A line of best fit models the overall linear relationship between an explanatory variable and a response variable in a scatterplot, allowing values of the response to be predicted from an equation, graph, or table. Predictions should reflect the slope, intercept, and units of the model, recognizing that interpolation within the observed data range is generally more reliable than extrapolation and that a line summarizes variation rather than passing through every point or establishing causation.
A line of best fit describes the overall pattern in a scatterplot. Its equation can be used to predict a response value from an explanatory value.
Suppose a scatterplot compares:
The data include students who studied between and hours. A line of best fit is
Here, means the predicted test score.
Predict the test score for a student who studies hours.
So, substitute into the equation:
A student who studies for hours is predicted to score 84 points.
The slope, , means that the predicted score increases by about 6 points for each additional hour studied. The intercept, , is the predicted score for hours of studying, although that value may not be meaningful unless hours is represented by the data.
Because hours is within the observed range of to hours, this is an interpolation, which is generally more reliable than predicting outside the data range. The prediction is an estimate based on the overall trend; it does not mean every student who studies for hours will score exactly points. A line of best fit summarizes the variation in the data and does not prove that studying causes higher scores.
Click a topic below to practice the foundational skills you'll need, learn the steps, or master this skill
Earned ?