A variable neighborhood search method for generalized blockmodeling of two-mode binary matrices

The clustering of two-mode proximity matrices is a challenging combinatorial optimization problem that has important applications in the quantitative social sciences. We focus on one particular type of problem related to the clustering of a two-mode binary matrix, which is relevant to the establishment of generalized blockmodels for social networks. In this context, clusters for the rows of the two-mode matrix intersect with clusters of the columns to form blocks, which should ideally be either complete (all 1s) or null (all 0s). A new procedure based on variable neighborhood search is presented and compared to an existing two-mode K-means clustering algorithm. The new procedure generally provided slightly greater explained variation; however, both methods yielded exceptional recovery of cluster structure.     

Constrained classification: The use of a priori information in cluster analysis

In many classification problems, one often possesses external and/or internal information concerning the objects or units to be analyzed which makes it appropriate to impose constraints on the set of allowable classifications and their characteristics. CONCLUS, or CONstrained CLUStering, is a new methodology devised to perform constrained classification in either an overlapping or nonoverlapping (hierarchical or nonhierarchial) manner. This paper initially reviews the related classification literature. A discussion of the use of constraints in clustering problems is then presented. The CONCLUS model and algorithm are described in detail, as well as their flexibility for use in various applications. Monte Carlo results are presented for two synthetic data sets with appropriate discussion of the resulting implications. An illustration of CONCLUS is presented with respect to a sales territory design problem where the objects classified are various Forbes-500 companies. Finally, the discussion section highlights the main contribution of the paper and offers some areas for future research.We wish to thank C. Mallows and J. D. Carroll for some helpful technical discussion and L. Clark and D. Art for their valuable computer assistance. We also wish to thank H. Pollak, R. Gnanadesikan, and J. Kettenring for their thorough reviews of a previous draft of this paper. Finally, we acknowledge helpful comments of the editor and two anonymous reviewers.     

A tabular method of obtaining tetrachoricr with median-cut variables

A method is presented that enables the immediate determination of tetrachoricr from a table if the proportion in the plus-plus cell for median-cut variables is known.     

Marginal mean weighting through stratification: a generalized method for evaluating multivalued and multiple treatments with nonexperimental data

Propensity score matching and stratification enable researchers to make statistical adjustment for a large number of observed covariates in nonexperimental data. These methods have recently become popular in psychological research. Yet their applications to evaluations of multi-valued and multiple treatments are limited. The inverse-probability-of-treatment weighting method, though suitable for evaluating multi-valued and multiple treatments, often generates results that are not robust when only a portion of the population provides support for causal inference or when the functional form of the propensity score model is misspecified. The marginal mean weighting through stratification (MMW-S) method promises a viable nonparametric solution to these problems. By computing weights on the basis of stratified propensity scores, MMW-S adjustment equates the pretreatment composition of multiple treatment groups under the assumption that unmeasured covariates do not confound the treatment effects given the observed covariates. Analyzing data from a weighted sample, researchers can estimate a causal effect by computing the difference between the estimated average potential outcomes associated with alternative treatments within the analysis of variance framework. After providing an intuitive illustration of the theoretical rationale underlying the weighting method for causal inferences, the article demonstrates how to apply the MMW-S method to evaluations of treatments measured on a binary, ordinal, or nominal scale approximating a completely randomized experiment; to studies of multiple concurrent treatments approximating factorial randomized designs; and to moderated treatment effects approximating randomized block designs. The analytic procedure is illustrated with an evaluation of educational services for English language learners attending kindergarten in the United States.     

Processing level and recognition: A search method for inducing alternative encodings of unrelated words

Twenty-four subjects viewed cards containing four words. In synonym orienting, half of the cards contained a synonym pair and half did not; in homophone orienting, half of the displays contained a homophone pair. The remaining two words in each display were used to index retention. During presentation of displays, subjects responded “yes” or “no” to indicate the presence or absence of a matching pair. Following presentation, a recognition test was administered. Half the items were tested early and half were tested late; within each test order, half the items appeared with context cues during testing and half appeared without. Results showed superior recognition (1) following semantic orienting, (2) for items tested early, (3) for items tested with context, and (4) for nonmatch displays requiring exhaustive item comparison. An Orienting by Test Cuing interaction showed that the presence of test cues improved recognition for homophone orienting items only. The interaction may have resulted from the lack of cuetarget associations and the reinstatement of the phonemic orienting set during the test.     

