Click to edit Master text styles
Second level
Third level
Fourth level
Fifth level
‹date/time›
‹footer›
‹#›
------=_NextPart_01C6AF00.E3A32AE0
Content-Location: file:///C:/CF6BE126/Stuff_files/master03.xml
Content-Transfer-Encoding: quoted-printable
Content-Type: text/xml; charset="utf-8"
‹header›
‹date/time&=
#8250;
‹footer›
‹#›
------=_NextPart_01C6AF00.E3A32AE0
Content-Location: file:///C:/CF6BE126/Stuff_files/pres.xml
Content-Transfer-Encoding: quoted-printable
Content-Type: text/xml; charset="utf-8"
=
Statistical
stuff happens
Vioxx,
placebo power and other wonders
![](3D"slide0001_image002.gif")
![](3D"slide0027_image004.jpg")
![](3D"slide0028_image006.jpg")
![](3D"slide0041_image008.jpg")
A few headlines
Low fat diet breast cancer hope (BBC May 2005)
Breast cancer link to high fat foods
(The Scotsman, July 2003=
)
Low- Fat Diet May Control Prostate Cancer (Health Ne=
ws, August
2005)
Low-fat diet, not wine, fights heart disease in France=
(CNN May, =
1999)
High-Fat Meal May Raise Risk Of Blood Clotting<=
span
lang=3DEN-GB>
-- Increasing Heart Attack And Stroke Risk (American =
Heart
Association, November 1997)
National study finds=
no
effect from reducing total dietary fat
The
study, a project of the National Institutes of Health, had taken eight yea=
rs, cost $415 million, and involved near=
ly
49,000 older women, 40 percent of whom were assigned to a diet that kept their intake of
calories from fat significantly below that of the other 60 percent. Researchers h=
ad
expected to confirm what earlier studies and conventional medical wisdom h=
ad
long suggested -- that consuming less fat is good for your health.
Researchers
found no difference between the two groups in terms of risk of =
breast cancer, colon cancer, heart d=
isease
or stroke.
Public release
date: 7- Feb-2006
Three Great Men
<=
span
style=3D'visibility:hidden'>•
<=
span
class=3DBB style=3D'position:absolute;left:-4.43%'>•Dr John Snow (1813 -1858)
<=
span
style=3D'visibility:hidden'>•
<=
span
class=3DBB style=3D'position:absolute;left:-4.09%'>•Sir Ronald Aylmer Fisher (1890 -1962)
<=
span
style=3D'visibility:hidden'>•
<=
span
class=3DBB style=3D'position:absolute;left:-4.43%'>•Sir Austin Bradford Hill (1897-1991)
=
<=
span
style=3D'visibility:hidden'>•
=
Dr John Snow
The f=
ather
of modern epidemiology
![](3D"slide0014_image009.gif")
![](3D"slide0013_image011.gif")
Sir Ro=
nald
Aylmer Fisher
•“perhaps the most original mathematical scientist of =
the
[twentieth] century” Bradley Efron Annals of Statistics (1976)
=
•“Fisher was a genius who almost single-handedly creat=
ed
the foundations for modern statistical science ….” Anders Hal=
d A History of Mathematical Statistics =
(1998)
•“Sir Ronald Fisher … could be regarded as
Darwin’s greatest twentieth-century successor.” Richa=
rd
Dawkins River out of
Eden (1995)
• Annals of Statistics (1976)
<=
span
style=3D'font-size:88%;visibility:hidden'>•
![](3D"slide0002_image012.jpg")
Randomisation!
Let it not be thought that Fisher in any way regarded Randomisation as an optiona=
l extra
to si=
gnificance
testing. One of the earliest sub-headings in his seminal book is Randomisation; =
the Physical Basis of the validit=
y of the
Test. Fi=
sher’s
many words on the subject can be boiled down to a simple statement – no randomisation means no significance!=
The one-in-twenty lottery!
![](3D"slide0015_image014.jpg")
![](3D"slide0016_image016.jpg")
Publication
Bias!
=
Sir Au=
stin
Bradford Hill
&#=
8226;Association of cigarettes with lung cancer
=
&#=
8226;Over-emphasis of significance testing
&#=
8226;The Hill Criteria
&=
#8211;Not about causation!
Relative Risk
<=
span
style=3D'visibility:hidden'>•
<=
span
style=3D'visibility:hidden'>•
•If X% of =
people
exposed to a putative cause suffer a certain effect and Y%=
not
exposed to the cause (or alternatively the general
population) suffer the same effect, the RR is X/Y
Relative Risk
•In epidemiologic research, [increases =
in
risk of less than 100 percent] are considered small and =
are usually difficult to interpret. Su=
ch
increases may be due to chance, statistical bias, or the <=
span
style=3D'position:absolute;top:49.25%;left:9.73%;width:84.45%;height:6.0%'=
>effects of confounding factors that ar=
e =
sometimes not evident .[Source: National Cancer Institute, Press Release, October =
26, =
1994.]
<=
span
style=3D'font-size:88%'>•100% increase is a relative risk of 2.0&#=
13;
<=
span
style=3D'visibility:hidden'>•=
The little red boo=
k
![](3D"slide0040_image018.jpg")