From Association to Causation: Some Remarks on the History of Statistics
D. Freedman. Statistical Science, 14 (3):
243--258(1999)
Zusammenfassung
The "numerical method" in medicine goes back to Pierre
Louis' 1835 study of pneumonia and John Snow's 1855 book on
the epidemiology of cholera. Snow took advantage of natural
experiments and used convergent lines of evidence to
demonstrate that cholera is a waterborne infectious
disease. More recently, investigators in the social and
life sciences have used statistical models and significance
tests to deduce cause-and-effect relationships from
patterns of association; an early example is Yule's 1899
study on the causes of poverty. In my view, this modeling
enterprise has not been successful. Investigators tend to
neglect the difficulties in establishing causal relations,
and the mathematical complexities obscure rather than
clarify the assumptions on which the analysis is based.
Formal statistical inference is, by its nature,
conditional. If maintained hypotheses A, B, C,... hold,
then H can be tested against the data. However, if A, B,
C,... remain in doubt, so must inferences about H. Careful
scrutiny of maintained hypotheses should therefore be a
critical part of empirical work-a principle honored more
often in the breach than the observance. Snow's work on
cholera will be contrasted with modern studies that depend
on statistical models and tests of significance. The
examples may help to clarify the limits of current
statistical techniques for making causal inferences from
patterns of association.
%0 Journal Article
%1 Free:1999
%A Freedman, David
%D 1999
%J Statistical Science
%K causality history statistics
%N 3
%P 243--258
%T From Association to Causation: Some Remarks on the History of Statistics
%V 14
%X The "numerical method" in medicine goes back to Pierre
Louis' 1835 study of pneumonia and John Snow's 1855 book on
the epidemiology of cholera. Snow took advantage of natural
experiments and used convergent lines of evidence to
demonstrate that cholera is a waterborne infectious
disease. More recently, investigators in the social and
life sciences have used statistical models and significance
tests to deduce cause-and-effect relationships from
patterns of association; an early example is Yule's 1899
study on the causes of poverty. In my view, this modeling
enterprise has not been successful. Investigators tend to
neglect the difficulties in establishing causal relations,
and the mathematical complexities obscure rather than
clarify the assumptions on which the analysis is based.
Formal statistical inference is, by its nature,
conditional. If maintained hypotheses A, B, C,... hold,
then H can be tested against the data. However, if A, B,
C,... remain in doubt, so must inferences about H. Careful
scrutiny of maintained hypotheses should therefore be a
critical part of empirical work-a principle honored more
often in the breach than the observance. Snow's work on
cholera will be contrasted with modern studies that depend
on statistical models and tests of significance. The
examples may help to clarify the limits of current
statistical techniques for making causal inferences from
patterns of association.
@article{Free:1999,
abstract = {The {"}numerical method{"} in medicine goes back to Pierre
Louis' 1835 study of pneumonia and John Snow's 1855 book on
the epidemiology of cholera. Snow took advantage of natural
experiments and used convergent lines of evidence to
demonstrate that cholera is a waterborne infectious
disease. More recently, investigators in the social and
life sciences have used statistical models and significance
tests to deduce cause-and-effect relationships from
patterns of association; an early example is Yule's 1899
study on the causes of poverty. In my view, this modeling
enterprise has not been successful. Investigators tend to
neglect the difficulties in establishing causal relations,
and the mathematical complexities obscure rather than
clarify the assumptions on which the analysis is based.
Formal statistical inference is, by its nature,
conditional. If maintained hypotheses A, B, C,... hold,
then H can be tested against the data. However, if A, B,
C,... remain in doubt, so must inferences about H. Careful
scrutiny of maintained hypotheses should therefore be a
critical part of empirical work-a principle honored more
often in the breach than the observance. Snow's work on
cholera will be contrasted with modern studies that depend
on statistical models and tests of significance. The
examples may help to clarify the limits of current
statistical techniques for making causal inferences from
patterns of association.},
added-at = {2009-10-28T04:42:52.000+0100},
author = {Freedman, David},
biburl = {https://www.bibsonomy.org/bibtex/2ea3c8d28f07a1a5067d7edac2e673994/jwbowers},
citeulike-article-id = {207609},
date-added = {2007-09-03 22:45:16 -0500},
date-modified = {2007-09-03 22:45:16 -0500},
interhash = {5f79bc245c862a42cb1f35e8bc022003},
intrahash = {ea3c8d28f07a1a5067d7edac2e673994},
journal = {Statistical Science},
keywords = {causality history statistics},
number = 3,
opturl = {http://links.jstor.org/sici?sici=0883-4237%28199908%2914%3A3%3C243%3AFATCSR%3E2.0.CO%3B2-V},
pages = {243--258},
priority = {2},
timestamp = {2009-10-28T04:42:58.000+0100},
title = {From Association to Causation: Some Remarks on the History of Statistics},
volume = 14,
year = 1999
}