Latent variable modeling in heterogeneous populations

Common applications of latent variable analysis fail to recognize that data may be obtained from several populations with different sets of parameter values. This article describes the problem and gives an overview of methodology that can address heterogeneity. Artificial examples of mixtures are given, where if the mixture is not recognized, strongly distorted results occur. MIMIC structural modeling is shown to be a useful method for detecting and describing heterogeneity that cannot be handled in regular multiple-group analysis. Other useful methods instead take a random effects approach, describing heterogeneity in terms of random parameter variation across groups. These random effects models connect with emerging methodology for multilevel structural equation modeling of hierarchical data. Examples are drawn from educational achievement testing, psychopathology, and sociology of education. Estimation is carried out by the LISCOMP program.Presidential address delivered at the Psychometric Society meetings in Los Angeles, USA and Leuven, Belgium, July 1989. The research was supported by Grant No. SES-8821668 from the National Science Foundation and by Grant No. OERI-G-86-003 from the Office for Educational Research and Improvement, Department of Education. I thank Leigh Burstein, Mike Hollis, Linda Muthén, and Albert Satorra for helpful discussions and Tammy Tam, Jin-Wen Yang, Suk-Woo Kim, and Lynn Short for computational assistance. Designs were created by Arlette Collier, Rita Ling and Jennifer Edic-Bryant.     

The impact of adjacent-dependencies and staged-input on the learnability of center-embedded hierarchical structures

A theoretical debate in artificial grammar learning (AGL) regards the learnability of hierarchical structures. Recent studies using an AⁿBⁿ grammar draw conflicting conclusions (Bahlmann and Friederici, 2006 and [De Vries et al., 2008] ). We argue that 2 conditions crucially affect learning AⁿBⁿ structures: sufficient exposure to zero-level-of-embedding (0-LoE) exemplars and a staged-input. In 2 AGL experiments, learning was observed only when the training set was staged and contained 0-LoE exemplars. Our results might help understanding how natural complex structures are learned from exemplars.     

Recovering a Probabilistic Knowledge Structure by Constraining its Parameter Space

In the Basic Local Independence Model (BLIM) of Doignon and Falmagne (Knowledge Spaces, Springer, Berlin, 1999), the probabilistic relationship between the latent knowledge states and the observable response patterns is established by the introduction of a pair of parameters for each of the problems: a lucky guess probability and a careless error probability. In estimating the parameters of the BLIM with an empirical data set, it is desirable that such probabilities remain reasonably small. A special case of the BLIM is proposed where the parameter space of such probabilities is constrained. A simulation study shows that the constrained BLIM is more effective than the unconstrained one, in recovering a probabilistic knowledge structure.     

Structural Realism, Scientific Change, and Partial Structures

Scientific change has two important dimensions: conceptual change and structural change. In this paper, I argue that the existence of conceptual change brings serious difficulties for scientific realism, and the existence of structural change makes structural realism look quite implausible. I then sketch an alternative account of scientific change, in terms of partial structures, that accommodates both conceptual and structural changes. The proposal, however, is not realist, and supports a structuralist version of van Fraassen’s constructive empiricism (structural empiricism).     

Angel or demon? Self-monitoring differences in the mental representations of current versus former romantic partners

We investigated whether high and low self-monitors had (a) segregated/integrated and (b) uniformly favorable (angelic)/uniformly unfavorable (demonic) mental representations of actual romantic partners. Self-monitoring was assessed using the 25-item Self-Monitoring Scale and the structure of mental representations was calculated using a modified segregation/integration measure. In Study 1, low self-monitors were more likely than high self-monitors to have (a) segregated and (b) disproportionally favorable mental representations of their current romantic partners. In Study 2, low self-monitors were more likely than high self-monitors to have (a) segregated and (b) generally unfavorable mental representations of their former romantic partners. Self-monitoring differences were not moderated in either study by relationship longevity or conflict.     

Presence of ε-martensite as an intermediate phase during the strain-induced transformation of SUS304 stainless steel

We have investigated the formation process of α′-martensite from the γ-phase induced by external strain using in situ synchrotron diffraction experiments, combined with Lorentz transmission electron microscopy (TEM) and high-resolution TEM observations. It is clearly demonstrated that ε-martensite with hexagonal symmetry appears as an intermediate structure during the plastic deformation of SUS304 stainless steel. In addition to stacking faults and dislocations, interfaces between the twin structures presumably play a key role in the formation of ε-martensite.