Module 4: Problem-solving and data analysis · Lesson 4.4 · about 18 min
Scatterplots, lines of best fit and two-way tables
Read scatterplots, describe associations, use and interpret a line of best fit, residuals, linear versus exponential patterns, and percentages from two-way tables.
Module 4 · about 18 minutes · read first: 2.5 Linear models, 3.4 Exponential functions. By the end you will read a scatterplot like a story and use its line of best fit to predict.
1. Describing the cloud
- Direction: rising left to right is a positive association; falling is negative.
- Strength: points hugging a line are strong; a loose cloud is weak.
- Form: straight (linear) or curved (often exponential).
2. The line of best fit
Predictions come from putting x into the line’s equation. The slope and intercept have meanings, exactly as in a linear model.
- Slope of the best-fit line
- the predicted change in y for each 1-unit increase in x ("about 4 more points per hour studied")
- Intercept
- the prediction at x = 0, which may be meaningless if x = 0 is far outside the data
- Residual
- actual minus predicted: positive means the point is above the line
- Physical meaning
- A best-fit line describes a trend in the data you have. Predicting far beyond it (extrapolating) is risky: no child keeps growing 6 cm a year forever.
3. Linear or exponential?
Look at the differences between equally spaced values. Constant differences: linear. Constant ratios: exponential.
4. Two-way tables
A two-way table counts people by two categories at once. The key is the denominator: “what percent of grade 9 students” divides by the grade 9 row total; “of the students who walk, what percent” divides by the walkers’ column total.
“A strong association proves that x causes y.” Ice cream sales and sunburns rise together because both follow hot weather. Only an experiment with random assignment shows cause (lesson 4.6).
Practice set
Ten questions on this lesson, from warm-up to hard, in the SAT’s own formats (four options or a typed answer). Press New numbers for a fresh set; every question has a full worked solution.
- Describe a scatterplot by direction, strength and form.
- Use the best-fit line like any linear model: slope = change per unit, intercept = value at 0.
- Residual = actual − predicted.
- In two-way tables, divide by the row or column the question names.
Check yourself
Sources
- College Board, SAT Math content domains: Problem-solving and data analysis (public test specifications) https://satsuite.collegeboard.org/digital
- fibub SAT question bank, two-variable data (original questions) https://fibub.com/learn/courses/sat/two-variable-data/
Your ticks stay in this browser. Save them as a file on the course home.
Updated 2026-11-22. SAT is a trademark of the College Board, which is not involved with and does not endorse fibub. Every question here is original. Test details were checked on the College Board's website on 22 November 2026; check the official source before test day.