Statistical Issues in the Study of Temporal Data: Daily Experiences

This article reviews statistical issues that arise in temporal data, particularly with respect to daily experience data. Issues related to nonindependence of observations, the nature of data structures, and claims of causality are considered. Through the analysis of data from a single subject, we illustrate concomitant time-series analysis, a general method of examining relationships between two or more series having 50 or more observations. We also discuss detection of and remedies for the problems of trend, cycles, and serial dependency that frequently plague temporal data, and present methods of combining the results of concomitant time series across subjects. Issues that arise in pooling cross-sectional and time-series data and statistical models for addressing these issues are considered for the case in which there are appreciably fewer than 50 observations and a moderate number of subjects. We discuss the possibility of using structural equation modeling to analyze data structures in which there are a large number (e.g., 200) of subjects, but relatively few time points, emphasizing the different causal status of synchronous and lagged effects and the types of models that can be specified for longitudinal data structures. Our conclusion highlights some of the issues raised by temporal data for statistical models, notably the important roles of substantive theory, the question being addressed, the properties of the data, and the assumptions underlying each technique in determining the optimal approach to statistical analysis.     

Personalism and cognitive labels as determinants of attitude attribution

An experiment was conducted to test hypotheses derived from Jones and Davis’ (1965) theory of correspondent inferences in conjunction with research on emotional misattribution effects. Subjects were informed that they had ingested either a stimulant or a tranquilizer (label). They then read an emotional, counterattitudinal essay which was written either personally for them or for another subject (personalism). The primary dependent variable was the attitude on the issue in question attributed to the author of the communication. The results showed that the subjects who read the more personal communication made more extreme attributions concerning the attitude of the author of the essay than did the subjects who read the less personal communication. In addition, subjects who were informed that they had received a tranquilizer made more extreme attitude attributions than subjects who were informed that they had received a stimulant. The implications of the results of the experiment for Jones and Davis’ principles of personalism and hedonic relevance are discussed.     

Perceptual supports for one-to-one correspondence in the conservation of number

This study compared provoked and spontaneous one-to-one correspondence along with two tasks having more perceptual support for correspondence. These four levels of correspondence appeared in a conservation of number condition and two conservation-related conditions (a partially static array or a static array). There were two sets of stimuli (toy animals or corks) in each condition. In opposition to Piaget's predictions, the four levels of correspondence did not differ in difficulty for kindergarteners. There was a strong order effect (p<.001) in the direction of increasing conservation over the eight trials. There was some evidence that the standard conservation condition was easier than the other two conditions. Implications for Piaget's theory are discussed.     

Primary process content in paranoid schizophrenic speech

Free speech samples given by paranoid schizophrenics, nonschizophrenic paranoids, and nonpsychotic psychiatric patients were submitted to computerized content analysis. Speech samples were searched for words belonging to the Regressive Imagery Dictionary (Martindale, 1975), which yields a well-validated measure of primary process content. Three word-concreteness dictionaries were also employed. Compared to the other groups, paranoid schizophrenics produced speech higher in primary process content as well as in transitive verb concreteness. Results are consistent with psychoanalytic theory.     

Social support in the workplace: Tests of six theoretical models

Six theoretical models of social support in relation to perceived job stress, burnout, and health were tested both cross-sectionally and longitudinally. Participants at Time 1 were state correctional officers (N = 262) who completed questionnaires in which multiple indicators of each construct were assessed. Time 2 participants (N = 177) were those officers from the Time 1 sample who completed the questionnaire again three months later. Structural equation analyses revealed that only one of the six models was supported by cross-sectional results. In this model a direct negative relationship between the WORKPLACE SOCIAL SUPPORT and BURNOUT latent variables was specified, along with direct, positive relationships between the JOB STRESS and BURNOUT latent variables and the BURNOUT and POOR HEALTH latent variables. However, none of the six models was supported by the longitudinal results. Thus, cross-sectional results were consistent with a model in which social support on the job influences positive health only through its direct and negative effect on burnout symptoms, but such causal connections were not validated longitudinally.     

Primary process cognition and hemispheric asymmetry

Several theorists have hypothesized that the right hemisphere operates in a primary process manner, whereas the left hemisphere operates in a secondary process manner. Evidence for this hypothesis, though supportive, has been indirect. In two experiments, we applied a validated content-analytic measure of primary process cognition to verbal material produced by subjects while right-hemisphere and left-hemisphere alpha-wave amplitude was monitored. Both experiments indicated that amount of primary process content in language is related to basal or long-term hemispheric asymmetry (high levels of right-hemisphere activation, as compared to left-hemisphere activation), and that the relation with asymmetry is stronger than that with absolute levels of either right-hemisphere or left-hemisphere activation. Both experiments showed that primary process content is not closely related to momentary asymmetry. The second experiment indicated that within subjects, momentary asymmetry is in fact weakly related to primary process content in the direction opposite to that predicted.     

Methodological developments in personality research: An introduction

This article first provides a brief overview of some of the empirical and conceptual work in personality following Mischel's (1968) critique Strengths and weaknesses of traditional personality research designs including laboratory experiments, experimental personality designs, and preexperimental correlational studies are presented Some more recent approaches to designing laboratory research that attempt to address issues of external validity and approaches to designing field Investigations that attempt to address issues of internal validity are discussed Issues associated with the measurement of constructs, the broadening of measurement methods, and newer data analytic techniques are noted Finally, a brief orientation to the other papers in the special issue is presented