This book is an extensive survey and critical examination of the literature on the use of expert opinion in scientific inquiry and policy making. The elicitation, representation, and use of expert opinion is increasingly important for two reasons: advancing technology leads to more and more complex decision problems, and technologists are turning in greater numbers to "expert systems" and other similar artifacts of artificial intelligence. Cooke here considers how expert opinion is being used today, how an expert's uncertainty is or (...) should be represented, how people do or should reason with uncertainty, how the quality and usefulness of expert opinion can be assessed, and how the views of several experts might be combined. He argues for the importance of developing practical models with a transparent mathematic foundation for the use of expert opinion in science, and presents three tested models, termed "classical," "Bayesian," and "psychological scaling." Detailed case studies illustrate how they can be applied to a diversity of real problems in engineering and planning. (shrink)

The claims of randomized controlled trials to be the gold standard rest on the fact that the ideal RCT is a deductive method: if the assumptions of the test are met, a positive result implies the appropriate causal conclusion. This is a feature that RCTs share with a variety of other methods, which thus have equal claim to being a gold standard. This article describes some of these other deductive methods and also some useful non-deductive methods, including the hypothetico-deductive method. (...) It argues that with all deductive methods, the benefit that the conclusions follow deductively in the ideal case comes with a great cost: narrowness of scope. This is an instance of the familiar trade-off between internal and external validity. RCTs have high internal validity but the formal methodology puts severe constraints on the assumptions a target population must meet to justify exporting a conclusion from the test population to the target. The article reviews one such set of assumptions to show the kind of knowledge required. The overall conclusion is that to draw causal inferences about a target population, which method is best depends case-by-case on what background knowledge we have or can come to obtain. There is no gold standard. (shrink)

In “The Toolbox of Science” (1995) together with Towfic Shomar we advocated a form of instrumentalism about scientific theories. We separately developed this view further in a number of subsequent works. Steven French, James Ladyman, Otavio Bueno and Newton Da Costa (FLBD) have since written at least eight papers and a book criticising our work. Here we defend ourselves. First we explain what we mean in denying that models derive from theory – and why their failure to do so should (...) be lamented. Second we defend our use of the London model of superconductivity as an example. Third we point out both advantages and weaknesses of FLBD’s techniques in comparison to traditional Anglophone versions of the semantic conception. Fourth we show that FLBD’s version of the semantic conception has not been applied to our case study. We conclude by raising doubts about FLBD’s overall project. (shrink)

A new, social epistemology of science that addresses practical as well as theoretical concerns.

Most traditional epistemologists see trust and knowledge as deeply antithetical: we cannot know by trusting in the opinions of others; knowledge must be based on evidence, not mere trust. I argue that this is badly mistaken. Modern knowers cannot be independent and self-reliant. In most disciplines, those who do not trust cannot know. Trust is thus often more epistemically basic than empirical evidence or logical argument, for the evidence and the argument are available only through trust. Finally, since the reliability (...) of testimonial evidence depends on the trustworthiness of the testifier, this implies that knowledge often rests on a foundation of ethics. The rationality of many of our beliefs depends not only on our own character, but on the character of others. (shrink)

We call for a new philosophical conception of models in physics. Some standard conceptions take models to be useful approximations to theorems, that are the chief means to test theories. Hence the heuristics of model building is dictated by the requirements and practice of theory-testing. In this paper we argue that a theory-driven view of models can not account for common procedures used by scientists to model phenomena. We illustrate this thesis with a case study: the construction of one of (...) the first comprehensive model of superconductivity by London brothers in 1934. Instead of theory-driven view of models, we suggest a phenomenologically-driven one. (shrink)