Suchergebnisse

Statistical power analysis has revolutionized the ways in which we conduct and evaluate research. Similar developments in the statistical analysis of incomplete (missing) data are gaining more widespread applications. This volume brings statistical power and incomplete data together under a common framework, in a way that is readily accessible to those with only an introductory familiarity with structural equation modeling. It answers many practical questions such as: How missing data affects the statistical power in a study How much power is likely with different.

Software developments increasingly facilitate inclusion of incomplete data, but relatively little research has examined the effects of incomplete data on statistical power. Seven steps needed to conduct power analyses with incomplete data for a variety of commonly tested hypotheses are illustrated, focusing on significance tests of individual parameters. The example extends a growth curve model simulation presented by Curran and Muthén (1999) to the incomplete data situation. How to estimate statistical power for a range of sample sizes from a single model, as well as how to calculate the sample size required to obtain a desired value of statistical power, is demonstrated. Effects of data being missing completely at random (MCAR) or missing at random (MAR) across a range from 0% (complete data) to 95% missing data are considered. SAS and LISREL syntax are provided in this paper with syntax for other software available from the authors.

This study examines whether the meaning of marital conflict and marital solidarity are affected by the transition to retirement, whether the retirement transition alters stability and variability of, and cross-spouse influences on, marital quality, and whether retirement influences latent means of marital quality. Data from both waves of the National Survey of Families and Households (NSFH) addressed these questions ( N= 407 couples for wives' retirement, and N= 550 couples for husbands' retirement). Results suggest that the structure of marital conflict is unaffected by husbands'and wives'transition to retirement, but that wives' continued employment may be associated with greater conflict longitudinally. Husbands' and wives' constructs of marital solidarity differ from one another; they were unaffected by wives' retirement but converged with husbands' retirement through changes for each partner in the importance of joint time together and potential for divorce. Effects of the retirement transition are far subtler than previously believed.

Limited research has examined caregivers for the oldest old (85+), a distinct group among older adults who are most likely to experience functional and cognitive limitations that require care. To profile socio-demographic characteristics of the oldest-old and their informal caregivers and assess their caregiving situations, we used data from 3163 care recipients with at least one functional limitation from the 2004 National Long-Term Care Survey and 1363 caregivers who were either adult children or spouses of care recipients. The oldestold with functional disabilities were less likely to be married and more likely to be women living alone. Compared with those under 85, the oldestold group were likely to have more extensive IADL and ADL limitations. However, with the exception of dementia, the oldest-old had a lower prevalence of chronic illness than younger elders. The oldest-old care recipients also tended to use more formal care service. While caregivers for the oldest old were less likely to be a sole caregiver and more likely to use formal care service, their physical and emotional stress from caregiving remained the same with their counterpart group of caregivers. Comparison of caregivers by their relationships to care recipients also indicated that adult children who cared for the oldest-old parents tended to express the most stress from caregiving. We contend that formal services need to be better incorporated with informal caregiving to attenuate negative caregiver outcomes, especially for the oldest-old whose informal caregiving network is rather limited.

We linked individual-level data from the 2004 wave of the National Long-Term Care Survey with state-level data from the National Aging Program Information Systems (NAPIS) State Program Reports to predict care mix and unmet need for assistance. Our sample consisted of 2422 community-dwelling individuals aged 65 and older (69% women, 8% nonwhite) who reported at least one limitation in an instrumental or basic activity of daily living. We used the data to predict the mix of formal and informal support received, and the probability of having at least one unmet need from individual (predisposing, enabling, and need) characteristics with statelevel home help coverage rates, intensity of home help services, and proportion of population aged 60+ residing in institutional settings. Consistent with past research, a majority (52.6%) of the disabled sample reported unmet need. At the individual level, enabling (availability of kin support) and need (number of basic and instrumental activity of daily living impairments, BADLs and IADLs) were most strongly associated with care mix and unmet need. Statelevel services were not associated with receipt of informal supports. In states providing home help services to a higher proportion of elders, women were more likely to receive formal help. In states providing more intensive services, women were less likely and individuals living alone more likely to receive formal supports. In states where a higher proportion of elders lived in nursing homes, individuals living alone were more likely to receive formal assistance, less likely overall to report unmet needs, but the oldest-old were more likely to report unmet need.