I'm in Italy (actually this discussion made me finally sign up to
Radical Statistcis with my Italian address, University of Bologna), and
we had a discussion here about the apparently high Covid-19 mortality in
Italy. One explanation that came up is that in Italy, on top of the high
average age of the population, there's a culture that old people go out
and socialise a lot, and have a lot of body contact, hugging, and
kissing. Surely there's not that much of it in Germany (I'm actually
German). To what extent this can explain the different observed death
rates is not clear, but it quite certainly plays a role (Germany
currently having zero deaths with >1000 confirmed infections is in any
case still a mystery; German old people are not all hanging around in
their homes *all the time*, not meeting people at all).
Higher death rate in Lombardy could be explained by the fact that the
thing started in Lombardy and early diagnoses were to a large percentage
serious cases whereas elsewhere (and also later in Lombardy) people were
tested based on information of contact with infected people alone, which
didn't exist in the beginning, and also milder symptoms.
Christian
On 3/9/20 2:15 PM, Greg Dropkin wrote:
> also age doesn't explain Lombardy vs Italy
>
> Lombardy: 22.59% over 65. Death rate 6.37%
> Italy: 22.75% over 65. Death rate 4.96%
>
> Greg
>
>> I expect there's more to it:
>>
>> Germany: 22.36% over 65. No reported deaths in 1151 cases = 0%
>> France: 19.82% over 65. Death rate 19 / 1209 = 1.57%
>> Spain: 18.15% over 65. Death rate 25 / 979 = 2.55%
>>
>> i.e. on this small sample, death rate is not simply explained by age
>> structure.
>>
>> my guess is that it is also something to do with poverty and the state of
>> the healthcare system.
>>
>> Greg
>>
>>> Interesting insights
>>>
>>>
>>>
>>> Thomas Cox PhD RN
>>> [log in to unmask]
>>>
>>>
>>> On Monday, March 9, 2020, 07:58:42 AM EDT, David Gordon
>>> <[log in to unmask]> wrote:
>>>
>>> #yiv7131858572 P {margin-top:0;margin-bottom:0;}Less than 12% of the
>>> population in China is aged over 65.
>>> Almost 23% of the population of Italy is aged over 65.
>>> Covid-19 seems to result in significantly higher death rates amongst
>>> older
>>> people.
>>> If you control for the age profile of Lombardy vs you comparison
>>> countries, then there may be no significant differences in the Lombardy
>>> mortality rate
>>>
>>> Regards
>>> David Gordon
>>> PS about 18% of the UK population is aged over 65....
>>> ___________________________________________
>>> Dave Gordon
>>> Bristol Poverty Institute
>>> Townsend Centre for International Poverty Research
>>> University of Bristol
>>> 10 Woodland Road
>>> Bristol BS8 1TZ, UK
>>>
>>> E-Mail: [log in to unmask]
>>> Tel: +44-(0)117-954 6761
>>> Fax: +44-(0)117-954 6756
>>> From: email list for Radical Statistics <[log in to unmask]> on
>>> behalf of Greg Dropkin <[log in to unmask]>
>>> Sent: 09 March 2020 11:33
>>> To: [log in to unmask] <[log in to unmask]>
>>> Subject: Re: Over to you, Radstatters! What can you make of this?! The
>>> death rate in Lombardy 6.37% is significantly higher than in Italy as
>>> a whole 4.96%, and Italy is much higher than the world rate 3.5%
>>>
>>> in R
>>>
>>> prop.test(c(267,366),c(4189,7375))
>>>
>>> 2-sample test for equality of proportions with continuity correction
>>>
>>> data: c(267, 366) out of c(4189, 7375)
>>> X-squared = 10.01, df = 1, p-value = 0.001557
>>> alternative hypothesis: two.sided
>>> 95 percent confidence interval:
>>> 0.00501951 0.02320298
>>> sample estimates:
>>> prop 1 prop 2
>>> 0.06373836 0.04962712
>>>
>>>
>>> prop.test(c(366,3892),c(7375,111228))
>>>
>>> 2-sample test for equality of proportions with continuity correction
>>>
>>> data: c(366, 3892) out of c(7375, 111228)
>>> X-squared = 42.383, df = 1, p-value = 7.505e-11
>>> alternative hypothesis: two.sided
>>> 95 percent confidence interval:
>>> 0.009490875 0.019780984
>>> sample estimates:
>>> prop 1 prop 2
>>> 0.04962712 0.03499119
>>>
>>> Greg
>>>
>>>>
>>>> ******************************************************
>>>> Please note that if you press the 'Reply' button your
>>>> message will go only to the sender of this message.
