Prediction and classification in nonlinear data analysis: Something old,something new,something borrowed,something blue

Prediction and classification are two very active areas in modern data analysis. In this paper, prediction with nonlinear optimal scaling transformations of the variables is reviewed, and extended to the use of multiple additive components, much in the spirit of statistical learning techniques that are currently popular, among other areas, in data mining. Also, a classification/clustering method is described that is particularly suitable for analyzing attribute-value data from systems biology (genomics, proteomics, and metabolomics), and which is able to detect groups of objects that have similar values on small subsets of the attributes.This article is based on the Presidential Address Jacqueline Meulman gave on July 9, 2003 at the 68th Annual Meeting of the Psychometric Society held near Cagliari, Italy on the island of Sardinia.—Editor     

Colour-cueing in visual search

Several studies have shown that people can selectively attend to stimulus colour, e.g., in visual search, and that preknowledge of a target colour can improve response speed/accuracy. The purpose was to use a form-identification task to determine whether valid colour precues can produce benefits and invalid cues costs. The subject had to identify the orientation of a "T"-shaped element in a ring of randomly-oriented "L"s when either two or four of the elements were differently coloured. Contrary to Moore and Egeth's (1998) recent findings, colour-based attention did affect performance under data-limited conditions: Colour cues produced benefits when processing load was high; when the load was reduced, they incurred only costs. Surprisingly, a valid colour cue succeeded in improving performance in the high-load condition even when its validity was reduced to the chance level. Overall, the results suggest that knowledge of a target colour does not facilitate the processing of the target, but makes it possible to prioritize it.     

Factor copula models for mixed data

We develop factor copula models to analyse the dependence among mixed continuous and discrete responses. Factor copula models are canonical vine copulas that involve both observed and latent variables, hence they allow tail, asymmetric and nonlinear dependence. They can be explained as conditional independence models with latent variables that do not necessarily have an additive latent structure. We focus on important issues of interest to the social data analyst, such as model selection and goodness of fit. Our general methodology is demonstrated with an extensive simulation study and illustrated by reanalysing three mixed response data sets. Our studies suggest that there can be a substantial improvement over the standard factor model for mixed data and make the argument for moving to factor copula models.     

Some Behaviorial Science Measurement Concerns and Proposals

Primarily from a measurement standpoint, we question some basic beliefs and procedures characterizing the scientific study of human behavior. The relations between observed and unobserved variables are key to an empirical approach to building explanatory theories and we are especially concerned about how the former are used as proxies for the latter. We believe that behavioral science can profitably reconsider the prevailing version of this arrangement because of its vulnerability to limiting idiosyncratic aspects of observed/unobserved variable relations. We describe a general measurement approach that takes into account idiosyncrasies that should be irrelevant to the measurement process but can intrude and may invalidate it in ways that distort and weaken relations among theoretically important variables. To clarify further our major concerns, we briefly describe one version of the measurement approach that fundamentally supports the individual as the primary unit of analysis orientation that we believe should be preeminent in the scientific study of human behavior.     

Cooperative responding in rats maintained by fixed‐ and variable‐ratio schedules

The present study investigated the effects of fixed‐ratio (FR) and variable‐ratio (VR) reinforcement schedules on patterns of cooperative responding in pairs of rats. Experiment 1 arranged FR 1, FR 10, and VR 10 schedules to establish cooperative responding (water delivery depended on the joint responding of two rats). Cooperative response rates and proportions were higher under intermittent schedules than under continuous reinforcement. The FR 10 schedule generated a break‐and‐run pattern, whereas the VR 10 schedule generated a relatively high and constant rate pattern. Experiment 2 evaluated the effects of parametric manipulations of FR and VR schedules on cooperative responding. Rates and proportions of cooperative responding generally increased between ratio sizes of 1 and 5 but showed no consistent trend as the ratio increased from 5 to 10. Experiment 3 contrasted cooperative responding between an FR6 schedule and a yoked control schedule. Coordinated behavior occurred at a higher rate under the former schedule. The present study showed that external consequences and the schedules under which the delivery of these consequences are based, select patterns of coordinated behavior.     

