Generalized approaches to the maxbet problem and the maxdiff problem,with applications to canonical correlations

Van de Geer has reviewed various criteria for transforming two or more matrices to maximal agreement, subject to orthogonality constraints. The criteria have applications in the context of matching factor or configuration matrices and in the context of canonical correlation analysis for two or more matrices. The present paper summarizes and gives a unified treatment of fully general computational solutions for two of these criteria, Maxbet and Maxdiff. These solutions will be shown to encompass various well-known methods as special cases. It will be argued that the Maxdiff solution should be preferred to the Maxbet solution whenever the two criteria coincide. Horst's Maxcor method will be shown to lack the property of monotone convergence. Finally, simultaneous and successive versions of the Maxbet and Maxdiff solutions will be treated as special cases of a fully flexible approach where the columns of the rotation matrices are obtained in successive blocks.The author is obliged to Henk Kiers for computational assistance and helpful comments.     

Alternating least squares algorithms for simultaneous components analysis with equal component weight matrices in two or more populations

Millsap and Meredith (1988) have developed a generalization of principal components analysis for the simultaneous analysis of a number of variables observed in several populations or on several occasions. The algorithm they provide has some disadvantages. The present paper offers two alternating least squares algorithms for their method, suitable for small and large data sets, respectively. Lower and upper bounds are given for the loss function to be minimized in the Millsap and Meredith method. These can serve to indicate whether or not a global optimum for the simultaneous components analysis problem has been attained.Financial support by the Netherlands organization for scientific research (NWO) is gratefully acknowledged.     

Least-squares approximation of an improper correlation matrix by a proper one

An algorithm is presented for the best least-squares fitting correlation matrix approximating a given missing value or improper correlation matrix. The proposed algorithm is based upon a solution for Mosier's oblique Procrustes rotation problem offered by ten Berge and Nevels. A necessary and sufficient condition is given for a solution to yield the unique global minimum of the least-squares function. Empirical verification of the condition indicates that the occurrence of non-optimal solutions with the proposed algorithm is very unlikely. A possible drawback of the optimal solution is that it is a singular matrix of necessity. In cases where singularity is undesirable, one may impose the additional nonsingularity constraint that the smallest eigenvalue of the solution be , where is an arbitrary small positive constant. Finally, it may be desirable to weight the squared errors of estimation differentially. A generalized solution is derived which satisfies the additional nonsingularity constraint and also allows for weighting. The generalized solution can readily be obtained from the standard unweighted singular solution by transforming the observed improper correlation matrix in a suitable way.     

Interfacing Apple and IBM computers for the analysis of clinical biofeedback

This paper demonstrates a method of transferring research data from a remote clinic to a large university mainframe for data manipulation and statistical analysis. Data collected by an Apple //e computer were transferred to an IBM 3031 mainframe by sending data files to an IBM PC by telephone modem or by direct hardwire connection to the PC. The IMB PC performed data-formatting routines and then uploaded the files to the mainframe for storage. Advantages and disadvantages of sending data over telephone lines via a modem are discussed.     

Single-subject statistical analysis of computer-assisted biofeedback

Single-subject statistics were used to analyze physiological data [electromyographic (EMG) temperature] recorded from two patients receiving computer-assisted biofeedback treatment in a clinic. When the data were analyzed by an ANOVA method or a regression technique, the results demonstrated that both patients learned to significantly reduce EMG levels. The rationale of using single-subject statistics is discussed, and the applicability of the statistical technique to the clinic population is illustrated.     

Value-based adoption of augmented reality: A study on the influence on online purchase intention in retail

The increasing use of digital technology-based retail services provides new opportunities for digital marketing. In this paper, we investigate how augmented reality (AR) technology can be leveraged as part of the firm's strategy. We explore the online purchase intention through AR smart glasses (ARSG), considering consumers' value assessment through a cost–benefit analysis and the influence of technical, experiential and social AR value drivers. We develop an augmented value-based adoption model addressing four main objectives: (1) Evaluate the effect of the perceived value of ARSG, (2) Evaluate the effect of immersion (experiential dimension), (3) Evaluate the effect of AR devices and technical complexity (technical dimension) and (4) Evaluate the importance of subjective norms (social dimension) on the online purchase intention through AR technology. Based on an ESIC Tech Lab experiment with two types of ARSG from market leaders and AR retail apps, the study uses survey data from 253 participants. The results suggest that the technical dimension has an ambiguous effect, with tech-complexity enhancing directly the perceived value of ARSG for online purchase while reducing the net value of consumers' economic cost–benefit analysis. We find strong evidence that the experiential and social AR dimensions (in the form of immersion and subjective norm) have a significant positive influence on consumers' purchase intention online, which are better predictors than the pure economic cost–benefit assessment (through usefulness and difficulty). Furthermore, the technical innovativeness of consumers is found to increase directly the online purchase intention through ARSG.     

Parental alcohol consumption and postneonatal mortality

The purpose of this study was to evaluate the role of maternal and paternal alcohol consumption as independent risk factors in postneonatal mortality. Questions on the frequency and quantity of alcoholic drinks consumed were included in a questionnaire used as part of a case-control study. Over a period of 11 months the families of 157 cases and 468 controls, matched for age and locality, were interviewed. Odds ratios and 95% confidence intervals were obtained by matched univariate analysis and by multiple conditional logistic regression. Maternal consumption during pregnancy, maternal consumption during breastfeeding and maternal consumption in the past year were not risk factors for postneonatal mortality. A multiple matched analysis did not alter these results. Matched univariate analysis of paternal alcohol consumption gave several positive results, including variables pertaining to the father's consumption in a multiple logistic regression model with traditional risk factors, which revealed that the frequency of paternal consumption in the last year, as estimated by the mother, was found to have a significant effect on postneonatal mortality.     

Illusory conjunctions and the cerebral hemispheres

Two visual half-field experiments tested Moscovitch’s (1979) proposition that cerebral asymmetry does not concern the earliest perceptual stages but only later processing. Subjects were briefly shown displays that included one (Experiment 1) or two (Experiment 2) types of forms differing in size and which, according to previous evidence, might lead to opposite laterality effects. Laterality effects were assessed for correct detections and for illusory conjunctions, both in terms of raw detection scores and in terms of perceptual discriminability (dr scores). In Experiment 1, displays included either rectangles or triangles. In the first case, the target was a cross; in the second case, it was a Star of David. A hemifield x size interaction was observed both on correct detections and on associated discriminability. Yet, no such interaction was obtained for illusory conjunctions or for associated d’ scores. In Experiment 2, the two types of forms were presented simultaneously, with the small ones either inside or outside the large ones. No laterality effects were observed. Some implications of these data for both hemispheric asymmetry and feature integration issues are discussed. The results suggest that early preattentive processes of feature extraction are not lateralized, whereas some integrative mechanisms, such as Treisman’s (1988) focal attention, may operate differently in the two hemispheres.