01 / 21

Scatter Plots
on the PSAT

Learn to read, interpret, and model bivariate data using scatter plots, lines of best fit, and correlation.

PSAT Math

What Is a Scatter Plot?

A scatter plot is a graph that displays the relationship between two quantitative variables. Each point represents one observation, with coordinates \((x, y)\) corresponding to the two measured values.

Hours Studied Test Score 1 2 3 4 5 60 70 80 90

Key Vocabulary

Bivariate Data
Data involving two variables measured on the same set of subjects.
Correlation
The strength and direction of the linear relationship between two variables.
Line of Best Fit
A straight line that best represents the data, minimizing the distance between the points and the line.

Types of Correlation

Positive
As \(x\) increases, \(y\) increases. Points trend upward left to right.
Negative
As \(x\) increases, \(y\) decreases. Points trend downward left to right.
No Correlation
No clear pattern. Points are scattered randomly with no trend.
Positive Negative None

The Line of Best Fit

The line of best fit (also called the regression line or least-squares line) is the straight line that minimizes the total squared distances from each point to the line. It has the form:

x y best fit

Interpreting Slope and Intercept

Slope \(b\)
For each 1-unit increase in \(x\), the predicted \(y\) changes by \(b\) units. A positive \(b\) means the relationship is increasing; a negative \(b\) means decreasing.
Intercept \(a\)
The predicted value of \(y\) when \(x = 0\). Sometimes this has real-world meaning (a baseline value), and sometimes it does not.

Correlation vs. Causation

A strong correlation between two variables does not mean one causes the other. Confounding variables, coincidence, or reverse causation could explain the association.

Correlation
Two variables move together in a predictable pattern. Established by observing data.
Causation
One variable directly causes a change in the other. Requires a controlled experiment to establish.

Strong vs. Weak Correlation

Strong Positive Weak Positive

How to Solve Scatter Plot Problems

1
Read the axes. Identify what each axis represents and note the units.
2
Identify the trend. Is the association positive, negative, or none? Is it linear or curved?
3
Use the equation. If given \(\hat{y} = a + bx\), substitute \(x\) to predict \(y\), or solve for \(x\) given \(y\).
4
Interpret slope/intercept. State meaning in context: "For each additional [x-unit], the model predicts [b] more/fewer [y-unit]."
5
Watch for outliers. Points far from the trend may be asked about separately.

Example 1: Reading the Line

A researcher collected data on the number of hours of sunlight and the height (in cm) of a plant after 30 days. The line of best fit is \(\hat{y} = 2.5 + 3.2x\). Predict the height when there are 6 hours of sunlight per day.

Example 2: Identifying Outliers

Temperature (°F) Ice Cream Sales ($) Outlier

Example 3: Residuals

A residual is the difference between the actual value and the predicted value from the line of best fit.

If the line of best fit gives \(\hat{y} = 80\) for a student who actually scored \(y = 85\), the residual is: \(85 - 80 = \) 5.

Positive Residual
Actual value is above the line. The model under-predicted.
Negative Residual
Actual value is below the line. The model over-predicted.

When the Data Is Not Linear

Sometimes the scatter plot shows a curved pattern. A linear model would be a poor fit. The PSAT may ask you to identify whether a linear, quadratic, or exponential model is most appropriate.

x y linear (poor fit) curve (good fit)

Interpolation vs. Extrapolation

Interpolation
Predicting within the range of the data. Generally reliable.
Extrapolation
Predicting outside the range of the data. Often unreliable because the trend may change.

Common Mistakes

✕ Confusing Correlation and Causation
A scatter plot shows association, not cause. Never say one variable "causes" the other based on a scatter plot alone.
✕ Misreading Axes
Swapping which variable is \(x\) and which is \(y\) leads to wrong slope interpretations. Always check labels.
✕ Ignoring Units
Slope has units: "y-units per x-unit." Forgetting this makes your interpretation meaningless.

Summary Table

Concept What to Remember
Scatter Plot Graph of bivariate data Each point is \((x, y)\)
Line of Best Fit \(\hat{y} = a + bx\) Minimizes residuals
Slope \(b\) Rate of change Units: y per x
Intercept \(a\) Predicted \(y\) when \(x=0\) May lack real meaning
Residual \(y - \hat{y}\) + above, − below line
Correlation Strength/direction Does NOT imply causation

Question 1 of 5

A line of best fit for a scatter plot is \(\hat{y} = 12 + 4.5x\). What is the predicted value of \(y\) when \(x = 8\)?

Question 2 of 5

In the equation \(\hat{y} = 150 - 2.3x\), what does the slope mean in context if \(x\) is hours of TV watched per week and \(y\) is test score?

Question 3 of 5

A scatter plot shows a strong positive linear association between exercise hours and resting heart rate decrease. Which statement is best supported?

Question 4 of 5

The line of best fit predicts \(\hat{y} = 72\) for a data point whose actual value is \(y = 65\). What is the residual?

Question 5 of 5

Data for students aged 14 to 18 shows a linear trend between age and shoe size. Using the line of best fit to predict shoe size for a 40-year-old is an example of: