A two-way table (or contingency table) displays the frequencies of two categorical variables at once, with one variable's categories as rows and the other's as columns, so you can compute marginal and conditional relative frequencies and check for association between the variables.
A two-way table is how AP Stats organizes data on two categorical variables at the same time. One variable's categories become the rows, the other's become the columns, and each cell holds the count of individuals that fall into both categories (like "juniors who are science majors"). Add up a row or column and you get a total for just one variable; the grand total in the corner is your whole sample.
The table itself is simple. The power comes from what you compute from it. Divide row and column totals by the grand total and you get marginal relative frequencies (the distribution of each variable alone). Divide a cell by its row or column total and you get a conditional relative frequency (the distribution of one variable given a category of the other). Comparing conditional distributions is the AP-approved way to decide whether two categorical variables are associated. Later, in Unit 8, the same table becomes the input for a chi-square test, where you compare observed cell counts to expected counts.
Two-way tables show up in three different units, which makes them one of the most recyclable tools in the course. In Unit 1 (LO 1.4.C), frequency tables let you compare two or more groups on the same categorical variable. In Unit 2 (LOs 2.3.A and 2.3.B), the two-way table is where you calculate marginal and conditional relative frequencies and use them to argue whether two variables are associated. Then in Unit 8 (LO 8.4.A), it comes back for inference, where you calculate expected counts with the formula (row total)(column total)/table total and feed them into a chi-square test for independence or homogeneity. If you can read a two-way table fluently, you've got a head start on three units' worth of exam content.
Keep studying AP Statistics Unit 2
Conditional Distribution (Unit 2)
A conditional distribution is what you get when you slice a two-way table one row (or one column) at a time and convert counts to proportions. If the conditional distributions look different across groups, the variables are associated. This is the single most common thing you'll do with a two-way table before Unit 8.
Marginal Distribution (Unit 2)
The marginal distribution lives in the margins of the table, literally. Row and column totals divided by the grand total give you the distribution of each variable by itself, ignoring the other one entirely.
Chi-Square Statistic (Unit 8)
The two-way table is the raw material for chi-square tests. You compute an expected count for every cell using (row total)(column total)/table total, then the chi-square statistic measures how far the observed counts stray from those expected counts. Big gap means evidence of association.
Bar Graph (Unit 1)
A segmented or side-by-side bar graph is basically a two-way table drawn as a picture. Each bar shows one conditional distribution, so bars that look different across groups are the visual version of 'these variables are associated.'
Two-way tables get tested in two flavors. In Units 1-2 style questions, you're handed a table and asked to compute or compare proportions. Watch the wording carefully, because "proportion of all students" means divide by the grand total, while "proportion of juniors who..." means divide by the junior total. In Unit 8, multiple-choice questions love the expected count formula. A typical stem gives you a row total, a column total, and the sample size, then asks for the expected count of one cell, exactly like (160)(200)/800. On the free-response side, the 2026 FRQ Q5 gave a two-way table of professional athletes by age-group and sport and asked about association, which is the classic chi-square test for independence setup. Expect to state hypotheses about association, verify that all expected counts are at least 5, and interpret the conclusion in context.
A frequency table summarizes ONE categorical variable, so it's just a list of categories and counts. A two-way table crosses TWO categorical variables, so every cell represents a combination of categories. The quick check is to count the variables, not the rows. A table with five rows of class years is still one-way; add a second variable like major across the columns and now it's two-way, and concepts like conditional distributions and chi-square tests apply.
A two-way table displays counts for two categorical variables, with each cell showing how many individuals fall into a specific combination of categories.
Marginal relative frequencies come from dividing row or column totals by the grand total, and they describe one variable while ignoring the other.
Conditional relative frequencies come from dividing a cell count by its row or column total, and comparing them across groups is how you check for association.
The expected count for any cell in a chi-square test is (row total)(column total)/table total, and you should be able to compute it from totals alone.
If the conditional distributions of one variable are roughly the same across every category of the other variable, the two variables show no association.
The same two-way table skill set carries you from describing data in Units 1-2 all the way to chi-square inference in Unit 8.
It's a table that organizes counts for two categorical variables at once, with one variable's categories as rows and the other's as columns. It's the foundation for marginal distributions, conditional distributions, and chi-square tests.
Multiply the cell's row total by its column total, then divide by the table's grand total. So in a table of 800 people where a row total is 160 and a column total is 200, that cell's expected count is (160)(200)/800 = 40.
No. A frequency table summarizes one categorical variable, while a two-way table crosses two. You only get marginal distributions, conditional distributions, and chi-square tests when two variables are involved.
The raw counts alone don't, but the conditional relative frequencies you compute from it do. If the conditional distributions differ noticeably across groups, that's evidence of association; in Unit 8, a chi-square test makes that judgment formally.
Not directly. Two-way tables are for categorical variables only; quantitative data calls for scatterplots and regression instead. The exception is when a quantitative variable gets binned into categories, like age-groups, which the 2026 FRQ did with professional athletes' ages.