And because someone rightly complained that the Add Country button wasn’t as prominent as it needs to be, that button is now bigger and blue.
-
-
And here is CFR vs median age in the country:https://ourworldindata.org/grapher/case-fatality-rate-of-covid-19-vs-median-age …
1 reply 2 retweets 4 likes -
Replying to @MaxCRoser @tylercowen
Might be worth making the radius of the circle the log of the total number of deaths. Then it would be easier to ignore the outliers.
1 reply 1 retweet 7 likes -
It would be interesting to see this on a log scale too. A handful of outliers are cramming a lot of interesting data into the bottom quarter of the graph. Why not make it a feature of all your graphs to have a button for switching from linear to log on the y axis?
1 reply 0 retweets 5 likes -
Replying to @paulg @tylercowen
Good points! Just changed it: https://ourworldindata.org/grapher/case-fatality-rate-of-covid-19-vs-median-age … The size of the circle now corresponds to the total confirmed deaths up to that date. And you can switch any of the axes to log.
1 reply 3 retweets 15 likes -
Replying to @MaxCRoser @tylercowen
I already learned something interesting. Judging from the data so far, the way countries end up with a lot of deaths is by having a high CFR (rather than having a high population).
6 replies 0 retweets 22 likes -
In fact, Max, how about a scatterplot of CFR vs total deaths? That should show the correlation directly.
2 replies 1 retweet 6 likes -
Replying to @paulg @tylercowen
Don't know what your prior was, but maybe it's less correlated that you had thought? https://ourworldindata.org/grapher/deaths-covid-19-vs-case-fatality-rate … (By clicking into the timeline you can see the change of both variables over time which shows that not in all countries both measures moved together.)
3 replies 4 retweets 8 likes -
Replying to @MaxCRoser @tylercowen
There looks like a definite trend to that data.
4 replies 0 retweets 2 likes -
Hard to untangle the causality though - it seems somewhat tautological that more deaths would yield a higher CFR and vice versa
1 reply 0 retweets 0 likes
It would be tautological(ish) if it were deaths per capita rather than simply deaths.
-
-
That's fair. I think this is still missing something that accounts for the testing coverage of each point though
0 replies 0 retweets 0 likesThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.