Prompt for Wednesday, April 12
Motivation: what does it mean when adding or subtracting a few data points changes the result?
The case of Reinhart and Rogoff
.
Tools:
CSS animation
and Efron's
Bootstrap
.
How can we evaluate confidence in a model?
How can we estimate variability without knowing a data-generating distribution?
What makes data sensitive to bootstrap samples?
Resample
Clear
Replications:
Slope (real):
; 90% Conf Int: [
,
]