You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add strong priors so that parameter estimates are (should be) altered considerably.
Validate parameter recovery in one-segment models against rstanarm, and loo and waic too.
Validate parameter recovery in multi-segment models by letting rstanarm or lme4 fit individual segments and compare fits. If reasonably vague priors and reasonably well-defined change points are used, they should be practically identical.
Plots: Check out the vdiffr package which ggplot2 uses.
The text was updated successfully, but these errors were encountered:
Test accuracy of fits:
rstanarm
, andloo
andwaic
too.rstanarm
orlme4
fit individual segments and compare fits. If reasonably vague priors and reasonably well-defined change points are used, they should be practically identical.vdiffr
package whichggplot2
uses.The text was updated successfully, but these errors were encountered: