AP Statistics Unit 2 Sentence Frames/Memorization Tips

Interpreting Slope

For every 1 unit increase in the [explanatory variable], the linear regression model predicts an average increase/decrease of slope in the explanatory variable.

Interpreting y-intercept

When the [explanatory variable] is 0 [units], the linear regression model predicts that the [response variable] would be [y-intercept] [r.v. units]

Interpreting residuals

The actual [response variable] is greater/less than the value predicted by [y-(y-hat)] units

Use CDOFS when describing scatter plots:

Context

Direction

Outliers

Form (linear/nonlinear)

Strength (strong/moderate/weak)

Interpreting S (Standard Deviation of Residuals)

The actual [response variable] typically varies by [S] (units) when using [explanatory variable] to predict [response variable]

Interpreting r² + how does variability change r²

[r²]% of the variation in the predicted [response variable] is accounted for by the possible linear relationship with [explanatory variable]. + when there is more variability UNaccounted for by the linear relationship with the explanatory variable, r² will decrease.

How does extrapolation effect reliability?

more extrapolation leads to less reliability in predictions

What does the least squared regression line do?

The least squared regression line makes the sum of the squared residuals the least, or as small as possible

fancy names for r² & r

r²= coefficient of determination, r= correlation coefficient

Conditional Relative Frequency

Conditional Relative Frequency gives the percent or proportion of individuals that have a specific value for one categorical variable among individuals