Master this deck with 18 terms through effective study methods.
Generated from uploaded pdf
Data must meet model assumptions.
Estimates of the errors in predictions.
Residuals are not independent; they are based on predictions.
The average of the residuals is zero.
It depends on the distance of observations from the mean.
Standardized residuals used for diagnostics.
They approximate a standard normal distribution.
The relationship between E(Y;) and x; is linear.
By plotting studentized residuals against x;.
Empirical quantiles of residuals align with normal quantiles.
It improves the fit of the model.
To include multiple explanatory variables in the model.
Minimizing the sum of squared residuals.
It simplifies the representation of multiple variables.
It tests if at least one coefficient is non-zero.
It adjusts for the number of parameters in the model.
By comparing studentized residuals to theoretical quantiles.
It relates to the distance of observations from the mean.