PubMed Health⌕ Search

Biomedical subjects

Camille B Warner

Publications and source records attributed to Camille B Warner.

2 recordsLinked to original sources

Grandmothers, caregiving, and family functioning.

OBJECTIVES: We used McCubbin's Resiliency Model of Family Stress, Adjustment and Adaptation ( McCubbin, Thompson, & McCubbin, 2001) to examine how demographic factors, family stress, grandmother resourcefulness, support, and role reward affect perceptions of family functioning for grandmothers raising grandchildren, grandmothers living in multigenerational households, and grandmothers not caregiving for grandchildren. METHODS: A sample of 486 grandmothers completed a mailed questionnaire. We used structural equation modeling to (a) test the effects of demographic factors (i.e., grandmother's age, race, marital status, and employment), family stressful life events and strain, grandmother's resourcefulness, subjective and instrumental support, and role reward on perceptions of family functioning for each grandmother group; (b) evaluate differences in the measurement and structural models between the grandmother groups using multisample analysis; and (c) test the model on the full sample, coding for caregiver status. RESULTS: The models did not differ significantly by grandmother group; therefore we assessed the composite model using a multisample analysis. We found general support for the resiliency model and equivalence of the models across grandmother groups. Less support, resourcefulness, and reward, and more intrafamily strain and stressful family life events contributed to perceptions of worse family functioning. DISCUSSION: Findings demonstrate the importance of the quality of family functioning for grandmothers in all types of families.

Adult↗

A comparison of imputation techniques for handling missing data.

Researchers are commonly faced with the problem of missing data. This article presents theoretical and empirical information for the selection and application of approaches for handling missing data on a single variable. An actual data set of 492 cases with no missing values was used to create a simulated yet realistic data set with missing at random (MAR) data. The authors compare and contrast five approaches (listwise deletion, mean substitution, simple regression, regression with an error term, and the expectation maximization [EM] algorithm) for dealing with missing data, and compare the effects of each method on descriptive statistics and correlation coefficients for the imputed data (n = 96) and the entire sample (n = 492) when imputed data are inculded. All methods had limitations, although our findings suggest that mean substitution was the least effective and that regression with an error term and the EM algorithm produced estimates closest to those of the original variables.

Algorithms↗