This study examines longitudinal correlates of coparental and family group-level dynamics during infancy. Thirty-seven couples observed at play with their 8–11-month-old infants (15 boys, 22 girls) rated their child's internalizing and externalizing symptoms, and their own coparenting behavior 3 years later. Teachers also rated child behavior at the 3-year follow-up. Several significant relationships emerged between observed family process (high hostility–competitiveness, low family harmony, and high parenting discrepancies in the triad) at Time 1, and subsequent reports of child and coparenting behavior at Time 2. Larger parenting discrepancies at Time 1 predicted greater child anxiety as rated by teachers; greater hostility–competitiveness and lower harmony forecast higher child aggression. Time 1 family process continued to predict Time 2 aggression even after controlling for individual and marital functioning. Several links were also found between distressed family process and later parental reports of negative coparenting behavior. These parental reports of coparenting also explained unique variance in concurrent child behavior ratings. The significance of coparenting as a distinct family construct is discussed.

Fifty-two married partners played with their 30-month-olds in both dyadic (parent-child) and whole family contexts and reported on their own coparenting activities (family integrity-promoting behavior, conflict, disparagement, and reprimand). Coparenting behavior observed in the whole family context was evaluated for antagonism, warmth and cooperation, child-adult centeredness, balance of positive involvement, and management of toddler behavior. Parallel balance and management scores were also formed using dyadic session data. Men's reported family integrity-promoting activities and women's reported conflict and reprimand activities were reliable correlates of family group process in both bivariate and discriminant analyses, with links enduring even after controlling for marital quality. Whole family- and dyad-based estimates of coparenting were altogether unrelated, and reported coparenting was tied only to behavior in family context, not to family measures created from dyad-based data.

The bootstrap, a computer-intensive approach to statistical data analysis, has been recommended as an alternative to parametric approaches. Advocates claim it is superior because it is not burdened by potentially unwarranted normal theory assumptions and because it retains information about the form of the original sample. Empirical support for its superiority, however, is quite limited. The present article compares the bootstrap and parametric approaches to estimating confidence intervals and Type I error rates of the correlation coefficient. The parametric approach is superior to the bootstrap under both assumption violation and nonviolation. The bootstrap results in overly restricted confidence intervals and overly liberal Type I error rates.

Most studies that have investigated the use of coarsely grained scales have indicated that the accuracy of statistics calculated on such scales is not compromised as long as the scales have about 5 or more points. Gregoire and Driver (1987), however; found serious perturbances of the Type I and Type II error rates using a 5-point scale. They carried out three computer simulation experiments in which continuous data were transformed to Likert-scale values. Two of the three experiments are shown to be flawed because the authors incorrectly specified the population mean in their simulation. This article corrects the flaw and demonstrates that the Type I and Type II error rates are not seriously compromised by the use of ordinal-scale data. Furthermore, Gregoire and Driver's results are reinterpreted to show that in most cases, the parametric test of location equality shows a power superiority to the nonparametric tests. Only in their most nonnormal simulation does a nonparametric test show a power superiority.

No abstract