Explicit candecomp/parafac solutions for a contrived 2 × 2 × 2 array of rank three

Kruskal, Harshman and Lundy have contrived a special 2 × 2 × 2 array to examine formal properties of degenerate Candecomp/Parafac solutions. It is shown that for this array the Candecomp/Parafac loss has an infimum of 1. In addition, the array will be used to challenge the tradition of fitting Indscal and related models by means of the Candecomp/Parafac process.     

Some additional results on principal components analysis of three-mode data by means of alternating least squares algorithms

Kroonenberg and de Leeuw (1980) have developed an alternating least-squares method TUCKALS-3 as a solution for Tucker's three-way principal components model. The present paper offers some additional features of their method. Starting from a reanalysis of Tucker's problem in terms of a rank-constrained regression problem, it is shown that the fitted sum of squares in TUCKALS-3 can be partitioned according to elements of each mode of the three-way data matrix. An upper bound to the total fitted sum of squares is derived. Finally, a special case of TUCKALS-3 is related to the Carroll/Harshman CANDECOMP/PARAFAC model.     

Playfulness, “World”-Travelling,and Loving Perception

A paper about cross-cultural and cross-racial loving that emphasizes the need to understand and affirm the plurality in and among women as central to feminist ontology and epistemology. Love is seen not as fusion and erasure of difference but as incompatible with them. Love reveals plurality. Unityndashnot to be confused with solidarityndashis understood as conceptually tied to domination.     

Convergence properties of an iterative procedure of ipsatizing and standardizing a data matrix,with applications to parafac/candecomp preprocessing

Centering a matrix row-wise and rescaling it column-wise to a unit sum of squares requires an iterative procedure. It is shown that this procedure converges to a stable solution. This solution need not be centered row-wise if the limiting point of the interations is a matrix of rank one. The results of the present paper bear directly on several types of preprocessing methods in Parafac/Candecomp.     

Fitting the off-diagonal dedicom model in the least-squares sense by a generalization of the harman and jones minres procedure of factor analysis

Harshman's DEDICOM model providesa framework for analyzing square but asymmetric materices of directional relationships amongn objects or persons in terms of a small number of components. One version of DEDICOM ignores the diagonal entries of the matrices. A straight-forward computational solution for this model is offered in the present paper. The solution can be interpreted as a generalized Minres procedure suitable for handing asymmetric matrices.     

Propionibacterium granulosum KP-45 in the treatment of subacute sclerosing panencephalitis

3 groups of patients, who suffered on SSPE (without treatment, with isoprinosine therapy, combined treatment with propionibacterium granulosum and isoprinosine) are compared. The results show a favourable effect of the combined treatment in a part of the patients. They are discussed in detail.     

Phonological priming in spoken word recognition: Task effects

In two experiments, we examined the role of phonological relatedness between spoken items using both the lexical decision task and the shadowing task. In Experiment 1, words were used as primes and overlaps of zero (control), one, two, or all four or five (repetition) phonemes were compared. Except for the repetition conditions, in which facilitation was found, phonological overlap resulted in interference on word responses. These effects occurred in both tasks but were larger in lexical decision than in shadowing. The effects that were evident in shadowing can be attributed to an attentional mechanism linked to the subjects' expectancies of repetitions. The extra effects obtained in lexical decision can be interpreted by taking into account both activation of the response corresponding to the prime's lexical status and postlexical processes that check for phonological congruency between prime and target. In Experiment 2, some modifications were introduced to prevent the involvement of strategic factors, and pseudowords were used as primes. No effect at all was observed in shadowing, whereas in lexical decision interference effects occurred, which is consistent with the hypothesis that lexical decision may be negatively affected by finding a phonological discrepancy at the same time as the primed response is reactivated. Neither experiment provided evidence for the occurrence of phonological priming in the perceptual processing of words.     

Phonetic analysis of speech and memory codes in beginning readers

Two experimental tasks, a speech segmentation and a short-term memory task, were presented to children who began to learn to read following either the “phonic” or the “wholeword” method. The segmentation task required the child to reverse two segments (either two phones or two syllables) in an utterance. The phonic group performed significantly better than the whole-word group in the “phonic reversal” task, but no difference appeared in the “syllable reversal” task. This indicated (1) that most children by the age of 6 years are ready to discover that speech consists of a sequence of phones and (2) that the moment at which they do it is influenced by the way they are taught to read. In the memory task, the children recalled series of visually presented items whose names either rhymed or did not. The difference in performance for the rhyming and nonrhyming series was significant in both groups. It was no greater for the phonic than for the whole-word group and was uncorrelated with the “phonic reversal” task. These results are discussed in connection with the distinction between ways of lexical access and ways of representing verbal information in short-term memory.     

Activity measures in stress-attenuated novelty tests as possible analogues for extraversion in rats: Some experimental results

In an attempt to extend and validate Garcia-Sevilla's (1974) hypothesis proposing ambulation in a non-stressful open field (OF) as an animal analogue of human extraversion, ambulatory behaviour and rearing behaviour were studied and compared in several experiments with genetically-unselected rats. The effects of variation of OF auditory stimulation level, the correlation with a two-way avoidance-learning situation and the effects of a stimulant dose of d-amphetamine and an anxiolytic one of diazepam upon rearing and ambulatory behaviours were studied. All in all, our results support some of the requirements of the hypothesis, but also generate some additional problems. The results show that the number of rearings could be a better and more sensitive measure of variations in the level of arousal and a better predictor of shuttle-avoidance conditioning than ambulation. However, all activity measures are at least moderately intercorrelated, and they become grouped when results are factor analysed. All the results are discussed with reference to Eysenck's personality theory and Gray's anxiety theory, and it is concluded that these measures are too multidetermined and too poorly controlled to represent correctly and in a direct form a personality dimension such as Extraversion. Anyway, this attempt could be a good point of departure for discovering more efficient animal behavioural measures of arousability.