Deck 11 – Simple Linear Regression (LM10

Why is a prediction interval for an individual $Y$ always wider than a confidence interval for mean $Y$?

It includes individual-observation variability in addition to mean uncertainty.

In a lin-log model, $Y=b_0+b_1\ln (X)$, what does $b_1$ measure?

The unit change in $Y$ for a 1% change in $X$.

What does LICN mean for regression assumptions?

Linear, Independent, Constant variance, Normal errors.

How is the OLS slope estimator $hat{b}_1$ computed in simple linear regression?

$hat{b}_1=\mathrm{Cov}(X,Y)/\mathrm{Var}(X)$.