An Introduction to Model Selection

This paper is an introduction to model selection intended for nonspecialists who have knowledge of the statistical concepts covered in a typical first (occasionally second) statistics course. The intention is to explain the ideas that generate frequentist methodology for model selection, for example the Akaike information criterion, bootstrap criteria, and cross-validation criteria. Bayesian methods, including the Bayesian information criterion, are also mentioned in the context of the framework outlined in the paper. The ideas are illustrated using an example in which observations are available for the entire population of interest. This enables us to examine and to measure effects that are usually invisible, because in practical applications only a sample from the population is observed. The problem of selection bias, a hazard of which one needs to be aware in the context of model selection, is also discussed. Copyright 2000 Academic Press.     

Karl Jaspers’ account of truth as a way into the discussion of theological truth-claims

This paper presents Karl Jaspers understanding of truth as communication as a framework for reflecting on the nature of truth-claims in Christian theology. Jaspers argues that the fact that we communicate with each other in several different modes implies that the criteria of truth in our discourse must vary in these different modes. In developing this view he distinguishes between four modes of communication: the mode of presenting and defending vital personal interests, the mode of common understanding of the observable world, the mode of developing and operating with ideas of unifying spiritual wholeness, and the mode of authentic personal identity. The formation of this framework draws heavily on Kant. His discussion of the spiritual ideas for example clearly links with Kant regulative ideas of reason. Yet where Kant seems to limit thwese ideas to three: the self, the world and God, Jaspers seems to offer a more open and indefinite view. This becomes important for making a comparison between his account of truth and an account which could accommodate claims of the Christian thelogians.     

A Theoretical Framework for Analysing the Notion of Relative Importance of Criteria

Multiple-criteria decision aid almost always requires the use of weights, importance coefficients or even a hierarchy of criteria, veto thresholds, etc. These are importance parameters that are used to differentiate the role devoted to each criterion in the construction of comprehensive preferences. Many researchers have studied the problem of how to assign values to such parameters, but few of them have tried to analyse in detail what underlies the notion of importance of criteria and to give a clear formal definition of it. In this paper our purpose is to define a theoretical framework so as to analyse the notion of the importance of criteria under very general conditions. Within this framework it clearly appears that the importance of criteria is taken into account in very different ways in various aggregation procedures. This framework also allows us to shed new light on fundamental questions such as: Under what conditions is it possible to state that one criterion is more important than another? Are importance parameters of the various aggregation procedures dependent on or independent of the encoding of criteria? What are the links between the two concepts of the importance of criteria and the compensatoriness of preferences? This theoretical framework seems to us sufficiently general to ground further research in order to define theoretically valid elicitation methods for importance parameters.     

A commentary on Rönnberg's distinction between perception and cognition

In a commentary on a note by Rönnberg (Rönnberg, J. On the distinction between perception and cognition. Scandinavian Journal of Psychology , 1990, 31 , 154–156), it is argued that one of Rönnberg's criteria for theoretically distinguishing perception from cognition, that of different biological purposes, is invalid. Congruent with a broad definition of perception and cognition which most researchers agree upon, Rönnberg's two other criteria essentially state that how internally represented information is processed distinguishes between perception and cognition. However, the more strict criterion of whether explicit retrieval of information from memory is necessary is too dependent on a particular, rather limited theoretical framework. A third, less theory-dependent criterion of whether the information available in the stimulus is sufficient to account for comprehension may be useful in research which investigates hypotheses about similarities between perception and cognition.     

Passionate Yearning Theory as a Theory of Meaning in Life

In this paper, I offer an original account of meaning in life, which I call the passionate yearning theory. Within the framework of the passionate yearning theory, meaning is understood as the intrinsically derived yearning, and passionate striving, for something (an ideal, or a state of affairs) that possesses some plausible objective claim to truth or facticity, which makes it worth pursuing for its own sake. To properly delineate the view, I present the various criteria that serve as the foundation for the passionate yearning view. These include the truth/facticity criterion, the lack of immorality, intrinsic subjectivity, passion, yearning and striving. I then show how these criteria coalesce into the passionate yearning theory and how exactly the theory works. Finally, I motivate the passionate yearning theory by addressing some possible criticisms and objections that can be raised against the view and also differentiate it from similar competing views.

     

Gender stereotyping and decision processes: extending and reversing the gender bias in fame judgments

M. R. Banaji and A. G. Greenwald (1995) demonstrated a gender bias in fame judgments--that is, an increase in judged fame due to prior processing that was larger for male than for female names. They suggested that participants shift criteria between judging men and women, using the more liberal criterion for judging men. This "criterion-shift" account appeared problematic for a number of reasons. In this article, 3 experiments are reported that were designed to evaluate the criterion-shift account of the gender bias in the false-fame effect against a distribution-shift account. The results were consistent with the criterion-shift account, and they helped to define more precisely the situations in which people may be ready to shift their response criterion on an item-by-item basis. In addition, the results were incompatible with an interpretation of the criterion shift as an artifact of the experimental situation in the experiments reported by M. R. Banaji and A. G. Greenwald.     