ConPar: a method for identifying groups of concordant subject proximity matrices for subsequent multidimensional scaling analyses

A common representation of data within the context of multidimensional scaling (MDS) is a collection of symmetric proximity (similarity or dissimilarity) matrices for each of M subjects. There are a number of possible alternatives for analyzing these data, which include: (a) conducting an MDS analysis on a single matrix obtained by pooling (averaging) the M subject matrices, (b) fitting a separate MDS structure for each of the M matrices, or (c) employing an individual differences MDS model. We discuss each of these approaches, and subsequently propose a straightforward new method (CONcordance PARtitioning—ConPar), which can be used to identify groups of individual-subject matrices with concordant proximity structures. This method collapses the three-way data into a subject×subject dissimilarity matrix, which is subsequently clustered using a branch-and-bound algorithm that minimizes partition diameter. Extensive Monte Carlo testing revealed that, when compared to K-means clustering of the proximity data, ConPar generally provided better recovery of the true subject cluster memberships. A demonstration using empirical three-way data is also provided to illustrate the efficacy of the proposed method.     

The three bases for the enthymeme: A dialogical theory

In traditional logic, an enthymeme is said to be an argument, or chain of argumentation, with one or more missing (implicit) premises or conclusions. In this paper a new theory of enthymemes, based on recent developments in argumentation technology including argumentation schemes, argument visualization tools and formal dialogue systems, is put forward. The dialogical theory hypothesizes three bases for the enthymeme in a formal dialogue system CBVK: (1) the participants' commitment sets, (2) sets of argumentation schemes (especially including presumptive schemes) shared by both participants, and (3) a set of propositions representing common knowledge shared by both participants. The formal dialogue system CBVK is the backbone of the theory of enthymemes into which these three components are built. Three examples of enthymemes of a kind commonly found in everyday conversational argumentation are used to show how the theory applies.     

A square root method of selecting a minimum set of variables in multiple regression: I. The method

An extension of Dwyer's “square root” method has been made to the problem of selecting a minimum set of variables in a multiple regression problem. The square root method of selection differs from the Wherry-Doolittle method primarily in that (1) the computations required are more compact, (2) anF ratio criterion is used which leads to the selection of fewer variables. The method provides solutions for the problems of test selection, item analysis, analysis of variance with disproportionate frequencies, and other problems requiring the rejection of superfluous variables. In a subsequent article a worked example will be given, and the square root and Wherry-Doolittle methods compared.     

Safety implications of co-locating road signs: A driving simulator investigation

BackgroundAs road complexity increases the requirement for number of road signs also increases, although the amount of road side space does not. One practical strategy to address this is to present multiple road signs on the same gantry (sign co-location). However, there is very little research on the safety implications of this practice.Method36 participants (mean age = 42.25 years, SD = 13.99, 18 females) completed three driving simulator scenarios, each scenario had a different sign co-location condition: no co-location, dual co-location and triple co-location. Each scenario presented similar information using direction signs, variable message signs and variable speed limit signs, under. Each drive included standard motorway driving (100 km/h speed zone) in free flow traffic and one emergency event where a lead vehicle suddenly braked. The scenario order was counterbalanced and the emergency event vehicle varied.ResultsOverall, there was no impact of co-locating signs on general driving performance. No significant difference was observed between conditions for reaction time and minimum headway in response to the emergency event. Participants were able to correctly choose their destination whether the signs were co-located or not.DiscussionFor the particular configuration of signs tested there is no evidence that co-location negatively impacts driving performance. However, there may be some implications for travel speed and the manner in which the emergency event is responded to. Future work should confirm the findings on real roads. These findings provided support for sign co-location as a practical and safe option for displaying multiple road signs in a confined area.     

An alternative perspective concerning the differential psychophysiological responsivity of persons with the type A and type B behavior patterns

A systematic review of the task-related differences in physiological arousal between Type A and Type B persons revealed that the differences are less consistent and of a smaller magnitude than what is usually assumed. Specifically, only 6 of the 24 experiments dealing with heart rate revealed reliable differences: only 4 of the 18 experiments dealing with diastolic blood pressure revealed realiable differences; and only 13 of the 20 experiments dealing with systolic blood pressure revealed reliable differences. Furthermore, the median difference in systolic blood pressure between Type A and Type B persons who were working on tasks is only 6 mm Hg. This summary probably constitutes a “liberal” estimate of the consistency and magnitude of the differences because it is based only on published investigations and because many investigations involved numerous comparisons. Hypotheses for the patterning of results were discussed. Conclusions based on this summary have a variety of implications for interpreting the research concerning personality type and coronary heart disease.     

CPCA: A program for principal component analysis with external information on subjects and variables

A program is described for principal component analysis with external information on subjects and variables. This method is calledconstrained principal component analysis (CPCA), in which regression analysis and principal component analysis are combined into a unified framework that allows a full exploration of data structures both within and outside known information on subjects and variables. Many existing methods are special cases of CPCA, and the program can be used for multivariate multiple regression, redundancy analysis, double redundancy analysis, dual scaling with external criteria, vector preference models, and GMANOVA (growth curve models).     

