Laplace once argued that if one could “comprehend all the forces by which nature is animated,” it would be possible to predict the future and explain the past. The advent of analysis of large-scale data sets has been accompanied by newfound concerns about “Laplace’s Demon” as it relates to certain fields of science as well as management, evaluation, and audit. I begin by asking how statistical data are constructed, illustrating the hermeneutic acts necessary to create a variable. These include attributing (...) a certain characteristic to a particular phenomenon, isolating the characteristic of interest, and assigning a value to it. In addition, a population must be identified and a sample must be “taken” from that population. Next, I examine how statistical analyses are conducted, examining the interpretive acts there as well. In each case, I show how big data add new challenges. I then show how statistics are incorporated into audits and evaluations, emphasizing how alternative interpretations are concealed in the audit process. I conclude by noting that these issues cannot be “resolved” as Laplace suggested. His Demon, already banished from physics, needs to be banished from other fields of science, management, audits, and evaluations as well. (shrink)

This paper discusses two senses in which a hypothesis may be said to unify evidence. One is the ability of the hypothesis to increase the mutual information of a set of evidence statements; the other is the ability of the hypothesis to explain commonalities in observed phenomena by positing a common origin for them. On Bayesian updating, it is only mutual information unification that contributes to the incremental support of a hypothesis by the evidence unified. This poses a challenge for (...) the view that explanation is a confirmatory virtue that contributes to such incremental support; its advocates must ground it in some relevant difference between humans and a Bayesian agent. (shrink)

It is argued in this paper that although much attention has been paid to causal chains and common causes within the literature on probabilistic causality, a primary virtue of that approach is its ability to deal with cases of multiple causation. In doing so some ways are indicated in which contemporary sine qua non analyses of causation are too narrow (and ways in which probabilistic causality is not) and an argument by Reichenbach designed to provide a basis for the asymmetry (...) of causation is refined. The importance of referring causal claims to an abstract model is also emphasized. (shrink)

For model-based frequentist statistics, based on a parametric statistical model ${{\cal M}_\theta }$, the trustworthiness of the ensuing evidence depends crucially on the validity of the probabilistic assumptions comprising ${{\cal M}_\theta }$, the optimality of the inference procedures employed, and the adequateness of the sample size to learn from data by securing –. It is argued that the criticism of the postdata severity evaluation of testing results based on a small n by Rochefort-Maranda is meritless because it conflates [a] misuses (...) of testing with [b] genuine foundational problems. Interrogating this criticism reveals several misconceptions about trustworthy evidence and estimation-based effect sizes, which are uncritically embraced by the replication crisis literature. (shrink)

Robert Merton's essays on theories of the middle range and his essays on functional explanation and the structural approach are among the most influential in the history of sociology. But their import is a puzzle. He explicitly allied himself with some of the most extreme scientistic formalists and contributed to and endorsed the Columbia model of theory construction. But Merton never responded to criticisms by Ernest Nagel of his arguments or acknowledged the rivalry between Lazarsfeld and Herbert Simon, rarely cited (...) the philosophical and methodological literature, and responded to critics with ambiguous concessions, leaving the Mertonian legacy profoundly ambiguous. Key Words: Robert Merton • Paul Lazarsfeld • theory construction • middle range theory • causal modeling • Émile Durkheim. (shrink)

Exploratory statistics represents the transformation of a realist theory of statistics held by early nineteenth-century astronomers into an empiricist theory of statistics held by biometricians at the turn of the twentieth century. This paper discusses four key ideas in empiricist thought that influenced the form exploratory statistics took: (1) Baconianism, (2) associationism, (3) the search for cognitive calculi, and (4) phenomenalism. Some limitations of and alternatives to exploratory statistics as a hypothesis-generating methodology are discussed.