Beyond Reasonable Doubt – a paradox of ideological immunity

Abstract

Ideology criticism, like scepticism, calls into question the objective or justified status of beliefs. However, where scepticism only refutes, and never puts forward, a substantive claim about anything, the ideology critic must maintain some criterion for distinguishing ideas which support relations of domination from those that do not, in virtue of her criticism of a particular set of ideas as “ideological”. The trouble for the ideology critic is that the sceptical methods she deploys undermine any critical thesis, including her own. Thus, the theory of ideology tends to undercut ideology criticism with a fundamental problem of self-implication.

This paper draws on the epistemological problem of the criterion to explain and define a basic problem of justification for the theory of ideology. A problem of self-implication is introduced in part one. I argue that the basis for ideology criticism inevitably succumbs to the very doubt it puts forward. I draw on various criticisms of ideology criticism to formulate a specific account of the basic, fundamental problem for the theory of ideology. I show how norms for ideology criticism are vulnerable to an Ancient sceptical problem for epistemic criteria, which brings the ideology critic to a dilemma: either (i) find independent grounds for criticism, immune to ideology, or (ii) show how ideology is self-undermining. Each horn of the dilemma is ideological.     

On the measurement of criterion noise in signal detection theory: the case of recognition memory

Traditional approaches within the framework of signal detection theory (SDT; Green & Swets, 1966), especially in the field of recognition memory, assume that the positioning of response criteria is not a noisy process. Recent work (Benjamin, Diaz, & Wee, 2009; Mueller & Weidemann, 2008) has challenged this assumption, arguing not only for the existence of criterion noise but also for its large magnitude and substantive contribution to individuals' performance. A review of these recent approaches for the measurement of criterion noise in SDT identifies several shortcomings and confoundings. A reanalysis of Benjamin et al.'s (2009) data sets as well as the results from a new experimental method indicate that the different forms of criterion noise proposed in the recognition memory literature are of very low magnitudes, and they do not provide a significant improvement over the account already given by traditional SDT without criterion noise.     

Subsumption and Relative Identity

This paper is a modification of Nicola Guarino and Christopher Welty's conception of the subsumption relation. Guarino and Welty require that that whether one property may subsume the other should depend on the modal metaproperties of those properties. I argue that the part of their account that concerns the metaproperty carrying a criterion of identity is essentially flawed. Subsequently, I propose to constrain the subsumption relation not, as Guarino and Welty require, by means of incompatible criteria of absolute identity but by means of incompatible criteria of relative identity. After discussing the benefits of applying relative identity in ontological investigations I provide a formal framework in which to prove a counterpart of the identity criteria constraint.This revised version was published online in October 2005 with corrections to the Cover Date.     

In defense of the signal detection interpretation of remember/know judgments

Donaldson (1996) argued that remember/know judgments can be conceptualized within a signal detection framework by assuming that they are based on two criteria situated along a strength-of-memory decision axis. According to this model, items that exceed a high criterion receive a remember response, whereas items that only exceed a lower criterion receive a know response. Although a variety of findings have been presented in evidence against this idea, Dunn (2004) recently showed that detection theory is fully compatible with those findings. We present a variety of new results and new analyses that weigh strongly in favor of the detection interpretation. We further show that a dual-process account of recognition memory is compatible with a unidimensional detection model despite the common notion that such a model necessarily assumes a single process. The key assumption of this model is that individual recognition decisions are based on both recollection and familiarity (not on one process or the other).     

Michael Polanyi, Tacit Cognitive Relativist

Celebrated as a theorist of science, and a source of stimulating ideas for theologians and philosophers of religion, Michael Polanyi explicitly denied cognitive relativism. Yet cognitive relativism, this paper suggests, is implied by Polanyi's account of conceptual frameworks and intellectual controversies.
In ' The Stability of Beliefs ' (1952) Polanyi understands conceptual frameworks (science, psychoanalysis, Azande witchcraft, Marxism) as embedded in, and as expressed in the use of, their own languages. The language-with-theory limits the range of discussable subjects, interprets relevant facts in its own terms, permits only certain questions to be asked, with answers to these questions serving to confirm the framework.
In Polanyi's masterwork, Personal Knowledge (1958), these ideas inform his discussion of controversies over scientific frameworks and frameworks vying to become part of science. In each controversy, frameworks are logically disconnected, Polanyi foreshadowing the incommensurability thesis
I argue that Polanyi's ideas satisfy recognised criteria of cognitive relativism. Perception is undetermined by objects and conditioned by language. Empirical propositions, in Polanyi's view, are accepted as true only within a conceptual framework. Polanyi regards supporters of logically disconnected frameworks as thinking differently, living in different worlds, speaking different languages and as experiencing communication failure. There is no framework-independent argument or evidence to distinguish any framework as the best available approximation to the truth. Frameworks are logically disconnected and incommensurable.     

