CDC statistics "declining percentages" - Printable Version
+- The CardBoard (https://thecardboard.org/board)
+-- Forum: Emergency (https://thecardboard.org/board/forum-11.html)
+--- Forum: Covid-19 (https://thecardboard.org/board/forum-12.html)
+--- Thread: CDC statistics "declining percentages" (/thread-20110.html)
+- The CardBoard (https://thecardboard.org/board)
+-- Forum: Emergency (https://thecardboard.org/board/forum-11.html)
+--- Forum: Covid-19 (https://thecardboard.org/board/forum-12.html)
+--- Thread: CDC statistics "declining percentages" (/thread-20110.html)
CDC statistics "declining percentages" - M T - 07-19-2020
From the CDC weekly surveillance postings on COVID-19, Mortality section:
"Based on death certificate data, the percentage of deaths attributed to pneumonia, influenza or COVID-19 (PIC) decreased from"
June 19: 11.4% during week 23 to 7.1% during week 24
June 26: 9.5% during week 24 to 6.9% during week 25 ...This is the ninth week of a declining percentage of deaths due to PIC,
July 3: 9.0% during week 25 to 5.9% during week 26, representing the tenth week of a declining percentage of deaths due to PIC.
July 10: 6.9% during week 26 to 5.5% during week 27, representing the eleventh week of a declining percentage of deaths due to PIC.
July 17(current): 8.1% during week 27 to 6.4% during week 28, representing the twelfth week of a declining percentage of deaths due to PIC.
Pretty good decrease, right? Every week, going down several percentage points. If you happen to see it any one week, it looks promising.
From 11.4%, it dropped a total of 13.1% over the next 5 weeks. Of course that's impossible. But it is sorta like walking down the UP elevator.
By 1st report of the various weeks: 7.1%, 6.9%, 5.9%, 5.5%, 6.4%. Declining percentage? No
By 2nd report of the weeks: 11.4%, 9.5%, 9.0%, 6.9%, 8.1% Declining percentage? No
It may be that as the numbers for each week (say #26) kept increasing over time, it may be that the 8.1% for week 27 was less than the 5.9%...6.9%....(what am I bid?) for week 26. This data is from the NCHS Mortality Surveillance Data. Their data page was last updated April 17.
That's not very transparent. I'd even say it look like misleading, even though they say the percentages will change, because they are reporting numbers far less than what they know the number will get to. For instance, trying to interpolate on a graph they present elsewhere, I'd say that "7.1% during week 24" looks to have wound up around 13+/-1%.
lex24 - lex24 - 07-19-2020
Your point being? I’ts a question, not sarcasm. I truly don’t get your point
RE: lex24 - magnus - 07-19-2020
(07-19-2020, 09:21 PM)lex24 Wrote: Your point being? I’ts a question, not sarcasm. I truly don’t get your pointLet me see if I understand M T...
He's saying that the CDC issues 2 reports for each week. One soon after the week has ended. And one a little while after the week has ended.
Likely, the 2nd report for each week will have more deaths because of late reports.
What M T finds misleading is that the CDC uses this 2nd report of a previous week and compares it to the 1st report of the current week.
That's not an apples to apples comparison. If they stuck to comparing only 2nd reports from each week, or only 1st reports from each week, they would have to report that in week 28, we've unfortunately started increasing again.
But instead, they do a little data manipulation and use the 2nd report from the previous week (which of course has now grown bigger than what it was from the 1st report) to compare to the 1st report from this week.
Anyway, I probably wasn't any better at explaining it. But maybe I threw out enough words that I was able to give you a glancing nudge. =)
lex24 - lex24 - 07-19-2020
(07-19-2020, 10:04 PM)magnus Wrote:(07-19-2020, 09:21 PM)lex24 Wrote: Your point being? I’ts a question, not sarcasm. I truly don’t get your pointLet me see if I understand M T...
He's saying that the CDC issues 2 reports for each week. One soon after the week has ended. And one a little while after the week has ended.
Likely, the 2nd report for each week will have more deaths because of late reports.
What M T finds misleading is that the CDC uses this 2nd report of a previous week and compares it to the 1st report of the current week.
That's not an apples to apples comparison. If they stuck to comparing only 2nd reports from each week, or only 1st reports from each week, they would have to report that in week 28, we've unfortunately started increasing again.
But instead, they do a little data manipulation and use the 2nd report from the previous week (which of course has now grown bigger than what it was from the 1st report) to compare to the 1st report from this week.
Anyway, I probably wasn't any better at explaining it. But maybe I threw out enough words that I was able to give you a glancing nudge. =)
Thanks. I think I’m dizzy, but thanks. :)