Search Results

The mediating and moderating effects of women's attachment style on interrelationships among emotional abuse, physical aggression and relational stability.

Description: This purpose of this study was to combine two bodies of literature on relationships, attachment and violence. Given the impact of men's physical aggression and emotional abuse on women, it is likely that these behaviors would also affect attachment. A model proposing that women's attachment style mediated and moderated the relationship between partners' physical and emotional abuse and the stability of women's relationships was tested. Archival data were used from two waves of interviews with a sample of lowincome, ethnically diverse community women. Most (89%) of the initial 835 participants of Project HOW: Health Outcomes of Women completed at least one additional interview providing information on the status of their initial relationships. Of these women, 39% were African American, 30% were Euro-American, and 31% were Mexican American. The effects of men's psychological abuse and physical violence on women's attachment style were tested with regression analyses. The interrelationships between partners' abuse, attachment and relational stability were tested with SEM. Attachment style was expected to moderate the associations among variables and mediate the impact of partners' negative behavior on relational stability. In regression analyses, partners' psychological abuse predicted avoidant and anxious, but not secure attachment ratings. Violence, although significant, explained less variance than psychological abuse for insecure attachment ratings. SEM indicated Physical Aggression was not a significant predictor of Attachment Rating in any group. Moderation was not found. There were no differences between attachment groups. Therefore, attachment was tested in the sample as a mediator. As in analyses for each group, the path from Physical Aggression to Attachment Rating was not significant. In the final model, Emotional Abuse predicted Physical Aggression and Attachment Rating mediated the effect of Emotional Abuse on Relational Stability. Specifically, Emotional Abuse increased (insecure) Attachment Rating, which decreased Relational Stability. Overall, previous research in the violence literature was ...
Date: December 2001
Creator: Weston, Rebecca
Partner: UNT Libraries

Simulating Statistical Power Curves with the Bootstrap and Robust Estimation

Description: Power and effect size analysis are important methods in the psychological sciences. It is well known that classical statistical tests are not robust with respect to power and type II error. However, relatively little attention has been paid in the psychological literature to the effect that non-normality and outliers have on the power of a given statistical test (Wilcox, 1998). Robust measures of location exist that provide much more powerful tests of statistical hypotheses, but their usefulness in power estimation for sample size selection, with real data, is largely unknown. Furthermore, practical approaches to power planning (Cohen, 1988) usually focus on normal theory settings and in general do not make available nonparametric approaches to power and effect size estimation. Beran (1986) proved that it is possible to nonparametrically estimate power for a given statistical test using bootstrap methods (Efron, 1993). However, this method is not widely known or utilized in data analysis settings. This research study examined the practical importance of combining robust measures of location with nonparametric power analysis. Simulation and analysis of real world data sets are used. The present study found that: 1) bootstrap confidence intervals using Mestimators gave shorter confidence intervals than the normal theory counterpart whenever the data had heavy tailed distributions; 2) bootstrap empirical power is higher for Mestimators than the normal theory counterpart when the data had heavy tailed distributions; 3) the smoothed bootstrap controls type I error rate (less than 6%) under the null hypothesis for small sample sizes; and 4) Robust effect sizes can be used in conjuction with Cohen's (1988) power tables to get more realistic sample sizes given that the data distribution has heavy tails.
Access: This item is restricted to UNT Community Members. Login required if off-campus.
Date: August 2001
Creator: Herrington, Richard S.
Partner: UNT Libraries

Comparative Models of the Impact of Social Support on Psychological Distress in Cancer Patients

Description: This study tested the relationship between Social Support, Psychological Distress, and Illness Stress in individuals who report cancer as a health condition. This study was based on archival data obtained from the Wave 1 of the Health and Retirement Study (HRS). The HRS provides a nationally representative sample of individuals aged 51 to 61 in 1992 and their spouses. The study sample was limited to cancer patients with a spouse or partner (n = 503). A structural equation modeling analysis procedure was used to test the theoretical models. Measures of social support were limited to variables assessing the participant's satisfaction with social support. Evidence was found for the Stress Prevention and the Support Deterioration models. This is congruent with previous research using measures of social support perception. Both the Stress Prevention and the Support Deterioration models predict a negative relationship between Illness Stress and Social Support. In addition, a univariate analysis of variance was used to test the stress buffering model. Similarly to other studies measuring the individual's degree of integration, or its perception, in the social network, the present research supported the only the Main Effect model and not the Stress Buffering model.
Date: May 2000
Creator: Forjaz, Maria João Bettencourt Pereira
Partner: UNT Libraries