On structural equation modeling with data that are not missing completely at random

A general latent variable model is given which includes the specification of a missing data mechanism. This framework allows for an elucidating discussion of existing general multivariate theory bearing on maximum likelihood estimation with missing data. Here, missing completely at random is not a prerequisite for unbiased estimation in large samples, as when using the traditional listwise or pairwise present data approaches. The theory is connected with old and new results in the area of selection and factorial invariance. It is pointed out that in many applications, maximum likelihood estimation with missing data may be carried out by existing structural equation modeling software, such as LISREL and LISCOMP. Several sets of artifical data are generated within the general model framework. The proposed estimator is compared to the two traditional ones and found superior.The research of the first author was supported by grant No. SES-8312583 from the National Science Foundation and by a Spencer Foundation grant. We wish to thank Chuen-Rong Chan for drawing the path diagram.     

Incorporating good programs into the larger laboratory context

The Scheduled Measurement System (SMS) is a collection of related programs for administering performance and rating tasks to human subjects. It was designed to provide a common task scheduling and data management environment for a diversity of measures. SMS has greatly reduced the effort required to analyze and archive data after experiments, but it has been less successful in reducing some of the effort required to implement experiments. While programming is not difficult, documentation and user training remain the most primitive parts of the system.     

Causal attribution and dispositional inference: Evidence of inconsistent judgments

Two experiments examined whether individuals who ascribe the disparity in the performances of two actors to situational constraints adequately adjust their dispositional inferences to reflect their own perceptions of causality. Using the quiz-game format of L. D. Ross, T. M. Amabile, and J. L. Steinmetz (1977, Journal of Personality and Social Psychology, 35, 485–494), the effects of the subjects' awareness of the role-determined, self-presentation advantage of the questioner on their dispositional inferences concerning the quiz-game participants are noted. It is hypothesized that subjects who indicated full awareness of the determining force of the situation would nevertheless draw more favorable dispositional inferences about the questioner than about the contestant. The prediction is confirmed. Although the situationally aware subjects rate the questioner and contestant more similarly than do the other subjects, they still rate the questioner higher in knowledge, memory, and education. The results of Experiment 2 indicate that increasing the salience of the subjects' assessment of the situational advantage of the questioner does not eliminate the disparity. It is proposed that the fudamental attribution error represents more a failure to adjust trait inferences for causal attributions than a misperception of causality. Implications concerning the relationship between knowledge of causality and social judgment and the utility of the distinction between “perceived causality” and “higher order causal inferences” are discussed.     

An educational-therapeutic group for drug and alcohol abusing combat veterans

Vietnam veterans have had a high incidence of substance abuse, resulting from attempts to control posttraumatic symptoms. Their recovery from drug and alcohol dependency has meant involvement in treatment for resolution of posttraumatic symptoms. The author found that the addition of a short-term educational-therapeutic group experience, focusing on the symptoms of posttraumatic stress disorder, was helpful for the participants. They worked-through important war-related experiences via the following phases: (1) Breaking through detachment and establishing control over disruptive symptoms, (2) Revealing experiences of death and dehumanization (3) Describing the internal death of self experience, and (4) Beginning the grief response.     

Reflections on the idea of personal fate and its psychopathology: Helene Deutsch's "Hysterical Fate Neurosis" revisited

The idea of a psychopathology of fate or what had come to be called a fate neurosis has failed to retain any established place in the structure of psychoanalytic thought. The clinical observations and theoretical formulations, to which the idea of a fate neurosis answered, have been subsumed in the course of things by more fundamental and systematic conceptualizations. A review of Helene Deutsch's (1930) paper, "Hysterical Fate Neurosis," is therefore bound to be largely an excursion into an area of intellectual history. However, such history never fails to shed light on certain ongoing clinical and theoretical problems that may have lost too much to current developments in psychoanalytic thought. It is with this historical purpose that the present study of Deutsch's classic paper on a fate neurosis is undertaken.     

Further evaluation of prompt density,rate of reinforcement,and the persistence of manding

Previous research has evaluated the effects of prompt rates on the rate of communicative behavior. More recent research has suggested that dense prompting can result in communicative behavior that is more resistant to change. However, existing research has not considered the impact that higher response rates had on reinforcement rate, a variable known to impact response persistence. The current study systematically replicated previous research by evaluating communicative responding in contexts associated with dense- and lean-prompt schedules and extended existing research by (a) holding reinforcement rates similar across the two prompting schedules (lean and dense), and (b) evaluating the persistence of communicative responding in the contexts associated with each prompting schedule. The results for Experiment 1 clearly replicated and extended previous research. The results for Experiment 2 were equivocal and suggested that previous reinforcement history and response class size impacted outcomes.     

The effect of pressurized air in establishing discriminative response suppression in stump-tailed macaques

Pressurized air was repeatedly associated with one of two frequencies of flashing light during performance of a VI 30-sec positive reinforcement schedule by stump-tailed monkeys. As revealed by the relative suppression of bar presses to each of the two visual stimuli, the Ss learned to discriminate between the different flicker frequencies. However, they also showed signs of adapting to the airblast during the course of training, and its location had to be changed in order to maintain discriminative suppression.