A three-stage estimation procedure for structural equation models with polytomous variables

This paper is concerned with the analysis of structural equation models with polytomous variables. A computationally efficient three-stage estimator of the thresholds and the covariance structure parameters, based on partition maximum likelihood and generalized least squares estimation, is proposed. An example is presented to illustrate the method.This research was supported in part by a research grant DA01070 from the U.S. Public Health Service. The production assistance of Julie Speckart is gratefully acknowledged.     

Homogeneity analysis withk sets of variables: An alternating least squares method with optimal scaling features

Homogeneity analysis, or multiple correspondence analysis, is usually applied tok separate variables. In this paper we apply it to sets of variables by using sums within sets. The resulting technique is called OVERALS. It uses the notion of optimal scaling, with transformations that can be multiple or single. The single transformations consist of three types: nominal, ordinal, and numerical. The corresponding OVERALS computer program minimizes a least squares loss function by using an alternating least squares algorithm. Many existing linear and nonlinear multivariate analysis techniques are shown to be special cases of OVERALS. An application to data from an epidemiological survey is presented.This research was partly supported by SWOV (Institute for Road Safety Research) in Leidschendam, The Netherlands.     

A square root method of selecting a minimum set of variables in multiple regression: II. A worked example

Thesquare root method of selection has been explained in a previous article. In the present article a worked example is given which illustrates the compactness of the procedure. The square root method is compared with the Wherry-Doolittle method.     

A general class of latent variable models for ordinal manifest variables with covariate effects on the manifest and latent variables

Previous work on a general class of multidimensional latent variable models for analysing ordinal manifest variables is extended here to allow for direct covariate effects on the manifest ordinal variables and covariate effects on the latent variables. A full maximum likelihood estimation method is used to estimate all the model parameters simultaneously. Goodness‐of‐fit statistics and standard errors are discussed. Two examples from the 1996 British Social Attitudes Survey are used to illustrate the methodology.     

A meta-analytic review of occupational commitment: relations with person- and work-related variables

Relations between occupational commitment (OC) and several person- and work-related variables were examined meta-analytically (76 samples; across analyses, Ns ranged 746-15,774). Major findings are as follows. First, OC was positively related to job-focused constructs such as job involvement and satisfaction, suggesting that attitudes toward the job itself may be a central concern in committing to one's occupation. Second, consistent with previous work, OC and organizational commitment were positively related. This relation was found to be moderated by the compatibility of the profession and the employing organization. Third, OC was positively related to job performance and had an indirect effect on organizational turnover intention through occupational turnover intention. This latter effect suggests that understanding of organizational turnover can be enhanced by incorporating occupation-related variables into turnover models.     

Alcohol and aggression: A replication study controlling for potential confounding variables

An experiment tested whether the Taylor reaction time paradigm generates a valid measure of aggression when used in alcohol research and when identified confounding influences are controlled. The Alcohol group drank 1.2 ml of 100% alcohel/kg body weight and was compared with a Control group drinking the equivalent amount of tonic. Subjects were tested in an exact replica of Taylor's paradigm. Results indicated that intoxicated subjects were more aggressive both when provoked and when not provoked, which was interpreted as supportive of the validity of this procedure. Discussion was concentrated on the role of dose level and number of and form of available alternatives to behave in the test situation.     

A penny for your thoughts: Patterns of sleep-related beliefs, insomnia symptoms and treatment outcome

The aim of this study was to determine how distinctive patterns of unhelpful beliefs about sleep endorsed by insomnia patients relate to their presenting symptoms and treatment responses. A sample of 281 primary insomnia sufferers completed items comprising the Dysfunctional Beliefs About Sleep scale (DBAS-16). Their resultant scores on the four DBAS-16 subscales were then subjected to a cluster analysis, which resulted in the identification of four distinctive age-matched subgroups. Two subgroups were characterized by pathologically elevated scores on at least two of the DBAS-16 subscales, whereas the other two subgroups had subscale scores that closely resembled those of a normative sample. Subsequent comparisons showed the insomnia subgroups differed in regard to their insomnia severity, use of prescribed medication for sleep, depression and anxiety symptoms, and daytime sleepiness. Furthermore, comparisons of treatment outcomes (i.e. analysis of change scores and normative comparisons) across clusters showed that the subgroups did not benefit equally from a standardized form of Cognitive-Behavioral Therapy (CBT) for insomnia. Findings demonstrate the contribution of specific sleep-related beliefs on presenting insomnia symptoms and suggest the potential usefulness of tailoring CBT protocols to match the needs of distinctive insomnia subtypes.