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.

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 intention-to-treat principle and the effect of treatment on the treated will also be discussed. Flaws in per-protocol and treatment-received estimates will be demonstrated.

Les documents de travail ne reflètent pas la position de l'INSEE et n'engagent que leurs auteurs. Working papers do not reflect the position of INSEE but only the views of the authors. 1 Observatoire sociologique du changement (Science-po & CNRS) and Laboratoire de Sociologie Quantitative

Causal inference is an important, controversial topic in the social sciences, where it is difficult to conduct experiments or measure and control for all confounding variables. To address this concern, the present study presents a probability index to assess the robustness of a causal inference to the impact of a confounding variable. The information from existing covariates is used to develop a reference distribution for gauging the likelihood of observing a given value of the impact of a confounding variable. Applications are illustrated with an empirical example pertaining to educational attainment. The methodology discussed in this study allows for multiple partial causes in the complex social phenomena that we study, and informs the controversy about causal inference that arises from the use of statistical models in the social sciences.

Traditional “hard ” OR has been based on quantitative modelling and embodies, usually implicitly, a positivist or empiricist philosophy. “Soft OR”, for instance problem structuring methods such as SSM, developed as an antithesis and embodied an interpretivist or constructivist philosophy. This has generated somewhat of a schism between the two sides. Previous papers have advocated critical realism as a philosophy of science that can potentially provide a dialectical synthesis in recognising both the value and limitations of these approaches. This paper explores the critical realist critique of quantitative modelling, as exemplified by multivariate statistics, and argues that its grounds must be reconceptualised within a multimethodological framework. Keywords:

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

This paper is a brief overview and evaluation of current mathematical/statistical causal models, including the structural equation model (SEM), TETRAD, and the graphical model. The efficacy of these approaches will be discussed in the philosophical context of the Duhem-Quine thesis, realism, simplicity, identifiability (testability), empirical adequacy, and probabilistic causality. The emphasis of this paper is on the philosophical aspect, not the mathematical or computational aspect of SEM, nonetheless, readers are not required to have a philosophical background to follow the arguments.

Statistical methods have had a successful half-century in sociology, contributing to a greatly improved standard of scientic rigor in the discipline. I identify three overlapping postwar generations of statistical methods in sociology, based on the kinds of data they address. The rst generation, which started in the late 1940s, deals with cross-tabulations, and focuses on measures of association and loglinear models, perhaps the area of statistics to which sociology has contributed the most. The second generation, which began in the 1960s, deals with unit-level survey data, and focuses on LISREL-type causal models and event history analysis. The third generation, starting to emerge in the late 1980s, deals with data that are neither cross-tabulations nor data matrices, either because they have a dierent form, such as texts or narratives, or because dependence is a crucial aspect, as with spatial or social network data. There are many new challenges and the area is ripe for statistic...

Statistical methods have had a successful half-century in sociology, contributing to a greatly improved standard of scientic rigor in the discipline. I identify three overlapping postwar generations of statistical methods in sociology, based on the kinds of data they address. The rst generation, which started in the late 1940s, deals with cross-tabulations, and focuses on measures of association and loglinear models, perhaps the area of statistics to which sociology has contributed the most. The second generation, which began in the 1960s, deals with unit-level survey data, and focuses on LISREL-type causal models and event history analysis. The third generation, starting to emerge in the late 1980s, deals with data that do not fall easily into either of these categories, either because they have a dierent form, such as texts or narratives, or because dependence is a crucial aspect, as with spatial or social network data. There are many new challenges and the area is ripe for statistical research; several major institutions have recently launched new initiatives in statistics and the social sciences. Contents 1

Abstract. Researchers are required to make methodological choices about the underlying nature of phenomena being investigated, which appropriate research methods to use and how to present valid evidence. Information systems (IS) is a discipline originally rooted in a single overarching perspective, the positivist/realist domain, but critics of such a narrow view have encouraged a move towards more interpretive approaches in order to understand human thought and action in social and organisational contexts. Addressing this gap, we demonstrate, using examples from case study and ethnographic research on human resourcing information systems (HRIS), how four analytical „tools ‟ (contextual narrative, personal narrative, template analysis and evaluation) can be used to interpret respondents‟ accounts. It is found that narratives can provide a meaningful description of events and experiences through time and go some way to encourage an informed consideration of alternative approaches to the positivist research dominating the IS domain. Critical reflections of narrative analysis are also provided in the paper.