A new variable interval schedule with constant hazard rate and finite time range

We propose a new variable interval (VI) schedule that achieves constant probability of reinforcement in time while using a bounded range of intervals. By sampling each trial duration from a uniform distribution ranging from 0 to 2 T seconds, and then applying a reinforcement rule that depends linearly on trial duration, the schedule alternates reinforced and unreinforced trials, each less than 2 T seconds, while preserving a constant hazard function.     

An Introduction to Network Psychometrics: Relating Ising Network Models to Item Response Theory Models

In recent years, network models have been proposed as an alternative representation of psychometric constructs such as depression. In such models, the covariance between observables (e.g., symptoms like depressed mood, feelings of worthlessness, and guilt) is explained in terms of a pattern of causal interactions between these observables, which contrasts with classical interpretations in which the observables are conceptualized as the effects of a reflective latent variable. However, few investigations have been directed at the question how these different models relate to each other. To shed light on this issue, the current paper explores the relation between one of the most important network models—the Ising model from physics—and one of the most important latent variable models—the Item Response Theory (IRT) model from psychometrics. The Ising model describes the interaction between states of particles that are connected in a network, whereas the IRT model describes the probability distribution associated with item responses in a psychometric test as a function of a latent variable. Despite the divergent backgrounds of the models, we show a broad equivalence between them and also illustrate several opportunities that arise from this connection.     

Item Randomized-Response Models for Measuring Noncompliance: Risk-Return Perceptions,Social Influences,and Self-Protective Responses

Randomized response (RR) is a well-known method for measuring sensitive behavior. Yet this method is not often applied because: (i) of its lower efficiency and the resulting need for larger sample sizes which make applications of RR costly; (ii) despite its privacy-protection mechanism the RR design may not be followed by every respondent; and (iii) the incorrect belief that RR yields estimates only of aggregate-level behavior but that these estimates cannot be linked to individual-level covariates. This paper addresses the efficiency problem by applying item randomized-response (IRR) models for the analysis of multivariate RR data. In these models, a person parameter is estimated based on multiple measures of a sensitive behavior under study which allow for more powerful analyses of individual differences than available from univariate RR data. Response behavior that does not follow the RR design is approached by introducing mixture components in the IRR models with one component consisting of respondents who answer truthfully and another component consisting of respondents who do not provide truthful responses. An analysis of data from two large-scale Dutch surveys conducted among recipients of invalidity insurance benefits shows that the willingness of a respondent to answer truthfully is related to the educational level of the respondents and the perceived clarity of the instructions. A person is more willing to comply when the expected benefits of noncompliance are minor and social control is strong. The authors are grateful to the reviewers whose suggestions helped to improve the clarity of the paper substantially. The authors also wish to thank the Dutch Ministry of Social Affairs and Employment for making the reported data available. This research was supported in parts by grants from the Social Sciences and Humanities Research Council of Canada and the Canadian Foundation of Innovation.     

Categorical Ontology of Levels and Emergent Complexity: An Introduction

An overview of the following three related papers in this issue presents the Emergence of Highly Complex Systems such as living organisms, man, society and the human mind from the viewpoint of the current Ontological Theory of Levels. The ontology of spacetime structures in the Universe is discussed beginning with the quantum level; then, the striking emergence of the higher levels of reality is examined from a categorical—relational and logical viewpoint. The ontological problems and methodology aspects discussed in the first two papers are followed by a rigorous paper based on Category Theory, Algebraic Topology and Logic that provides a conceptual and mathematical basis for a Categorical Ontology Theory of Levels. The essential links and relationships between the following three papers of this issue are pointed out, and further possible developments are being considered.     

罗夏测验在西方近10年的最新发展

近10年来, 罗夏综合系统不断发展, 新增了XA%与WDA%、知觉−思维指数PTI、GHR:PHR等多个指标, 修改了8个群变量, 删除了精神分裂SCZI指标。这些新调整虽然不是本质性的, 但使得罗夏综合系统内容更加完善, 信度和效度不断提高, 更加精确化和标准化, 成为西方不可或缺的心理测验工具。尽管罗夏综合系统不断发展, 但仍然存在着操作过于复杂、功能还需要进一步完善等问题。罗夏综合系统作为一个代表性的投射测验, 与其它客观测验组成了一个完整的心理测量体系, 会发挥越来越大的作用。