search

ImperialCollegeLondon / epidemia

epidemia package
https://imperialcollegelondon.github.io/epidemia/index.html
47 stars 15 forks source link

Reporting Rt as a moving average over x days #25

Closed s-mishra closed 4 years ago

s-mishra commented 4 years ago

I do not necessarily agree with this but many packages in R estimation have this functionality of reporting Rt as a moving average of estimated value. For us, this would be a simple tweak to have it, where default is no moving-average but user can provide things like x days moving average.

agandy commented 4 years ago

Is this just saying that plot_Rt(...) should be having a "smooth" argument?

agandy commented 4 years ago

@s-mishra how exactly do you suggest this to be implemented? An option "movingaverage=x", where x gives the number of days to compute the moving average over?

s-mishra commented 4 years ago

yes @agandy exactly as you suggested above. By default no moving average

jonathanishhorowicz commented 4 years ago

I can add this with #34. To clarify, we just want to plot the mean of the Rt samples, but with an option to smooth it over a number of days?

s-mishra commented 4 years ago

Not just means but whole posterior. So we would need to essentially do a moving average across all posterior samples and then give same information of 50%CI, 95%CI and mean.

agandy commented 4 years ago

Yes, so the same plot as plot_rt, but the individual Rt samples get replaced by Rt samples averaged over the last x days.

From: Swapnil Mishra notifications@github.com Sent: 06 July 2020 10:02 To: ImperialCollegeLondon/epidemia epidemia@noreply.github.com Cc: Gandy, Axel a.gandy@imperial.ac.uk; Mention mention@noreply.github.com Subject: Re: [ImperialCollegeLondon/epidemia] Reporting Rt as a moving average over x days (#25)

This email from notifications@github.commailto:notifications@github.com originates from outside Imperial. Do not click on links and attachments unless you recognise the sender. If you trust the sender, add them to your safe senders listhttps://spam.ic.ac.uk/SpamConsole/Senders.aspx to disable email stamping for this address.

Not just means but whole posterior. So we would need to essentially do a moving average across all posterior samples and then give same information of 50%CI, 95%CI and mean.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://github.com/ImperialCollegeLondon/epidemia/issues/25#issuecomment-654109066, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AA7JUZS44YYMSXZK7M2DW53R2GHI5ANCNFSM4N726N7Q.

jonathanishhorowicz commented 4 years ago

Ok, will do

jonathanishhorowicz commented 4 years ago

Resolved along with #34