Factor analysis by instrumental variables methods

Three alternative estimation procedures for factor analysis based on the instrumental variables method are presented. These procedures are justified by the method of least squares. Formulas for asymptotic standard errors of factor loadings are derived. The procedures are empirically compared to the method of maximum likelihood. The conclusion, based on the data used in this study, is that two of the procedures seem to work well.     

Individual response patterns and the effects of different behavioral methods in the treatment of claustrophobia

The importance of individual response patterns in claustrophobic patients was examined in the present study. Thirty-four psychiatric outpatients with a phobia of enclosed spaces were assessed in a small test chamber. During the test their overt behavior was video-taped, heart-rate was measured continuously, and self-ratings of experienced anxiety were made at certain intervals. On the basis of their reactions in the test situation, the patients were divided into two groups showing different response patterns—behavioral and physiological reactors. Within each group the patients were randomly assigned to one behaviorally-focused method (exposure), one physiologically-focused method (applied relaxation) and a waiting-list control group. The patients were treated individually in eight sessions. The between-group comparisons showed that both exposure and applied relaxation were significantly better than the waiting-list condition. Furthermore, exposure yielded better results than applied relaxation for the behavioral reactors, while applied relaxation was better than exposure for the physiological reactors. The improvements were maintained at a follow-up assessment 14 months after the end of treatment. The results support the hypothesis that greater effects are achieved when the method used fits the patient's response pattern than when it does not.     

Channel capacity and processing of modality specific information

The synthesis model, designed to explain effects of modality specific information on retention, is presented and tested. The model encompasses qualitative and quantitative components. The qualitative characteristics reflect the physiological properties of the auditory and visual channels. Three parameters are assumed to affect the quantitative efficiency of the channels. Each channel is assumed to have a certain capacity, and processing of information in the channels is determined by situational demands. Furthermore, processing in a channel is regarded as superficial. Increased allocation of processing to the superficial level was manipulated by the use of modality specific distractors and conditions of ‘supracapacity load’. Transformation of information from the visual to the auditory channel was controlled by the use of one mixed-mode and one single-mode experiment. Thirty subjects participated in the mixed-mode experiment and 60 in the single-mode experiment. Both experiments employed an identical distraction task, intervening presentation and free recall of the to-be-remembered items. The results confirmed the predictions of (a) modality specific distraction, (b) supracapacity performance decrement, (c) a larger distraction effect for the auditory channel and (d) transformation effects in the single-mode experiment.     

Situational factors in meaning

Summary Our hypothesis:The meaning of a word experienced by the speaker/ listener using this word depends, in part, on the cognition of the situation in which the sentence is uttered. In order to test this hypothesis drawings showing two persons each were selected; the persons had been rated on the Semantic Differential as being high (or low) on one of the dimensions of Activity, Potency, or Evaluation, and medium on the two other dimensions. In the next step, 36 Ss rated on the Semantic Differential the verb of a short utterance (e.g. ich bitte dich) shown as being spoken by one person of the drawing to the other person. The same words were rated in isolation.Result:The connotative meaning of an utterance (as assessed by the SD) is determined not less by the persons perceived in verbal communication than by what is being said. The theoretical implications of these results are discussed.

---

Zusammenfassung Nach unserer Ausgangshypothese hängt die Bedeutung eines Wortes, das ein Sprecher/Hörer verwendet, mit davon ab, wie dieser Sprecher/ Hörer die Situation kognitiv erfaßt, in welcher das Wort geäußert wird. Zur Prüfung dieser Hypothese wurden Zeichungen ausgesucht, auf denen jeweils zwei Personen zu sehen waren. Diese Personen waren auf dem Semantischen Differential eingestuft worden und zeigten hohe (oder niedere) Werte auf einer der drei Dimensionen Aktivität, Potenz bzw. Valenz, und mittlere Werte auf den beiden anderen Dimensionen. Im nächsten Abschnitt des Versuchs stuften 36 Vpn. das Verb eines kurzen Satzes (z. B. ich bitte dich), der in der Zeichung als von einer Person zur anderen gesprochen dargestellt wurde, ebenfalls auf dem SD ein. Die gleichen Wörter wurden dann noch isoliert eingestuft.Ergebnis: Die konnotative Bedeutung einer Äußerung scheint mindestens so sehr davon determiniert zu werden, wie man Sprecher/Hörer auffaßt, als von einer dem Wort sozusagen inhärenten Bedeutung.

     

Statistical analysis of sets of congeneric tests

Various models for sets of congeneric tests are considered, including models appropriate for the analysis of multitrait-multimethod data. All models are illustrated with real data. The special cases when two or more tests within a set are tau-equivalent or parallel are also considered. All data analyses are done within the framework of a general model by Jöreskog [1970].Research reported in this paper has been supported by Grant NSF-GB-12959 from National Science Foundation. The writer wishes to thank Gunnar Gruvaeus and Marielle van Thillo, who wrote the computer program and assisted in all aspects of the computational work.     

The minimum average correlation between equivalent sets of uncorrelated factors

A simplified proof of a lemma by Ledermann [1938], which lies at the core of the factor indeterminacy issue, is presented. It leads to a representation of an orthogonal matrixT, relating equivalent factor solutions, which is different from Ledermann's [1938] and Guttman's [1955].T is used to evaluate bounds on the average correlation between equivalent sets of uncorrelated factors. It is found that the minimum average correlation is independent of the data.This paper owes much to an unknown reviewer.