Results 1  10
of
14
From association to causation: Some remarks on the history of statistics
 Statist. Sci
, 1999
"... The “numerical method ” in medicine goes back to Pierre Louis ’ study of pneumonia (1835), and John Snow’s book on the epidemiology of cholera (1855). Snow took advantage of natural experiments and used convergent lines of evidence to demonstrate that cholera is a waterborne infectious disease. More ..."
Abstract

Cited by 23 (6 self)
 Add to MetaCart
The “numerical method ” in medicine goes back to Pierre Louis ’ study of pneumonia (1835), and John Snow’s book on the epidemiology of cholera (1855). 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 causeandeffect relationships from patterns of association; an early example is Yule’s study on the causes of poverty (1899). 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. 1.
On specifying graphical models for causation, and the identification problem
 Evaluation Review
, 2004
"... This paper (which is mainly expository) sets up graphical models for causation, having a bit less than the usual complement of hypothetical counterfactuals. Assuming the invariance of error distributions may be essential for causal inference, but the errors themselves need not be invariant. Graphs c ..."
Abstract

Cited by 16 (1 self)
 Add to MetaCart
This paper (which is mainly expository) sets up graphical models for causation, having a bit less than the usual complement of hypothetical counterfactuals. Assuming the invariance of error distributions may be essential for causal inference, but the errors themselves need not be invariant. Graphs can be interpreted using conditional distributions, so that we can better address connections between the mathematical framework and causality in the world. The identification problem is posed in terms of conditionals. As will be seen, causal relationships cannot be inferred from a data set by running regressions unless there is substantial prior knowledge about the mechanisms that generated the data. There are few successful applications of graphical models, mainly because few causal pathways can be excluded on a priori grounds. The invariance conditions themselves remain to be assessed.
Statistical Models for Causation: What Inferential Leverage Do They Provide?” Evaluation Review, 30, 691–713. http://www.stat.berkeley.edu/users/census/oxcauser.pdf
 2008a). “Diagnostics Cannot Have Much Power Against General Alternatives.” http://www.stat.berkeley.edu/users/census/notest.pdf Freedman, D. A. (2008b). “Randomization Does Not Justify Logistic Regression.” http://www.stat.berkeley.edu/users/census/neylog
, 2006
"... Experiments offer more reliable evidence on causation than observational studies, which is not to gainsay the contribution to knowledge from observation. Experiments should be analyzed as experiments, not as observational studies. A simple comparison of rates might be just the right tool, with littl ..."
Abstract

Cited by 11 (4 self)
 Add to MetaCart
Experiments offer more reliable evidence on causation than observational studies, which is not to gainsay the contribution to knowledge from observation. Experiments should be analyzed as experiments, not as observational studies. A simple comparison of rates might be just the right tool, with little value added by “sophisticated” models. This article discusses current models for causation, as applied to experimental and observational data. The intentiontotreat principle and the effect of treatment on the treated will also be discussed. Flaws in perprotocol and treatmentreceived estimates will be demonstrated.
Presenting Confounding and Standardization Graphically
 STATS MAGAZINE
, 2006
"... Did you know that the US has a higher death rate than Mexico? It’s a fact. In 2003, the death rate was 80 % higher in the US than in Mexico (8.4 per 100,000 versus 4.7). What does this statistic mean? Does Mexico have better health care than the US? That seems very unlikely. Yet it is difficult to c ..."
Abstract

