Open rnayebi21 opened 2 weeks ago
Hey @rnayebi21 , thanks!
Before I try to review more carefully, can you:
dev
into your branch and fix any conflicts? (dev
now has vignette code with hard line breaks to make reviewing easier).styler::style_pkg()
to avoid the failing check above ☝️ . This is also available on the Addins tab at the top of RStudio.
Checklist
Please:
DESCRIPTION
andNEWS.md
. Always increment the patch version number (the third number), unless you are making a release PR from dev to main, in which case increment the minor version number (the second number).epiprocess
version in theDESCRIPTION
file ifepiprocess
soonepipredict
andepiprocess
Change explanations for reviewer
The current examples for the sliding AR and ARX produce forecasts that could use improvement due to the complex nature of the task. Additionally, the code somewhat hard to understand, especially the
k_week_ahead()
function.To address these problems, I've created a new version-faithful example that demonstrate more tractable forecasting tasks. Specifically, the example predicts the 7-day average of case rates using both lagged case rate averages and lagged death rate averages, rather than only predicting the case rate from lagged case rates. Moreover, I incorporated geo-pooling to improve the accuracy of the forecasts.