covidseir
covidseir copied to clipboard
seananderson
Bayesian SEIR model to estimate the effects of social-distancing on COVID-19
This is a very minor point. The link on the README about installing on Windows (https://github.com/stan-dev/rstan/wiki/Installing-RStan-from-source-on-Windows) looks broken, probably on the Stan side. I don't know whether it would be...
How did you estimate the fraction of positive cases that are sampled/detected (the variable `samp_frac`)? You mentioned a model that works with hospital data etc.? Thanks in advance
- Implemented changes to introduce VoC into fitting and projections. - Updated version number and news to reflect changes - Ran `R CMD check` without errors
In order for the model to remain relevant into 2021 we need to consider how to incorporate the impact of vaccination and VoC. Both of these issues will require changes...
Add option to `plot_projection` to output a sample of trajectories from the posterior as opposed to showing the ribbons representing the percentiles.
I followed the instructions to install the covidseir package. The previous statement regarding the pkgbuild printed TRUE. Error: Failed to install 'covidseir' from GitHub: (converted from warning) installation of package...
So far we've been relying on lots of examples that get run on R CMD check (and of course the pre-prints that include simulation testing), but proper unit tests should...
Currently the approach is to treat every projection year as having a unique f parameter and they can just happen to be the same value. This is simplest coding wise...
- would somewhat slow down fitting since more estimated parameters would go into the ODE, but on balance it would require less fiddling and arbitrariness to setting breakpoints - this...
- would be helpful for us - a Shiny app could also potentially be used by others to upload their data and fit - would likely use the MAP estimate...
Metadata
Owner
Metadata
Bayesian SEIR model to estimate the effects of social-distancing on COVID-19