>>>> If you want to reply to the whole list, use your mailer's
>>>> 'Reply-to-All' button to send your message automatically
>>>> to [log in to unmask]
>>>> Disclaimer: The messages sent to this list are the views of the sender
>>> and
>>>> cannot be assumed to be representative of the range of views held by
>>> subscribers to the Radical Statistics Group. To find out more about
>>> Radical Statistics and its aims and activities and read current and past
>>> issues of our newsletter you are invited to visit our web site
>>>> www.radstats.org.uk.
>>>> *******************************************************
>>>>
>>> ******************************************************
>>> Please note that if you press the 'Reply' button your
>>> message will go only to the sender of this message.
>>> If you want to reply to the whole list, use your mailer's
>>> 'Reply-to-All' button to send your message automatically
>>> to [log in to unmask]
>>> Disclaimer: The messages sent to this list are the views of the sender
>>> and
>>> cannot be assumed to be representative of the range of views held by
>>> subscribers to the Radical Statistics Group. To find out more about
>>> Radical Statistics and its aims and activities and read current and past
>>> issues of our newsletter you are invited to visit our web
>>> sitewww.radstats.org.uk.
>>> *******************************************************
>>> ******************************************************Please note that
>>> if
>>> you press the 'Reply' button yourmessage will go only to the sender of
>>> this message.If you want to reply to the whole list, use your
>>> mailer's'Reply-to-All' button to send your message automaticallyto
>>> [log in to unmask]: The messages sent to this list are
>>> the
>>> views of the sender and cannot be assumed to be representative of the
>>> range of views held by subscribers to the Radical Statistics Group. To
>>> find out more about Radical Statistics and its aims and activities and
>>> read current and past issues of our newsletter you are invited to visit
>>> our web site
>>> www.radstats.org.uk.*******************************************************
>>>
>>> ******************************************************
>>> Please note that if you press the 'Reply' button your
>>> message will go only to the sender of this message.
>>> If you want to reply to the whole list, use your mailer's
>>> 'Reply-to-All' button to send your message automatically
>>> to [log in to unmask]
>>> Disclaimer: The messages sent to this list are the views of the sender
>>> and
>>> cannot be assumed to be representative of the range of views held by
>>> subscribers to the Radical Statistics Group. To find out more about
>>> Radical Statistics and its aims and activities and read current and past
>>> issues of our newsletter you are invited to visit our web site
>>> www.radstats.org.uk.
>>> *******************************************************
>> ******************************************************
>> Please note that if you press the 'Reply' button your
>> message will go only to the sender of this message.
>> If you want to reply to the whole list, use your mailer's
>> 'Reply-to-All' button to send your message automatically
>> to [log in to unmask]
>> Disclaimer: The messages sent to this list are the views of the sender and
>> cannot be assumed to be representative of the range of views held by
>> subscribers to the Radical Statistics Group. To find out more about
>> Radical Statistics and its aims and activities and read current and past
>> issues of our newsletter you are invited to visit our web site
>> www.radstats.org.uk.
>> *******************************************************
>>
>>
> ******************************************************
> Please note that if you press the 'Reply' button your
> message will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's
> 'Reply-to-All' button to send your message automatically
> to [log in to unmask]
> Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
--
Christian Hennig
Dipartimento di Scienze Statistiche "Paolo Fortunati",
Universita di Bologna, phone +39 05120 98163
[log in to unmask]
******************************************************
Please note that if you press the 'Reply' button your
message will go only to the sender of this message.
If you want to reply to the whole list, use your mailer's
'Reply-to-All' button to send your message automatically
to [log in to unmask]
Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk.
*******************************************************
|