the form of the answer but whether the denominator matches the condition given in the problem.

A reliable process

• Read the question carefully and identify the conditioned group.

• Locate the relevant cell count.

• Locate the total for the row or column named in the condition.

• Divide the cell count by that row or column total.

• State the answer in context, naming both the subgroup and the conditioned group.

If the condition is based on a row, the conditional relative frequencies across that row should add to 1, aside from small rounding differences. If the condition is based on a column, the conditional relative frequencies down that column should add to 1.

Interpreting the Result in Context

A conditional relative frequency describes a within-group proportion. It answers a question about one category inside another category. It does not describe the proportion in the entire data set, and it does not automatically describe the reverse condition.

For instance, a statement such as “the conditional relative frequency of commuters who bike, given that they live within two miles of campus” means that you begin with the group who live within two miles, then find what proportion of that group bikes.

Writing interpretations clearly

A strong interpretation usually does four things:

• names the conditioned group first,

• names the category of interest second,

• reports the proportion or percent,

• keeps the statement tied to the context of the data.

Useful sentence starters include:

• “Among students who …”

• “Of the adults in the … group, …”

• “Within the category …, the proportion that … is …”

This order matters because the denominator is part of the meaning. If you do not identify the conditioned group clearly, the number can be misunderstood.

Row Conditions and Column Conditions

Conditional relative frequencies can be computed by rows or by columns. Neither direction is automatically correct. The correct direction depends entirely on the wording of the question.

If the condition names a row category, divide by the row total. If the condition names a column category, divide by the column total. A common AP Statistics mistake is to choose a denominator based on where the numbers are easiest to see rather than on what the question actually asks.

Another common error is to reverse the condition.

These worked examples illustrate conditional relative frequencies computed by conditioning on a row versus conditioning on a column. The same two-way table is used to answer different “given that …” questions, emphasizing that the denominator must match the conditioned group (row total or column total). Source

The proportion of athletes who are juniors is not the same as the proportion of juniors who are athletes. The same cell count may appear in both calculations, but the denominator changes, so the conditional relative frequency usually changes as well.

Common Mistakes to Avoid

• Using the grand total: that produces an overall relative frequency, not a conditional relative frequency.

• Ignoring the wording: phrases like among or given that determine the denominator.

• Switching rows and columns: the denominator must match the conditioned category.

• Reporting only a number: the answer should identify the group being described.

• Confusing a count with a proportion: the cell entry is often a count, but the conditional relative frequency is found only after division.

• Rounding too early: keep enough decimal places until the final reported answer.

A quick self-check is to ask, “What group am I dividing by?” If that group matches the condition in the question, the setup is likely correct.