[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Cohen's latest reward



From: Kai Kaletsch <info@eic.nu>>Don,



Don,



Your reference below deals with problems that arise when you try to take an 

observation at the county level and make inferences about risk at an 

individual level.

--------------

Kai, No, what you are talking about above is called the ecologic fallacy.  

You are confusing the ecologic fallacy with cross-level bias and intra/inter 

county bias.



Don Smith



---------------

> > Kai,

> >

> > Cross-level bias or inter and intra county variability are not a problem

>for

> > case-control studies since you have data from INDIVIDUALs or individual

> > level data. As far as its plausibility, see:

> >

> > Ann Public Health 1995;16:61-81

> >

> > Ecologic studies in epidemiology: concepts, principles, and methods.

> >

> > Morgenstern H.

> >

> > Department of Epidemiology, University of California, Los Angeles, 

>School

>of

> > Public Health, USA.

> >

> > An ecologic study focuses on the comparison of groups, rather than

> > individuals; thus, individual-level data are missing on the joint

> > distribution of variables within groups. Variables in an ecologic 

>analysis

> > may be aggregate measures, environmental measures, or global measures. 

>The

> > purpose of an ecologic analysis may be to make biologic inferences about

> > effects on individual risks or to make ecologic inferences about effects

>on

> > group rates. Ecologic study designs may be classified on two dimensions:

>(a)

> > whether the primary group is measured (exploratory vs analytic study); 

>and

> > (b) whether subjects are grouped by place (multiple-group study), by 

>time

> > (time-trend study), or by place and time (mixed study). Despite several

> > practical advantages of ecologic studies, there are many methodologic

> > problems that severely limit causal inference, including ecologic and

> > cross-level bias, problems of confounder control, within-group

> > misclassification, lack of adequate data, temporal ambiguity,

>collinearity,

> > and migration across groups.

> >

> > ----------------------------

> >

> >

> > Don Smith

> >

> >

> > >From: Kai Kaletsch <info@eic.nu>

> > >

> > >Don,

> > >

> > >"inter county variability" in itself can never be a reason for 

>anything,

> > >not

> > >just Cohen's data. There has to be a systematic reason (mechanism) why

> > >inter

> > >county variability would produce such a strong correlation. If there is

> > >random inter county variability, it would bias the results toward the

>null.

> > >

> > >If you have a graph of x vs. y which shows a statistically significant

> > >structure, your explanation of the graph must, in some way, involve 

>both

>x

> > >and y. Otherwise it is not an explanation of the graph. This holds for

>all

> > >sciences. Epidemiology is not exempt from the basic laws of logic.

> > >

> > >Kai Kaletsch

> > >

> > >P.S.: You can probably control the inter county variability (by

>stratifying

> > >the data) better than you can control the inter person variability (by

> > >choosing the right controls) in case control studies. Would you not be

>more

> > >concerned about "intra" county variability? As long as you leave the 

>data

> > >at

> > >the county level, there is no ecological fallacy. You could consider 

>each

> > >county to be an organism [my version of the Gaia theory :) ]. You would

> > >still be left with the question: What are the counties with high radon

> > >doing

> > >right and what are the counties with low radon doing wrong?

> > >

> > >----- Original Message -----

> > >From: "Rad health" <healthrad@hotmail.com>

> > >To: <info@eic.nu>; <radsafe@list.vanderbilt.edu>

> > >Sent: Wednesday, January 16, 2002 8:18 PM

> > >Subject: Re: Cohen's latest reward

> > >

> > >

> > > > Kai,

> > > >

> > > > What emperical basis do you have to show that Cohen's inverse

> > >relationship

> > > > is not due to inter county variability?

> > > >

> > > > Don Smith

> > > >

> > > >

> > > > >From: Kai Kaletsch <info@eic.nu>

> > > > >To: Rad health <healthrad@hotmail.com>, radsafe@list.vanderbilt.edu

> > > > >Subject: Re: Cohen's latest reward

> > > > >Date: Wed, 16 Jan 2002 19:39:17 -0600

> > > > >

> > > > >Explaining a statistically strong association with "cross level 

>bias

> > >and

> > > > >inter county variability" is like explaining the pollution in a 

>lake

> > >with

> > > > >"all the dead fish that keep washing up on shore". Both the cross

>level

> > > > >bias

> > > > >and the dead fish are symptoms of some more fundamental mechanism

>that

> > > > >needs

> > > > >to be identified.

> > > > >

> > > > >Kai Kaletsch

> > > > >

> > > > >----- Original Message -----

> > > > >From: "Rad health" <healthrad@HOTMAIL.COM>

> > > > >To: <radsafe@list.vanderbilt.edu>

> > > > >Sent: Wednesday, January 16, 2002 4:48 PM

> > > > >Subject: Cohen's latest reward

> > > > >

> > > > >

> > > > > > Dr. Cohen,

> > > > >

> > > > > >....one of the major factors,

> > > > > > among others, most likely causing your paradoxical findings is

> > > > >cross-level

> > > > > > bias or inter county variability....

> > > > >

> > > > >

> > > > >

> > > >

> > > >

> > > > _________________________________________________________________

> > > > Send and receive Hotmail on your mobile device: 

>http://mobile.msn.com

> > > >

> > >

> >

> >

> > _________________________________________________________________

> > MSN Photos is the easiest way to share and print your photos:

> > http://photos.msn.com/support/worldwide.aspx

> >

> > ************************************************************************

> > You are currently subscribed to the Radsafe mailing list. To 

>unsubscribe,

> > send an e-mail to Majordomo@list.vanderbilt.edu  Put the text 

>"unsubscribe

> > radsafe" (no quote marks) in the body of the e-mail, with no subject 

>line.

>You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/

> >

>

>************************************************************************

>You are currently subscribed to the Radsafe mailing list. To unsubscribe,

>send an e-mail to Majordomo@list.vanderbilt.edu  Put the text "unsubscribe

>radsafe" (no quote marks) in the body of the e-mail, with no subject line. 

>You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/

>





_________________________________________________________________

Chat with friends online, try MSN Messenger: http://messenger.msn.com



************************************************************************

You are currently subscribed to the Radsafe mailing list. To unsubscribe,

send an e-mail to Majordomo@list.vanderbilt.edu  Put the text "unsubscribe

radsafe" (no quote marks) in the body of the e-mail, with no subject line. You can view the Radsafe archives at http://www.vanderbilt.edu/radsafe/