Cited by 9 (7 self)
 Add to MetaCart
Did you know that the US has a higher death rate than Mexico? It’s a fact. In 2003, the death rate was 80 % higher in the US than in Mexico (8.4 per 100,000 versus 4.7). What does this statistic mean? Does Mexico have better health care than the US? That seems very unlikely. Yet it is difficult to claim that this unexpected relationship is due to chance, error or bias. The populations being studied are large; death is definite and usually counted accurately. You may be perplexed, confused or confounded when you learn that death rates are even lower in Ecuador and Saudi Arabia (4.3 and 2.7). An alternate explanation is confounding. Last (1995) defines confounding as “a situation in which the effects of two processes are not separated.” Confounding reflects the influence of a lurking variable. A lurking variable is often referred to as a confounder which Last defines as “a variable that can cause or prevent the outcome of interest … and is associated with the factor under investigation.” In comparing these death rates, a lurking variable may be the difference in the age distributions. Mexico has a much younger population than the US. In 2003, people under 15 were 50% more prevalent in Mexico than in the US (32% compared to 21%). People 65 and older were more than twice as prevalent in the US as in Mexico (12% compared to 5%). It’s a fact that older people are much more likely to die than younger people. Unless we take age distribution into account, a comparison of these crude (unadjusted) death rates may be misleading. Mexico’s comparatively low death rate is most likely due to its youthful population, rather than to its health care system. So how can we untangle this confusion? How can we “take into account’ the influence of a lurking variable that confounds an association?
Causation, Statistics, and Sociology
 EUROPEAN SOCIOLOGICAL REVIEW,VOL. 17 NO. 1, 1^20
, 2001
"... Three different understandings of causation, each importantly shaped by the work of statisticians, are examined from the point of view of their value to sociologists: causation as robust dependence, causation as consequential manipulation, and causation as generative process. The last is favoured as ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
Three different understandings of causation, each importantly shaped by the work of statisticians, are examined from the point of view of their value to sociologists: causation as robust dependence, causation as consequential manipulation, and causation as generative process. The last is favoured as the basis for causal analysis in sociology. It allows the respective roles of statistics and theory to be clarified and is appropriate to sociology as a largely nonexperimental social science in which the concept of action is central.
Toward improved use of regression in macrocomparative analysis
 Comparative Social Research
, 2007
"... I agree with much of what Michael Shalev (2007) says in his paper, both about the limits of multiple regression and about how to improve quantitative analysis in macrocomparative research. With respect to the latter, Shalev suggests three avenues for advance: (1) improve regression through technica ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
I agree with much of what Michael Shalev (2007) says in his paper, both about the limits of multiple regression and about how to improve quantitative analysis in macrocomparative research. With respect to the latter, Shalev suggests three avenues for advance: (1) improve regression through technical refinement; (2) combine regression with case studies (triangulation); (3) turn to alternative methods of quantitative analysis such as multivariate tables and graphs or factor analysis (substitution). I want to suggest some additional ways in which the use of regression in macrocomparative analysis could be improved. None involves technical refinement. Instead, most have to do with relatively basic aspects of quantitative analysis that seem, in my view, to be commonly ignored or overlooked. LOOK AT THE DATA Shalev’s third suggested path for progress consists of using tables, graphs, and tree diagrams to examine causal hierarchy and complexity and to identify cases meriting more indepth scrutiny. This should be viewed not as (or at least not solely as) a substitute for regression but rather as a critical component of regression analysis. All of us were (I hope) taught in our first
Statistical Models for Causation
, 2005
"... We review the basis for inferring causation by statistical modeling. Parameters should be stable under interventions, and so should error distributions. There are also statistical conditions on the errors. Stability is difficult to establish a priori, and the statistical conditions are equally probl ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We review the basis for inferring causation by statistical modeling. Parameters should be stable under interventions, and so should error distributions. There are also statistical conditions on the errors. Stability is difficult to establish a priori, and the statistical conditions are equally problematic. Therefore, causal relationships are seldom to be inferred from a data set by running statistical algorithms, unless there is substantial prior knowledge about the mechanisms that generated the data. We begin with linear models (regression analysis) and then turn to graphical models, which may in principle be nonlinear.
Statistical Models for Causation: A Critical Review
"... Regression models are often used to infer causation from association. For instance, Yule [79] showed – or tried to show – that welfare was a cause of poverty. Path models and structural equation models are later ..."
Abstract
 Add to MetaCart
Regression models are often used to infer causation from association. For instance, Yule [79] showed – or tried to show – that welfare was a cause of poverty. Path models and structural equation models are later
35 LEARNING TO USE STATISTICS IN RESEARCH: A CASE STUDY OF LEARNING IN A UNIVERSITY BASED STATISTICAL CONSULTING CENTRE 4
"... This paper presents a qualitative case study of statistical practice in a universitybased statistical consulting centre. Naturally occurring conversations and activities in the consulting sessions provided opportunities to observe questions, problems, and decisions related to selecting, using, and r ..."
Abstract
 Add to MetaCart
This paper presents a qualitative case study of statistical practice in a universitybased statistical consulting centre. Naturally occurring conversations and activities in the consulting sessions provided opportunities to observe questions, problems, and decisions related to selecting, using, and reporting statistics and statistical techniques in research. The consulting sessions provided simultaneous opportunities for consultants and clients to learn about using statistics in research. Consistent with contemporary theories that emphasize social dimensions of learning, major themes relate to (a) types of clients and consulting interactions, (b) disciplinary and statistical expertise, and (c) the role of material objects and representations. Evidence shows that consultants and clients learned during the consulting sessions and that the statistical consulting centre contributed positively to teaching and research at the university.
What is Field Theory?* forthcoming, American Journal of Sociology
"... 19,000 incl. abstract, references & notes * I have profited from the rancorous discussions of the Highland Park Colloquium on Theory, Methods, and Beer. I would also like to thank Neil Fligstein, Matt George, Ann Mische, and the reviewers for their probing criticisms that greatly increased the coher ..."
Abstract
 Add to MetaCart
19,000 incl. abstract, references & notes * I have profited from the rancorous discussions of the Highland Park Colloquium on Theory, Methods, and Beer. I would also like to thank Neil Fligstein, Matt George, Ann Mische, and the reviewers for their probing criticisms that greatly increased the coherence of the argument, though all called for a more complete theoretical specification than I was able to provide. Finally, one can only acknowledge the loss of Pierre Bourdieu—it seems impossible to adequately describe how great a loss this is for the social sciences. What is Field Theory? Field theory is a more or less coherent approach in the social sciences, although the main directions of field theory have not been systematically integrated. The essence of field theory in the social sciences is the explanation of regularities in individual action by recourse to position visàvis others. Position in the field is in turn considered to indicate the potential for a force exerted on the person, but a force that impinges “from the inside ” through motivation as opposed to through external compulsion. Motivation is accordingly considered to be the paramount example of social structure in action, as opposed to a residue of chance or freedom. Field theory