You don’t _need_ a plot of a log-linear graph. It’s just easier to pick out the changes from the exponential. We’re very good at perceiving lines and when lines veer off in a new direction.
-
New conversation
-
-
-
Great idea to graph the log, but the article seems to start from the premise that the number of positive tests is proportional to the number of cases. What is the justification for that assumption?
-
1) Just the number of known positive tests will overwhelm hospitals in parts of the country next week (New York). 2) Details will be complicated but regardless, you want the view that tells the clearest story. Then you can take the next steps.
End of conversation
New conversation -
-
-
Thanks for this, can we view a graph like this updated every day?
-
This site is good for giving you the latest terrible numbers. You can toggle between linear and logarithmic. https://www.worldometers.info/coronavirus/country/us/ …
- 1 more reply
New conversation -
-
-
Log graphs are the way to go to track exponential growth! US cases for example almost perfectly tracking 10x every 7.8 days (L) as many countries doing/did (R)pic.twitter.com/QvAGXFyQfR
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
when linearity can interpret the data incorrectly, and the logarithmic curve is able to explain the increase exponentially
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It's the same, the only difference is that
#COVIDー19 started later in the USA (so in both charts patterns are the same but little further on the right side for the USA) and Italy has 60milion vs >300milion population. But I agree, chart curves could mislead the perceptionThanks. 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.