The simplicity of theories: Its degree and form

Almost all commentators acknowledge that among the grounds on which scientists perform theory-choices are criteria of simplicity. In general, simplicity is regarded either as only a logico-empirical quality of a theory, diagnostic of the theory's future predictive success, or as a purely aesthetic or otherwise extra-empirical property of it. This paper attempts to demonstrate that the simplicity-criteria applied in scientific practice include both a logicoempirical and a quasi-aesthetic criterion: to conflate these in an account of scientists' theory-choice is to court confusion.     

Diagnosing agoraphobia in the context of panic disorder: examining the effect of DSM-IV criteria on diagnostic decision-making

A diagnostic and statistical manual (DSM)-IV diagnosis of agoraphobia in the context of panic disorder (PD) is based on three nosologically sufficient criteria: (1) avoidance, (2) use of companions, and (3) endurance of situations despite distress. Therefore, an agoraphobia diagnosis can be made across an extremely broad range of cases including when there are no avoidance behaviors (e.g., the patient endures the situation). It was hypothesized that clinicians do not weight these criteria equally and that the DSMs individual, sufficient criteria lead to poor inter-rater reliability. Clinicians (N=48) rated hypothetical patients with symptom profiles emphasizing each of these three criteria. Consistent with expectation, clinicians differentially weighted these criteria. Avoidance was relatively more apt to produce a diagnosis when only one criterion was emphasized in clinical vignettes. Inter-rater reliability was poor in instances when only one sufficient criterion was highlighted. Knowledge concerning DSM criteria resulted in a greater rate of agoraphobia endorsement, but knowledge did not account for the overall pattern of findings.     

Enactive subjectivity as flesh

Maurice Merleau-Ponty’s philosophy of embodiment has been widely adopted by enactivists seeking to provide an account of cognition that is both embodied and embedded. Yet very little attention has been paid to Merleau-Ponty’s later works. This is troubling given that in The Visible and the Invisible Merleau-Ponty revises his conception of embodied subjectivity because he came to the realization that understanding consciousness through the concepts of subject and object imposed a dualistic framework that he was trying to escape. To overcome this dichotomy Merleau-Ponty more fully develops the radically embodied ontology implicit in his earlier work by introducing the concept of flesh. I argue that the enactive account of subjectivity would be improved by “giving flesh” to the enactive subject, given that the enactive account of subjectivity as grounded in pre-reflective bodily self-consciousness is ultimately rooted in accounts of which the later Merleau-Ponty is critical. Incorporating flesh resolves the underlying problems with the enactive account of subjectivity and makes the account more consistent with the ontological commitments to embodiment and embeddedness.     

Meaning(fullness) Without Metaphysics: Another Look at Hume’s “Meaning Empiricism”

Although Hume has no developed semantic theory, in the heyday of analytic philosophy he was criticized for his “meaning empiricism,” which supposedly committed him to a private world of ideas, led him to champion a genetic account of meaning instead of an analytic one, and confused “impressions” with “perceptions of an objective realm.” But another look at Hume’s “meaning empiricism” reveals that his criterion for cognitive content, the cornerstone both of his resolutely anti-metaphysical stance and his naturalistic “science of human nature,” provides the basis for a successful response to his critics. Central to his program for reforming philosophy, Hume’s use of the criterion has two distinct aspects: a critical or negative aspect, which assesses the content of the central notions of metaphysical theories to demonstrate their unintelligibility; and a constructive or positive aspect, which accurately determines the cognitive content of terms and ideas.     

Reasoning with Factors

The paper proposes an analysis and a formalisation of factor-based reasoning. After examining the relevance of factors in legal reasoning, binary and scalable factors (dimensions) are distinguished and the relations between them are discussed. An account of a fortiori reasoning with both types of factors is developed. This article reports ideas which are discussed and developed in Sartor (2005). We refer to the latter work for the theoretical framework in which our analysis of factors is embedded.     

Hume's Dual Criteria for Memory

In his brief treatment of memory, Hume characterizes memory using two kinds of criteria: ideas' phenomenal character and their correspondence to the past experiences from which they derived. These criteria have seemed so perplexing to interpreters, both individually and jointly, that Hume's account of memory is commonly considered one of the weakest parts of his philosophical system. This paper defends Hume's criteria by showing that they achieve two theoretical aims: a scientific classification of ideas and a definition of ‘memory.’ In particular, I argue that Hume's definition of ‘memory’ is cogent in light of Putnamian considerations about definitions.     

Is Hume's shade of blue a red herring?

The existence of an idea of a missing shade of blue contradicts Hume's first principle that simple ideas all derive from corresponding simple impressions. Hume dismisses the ‘exception’ to his principle as unimportant. Why does he do so? His later account of distinctions of reason suggests a systematic way of dealing with simple ideas not derived from simple impressions. Why does he not return to the problem of the missing shade, having offered that account? Several suggestions as to Hume's solution of the problem of the missing shade (not all appealing to distinctions of reason) are explored with an eye both to their adequacy as Humean solutions and their value as clues to his dismissal of the problem. Hypotheses concerning the latter perplexity are formulated and discussed as well. Senses in which the missing shade of blue is or may be a red herring are identified. In course, this author names Hume's missing shade ‘marjorie grene’. Historians of philosophy will want to adopt this nomenclature.