1/8
Looks like no tags are added yet.
explanatory variable
Independent variable (X) to see if it explains the other one
dependent variable
Dependent variable (y) to see if it responds to the change in X
If residual is positive…
model underestimated the actual responses (actual > predicted)
If residual is negative…
model overestimated the actual responses (actual < predicted)
LSRL Slope interpretation
For every 1 unit of increase in explanatory variable, our mode predicts an average increase/decrease of slope in response variable (y)
LSRL y-intercept interpretation
When the explanatory variable is zero units, our model predicts that the response variable would be the y-intercept.
Translation with LSRL
r²% of the variation in response variable can be explained by the linear relationship with explanatory variable.
What happens when outlier points are removed?
changes the correlation coefficient (r)
What happens when high-leverage points are removed?
changes the y-intercept and slope