Stats shit to remember 😍😭

Stuff that I should remember for FRQ's LMFAOo

Explanatory

use to predict (input) (always x)

Response

outcomes (output) (always y)

What does DUFS stand for

D: Direction

U: Unusual feature (outliers/clusters)

F: Form (linear/not linear)

S: Strength (strong/moderate/weak)

Properties of r

unusual value in pattern = strengthen r

unusual value in pattern = weaken r

r has no units

changing units for x & y doesn’t change r

correlation doesn’t equal causation

How do you find a residual?

Actual - Predicted (A-P)

residual interpretation

The actual (context) was (residual) (above/below) the predicted value for (x = #).

y-intercept interpretation

When (x = 0 context) the predicted (y context) is (y-int)

slope interpretation

With each additional (x context) the predicted (y context) (increases/decreases) by (slope)

standard deviation interpretation

The actual (y context) is typically about (s) away from the number predicted by the LSRL (least-squares regression line)

Coefficient of Determination (r²) interpretation

About (r²%) of the variability in (y context) is accounted for by the LSRL

What should you do when checking for the best models?

1. check scatterplot for linear

2. check residual plot for random scatter

3. check r² closest to 1