Estimation of the hypothesis hierarchy in probabilistic inference tasks*

Is there a hierarchical order among the hypotheses about functional rules in probabilistic inference tasks, i.e. what is the construction and the procedure of the “hypothesis sampling mechanism” employed by the subjects in this kind of task? According to the hypothesis sampling model initially proposed by Brehmer (1974) there should be a hierarchical order among the hypotheses in the subject's hypothesis pools. The procedures of hypothesis sampling and testing ought to follow this strict data independent order (see e.g. Sniezek, 1986; Brehmer, 1987). Knez (1991a, b) showed, however, that this assumption may be incorrect. As a follow up to these results the question regarding the construction of the subject's hypothesis pools was reapproached in the present study. The results indicated a consistency with the hierarchical assumption (Brehmer, 1974) only regarding the relation between the linear and nonlinear rules but not within these types of rules.     

The transitivity of choices between different response requirements

This experiment tested the transitivity of hens' choices between response requirements differing in both form and number. In a concurrent second-order schedule procedure, 6 hens chose between two alternatives by making either key-peck or door-push responses. The reinforcement rates on the two alternatives remained constant and equal throughout conditions, but the number of responses (i.e., key pecks or door pushes) required on each alternative was varied by changing the second-order (fixed-ratio) requirements. The preferences obtained from two pairings of response requirements allowed prediction of the preferences expected in a third pairing. No intransitivities were found, implying that the response requirements lie on a common unitary scale of value. For response-based measures, the obtained preferences varied evenly around perfect, multiplicative prediction, and all satisfied strong transitivity, implying an underlying interval scale of value. For time-based measures, only moderate transitivity was satisfied, implying only an ordinal scale of value. Time-based measures were confounded with the differing times taken to complete each response requirement. The existence of such scales indicates that direct comparisons of different response requirements may be possible.     

On Keats' generalization of the rasch model

Parameter estimation for Keats generalization of the Rasch model that takes account of guessing behavior is investigated. It is shown that no minimal sufficient statistics for the ability parameters independent of the difficulty parameters exist. Thus Andersen's conditional inference technique for consistent estimation is not applicable to Keats' model. The notion of separability of the parameters is generalized.     

On the sampling interpretation of confidence intervals and hypothesis tests in the context of conditional maximum likelihood estimation

In the context ofconditional maximum likelihood (CML) estimation, confidence intervals can be interpreted in three different ways, depending on the sampling distribution under which these confidence intervals contain the true parameter value with a certain probability. These sampling distributions are (a) the distribution of the data given theincidental parameters, (b) the marginal distribution of the data (i.e., with the incidental parameters integrated out), and (c) the conditional distribution of the data given the sufficient statistics for the incidental parameters. Results on the asymptotic distribution of CML estimates under sampling scheme (c) can be used to construct asymptotic confidence intervals using only the CML estimates. This is not possible for the results on the asymptotic distribution under sampling schemes (a) and (b). However, it is shown that theconditional asymptotic confidence intervals are also valid under the other two sampling schemes. I am indebted to Theo Eggen, Norman Verhelst and one of Psychometrika's reviewers for their helpful comments.     

Visual analysis of single-case time series: Effects of variability, serial dependence, and magnitude of intervention effects

Visual analysis is the dominant method of analysis for single-case time series. The literature assumes that visual analysts will be conservative judges. We show that previous research into visual analysis has not adequately examined false alarm and miss rates or the effect of serial dependence. In order to measure false alarm and miss rates while varying serial dependence, amount of random variability, and effect size, 37 students undertaking a postgraduate course in single-case design and analysis were required to assess the presence of an intervention effect in each of 27 AB charts constructed using a first-order autoregressive model. Three levels of effect size and three levels of variability, representative of values found in published charts, were combined with autocorrelation coefficients of 0, 0.3 and 0.6 in a factorial design. False alarm rates were surprisingly high (16% to 84%). Positive autocorrelation and increased random variation both significantly increased the false alarm rates and interacted in a nonlinear fashion. Miss rates were relatively low (0% to 22%) and were not significantly affected by the design parameters. Thus, visual analysts were not conservative, and serial dependence did influence judgment.     

中文故事阅读中预期与前后向推理的关系

通过3项实验,考察了中文故事阅读中前后向推理的差异及其与预期的关系。采用3×2独立设计,以反应时为指标,以较长的语篇为实验材料,分别利用核证法与命名法进行了实验一和二。实验三在实验二的基础上,用2×2独立设计,并根据实验目的修改了实验材料。实验一的结果显示,前向推理和后向推理差异显著;实验二的结果则是前向推理和后向推理无显著差异,而且预期的3个水平在前后向推理上均无显著差异;实验三的结果表明,在预期与前后向推理间距离近和预期句详述的情况下,预期与前后向推理产生了交互作用     

Sampling assumptions in inductive generalization

Inductive generalization, where people go beyond the data provided, is a basic cognitive capability, and it underpins theoretical accounts of learning, categorization, and decision making. To complete the inductive leap needed for generalization, people must make a key 'sampling' assumption about how the available data were generated. Previous models have considered two extreme possibilities, known as strong and weak sampling. In strong sampling, data are assumed to have been deliberately generated as positive examples of a concept, whereas in weak sampling, data are assumed to have been generated without any restrictions. We develop a more general account of sampling that allows for an intermediate mixture of these two extremes, and we test its usefulness. In two experiments, we show that most people complete simple one-dimensional generalization tasks in a way that is consistent with their believing in some mixture of strong and weak sampling, but that there are large individual differences in the relative emphasis different people give to each type of sampling. We also show experimentally that the relative emphasis of the mixture is influenced by the structure of the available information. We discuss the psychological meaning of mixing strong and weak sampling, and possible extensions of our modeling approach to richer problems of inductive generalization.     

The case for a dual-process theory of transitive reasoning

Ever since its popularisation by Piaget around 60 years ago, transitive reasoning (deductively-inferring A > C from premises A > B and B > C) has been of psychological interest both as a mental phenomenon and as a tool in areas of psychological discourse. However, the focus of interest in it has shifted periodically first from child development, to learning disability, to non-humans and currently to cognitive and clinical neuroscience. Crucially, such shifts have always been plagued by one core question – the question of which of two competing paradigms (extensive-training paradigm versus non-training paradigm) is valid for assessing transitive reasoning as originally conceived in Piagetian research. The continued avoidance of this question potentially undermines several important findings recently reported: Such as about exactly what is involved in deducing transitive inferences, which brain regions are critical for reaching transitive inference, and what links exist between weakened deductive transitivity and mental illnesses like schizophrenia. Here, we offer the view that both of the competing paradigms are indexing transitivity, but each one tends to tap a different aspect of it. Then, we summarise studies from child and adult cognitive psychology, disabilities research, and from cognitive neuroscience. These, together with studies of non-human reasoning, seem to afford a theory of transitive reasoning that has two major components; one deductive but the other associative. It is proposed that only a dual-process theory of transitivity (having analytic versus intuitive routes approximate to deductive versus associative processing respectively) can account both for the variety of findings and the apparently-disparate paradigms. However, fuzzy-trace theory (“Gist” processes and representations), if not already embodying such a dual-process theory, will need to be incorporated into any complete theory.