PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 15969835

Modelling non-ignorable missing-data mechanisms with item response theory models.

Rebecca Holman·Cees A W Glas
View original source ↗Export metadata ↓

Abstract

A model-based procedure for assessing the extent to which missing data can be ignored and handling non-ignorable missing data is presented. The procedure is based on item response theory modelling. As an example, the approach is worked out in detail in conjunction with item response data modelled using the partial credit and generalized partial credit models. Simulation studies are carried out to assess the extent to which the bias caused by ignoring the missing-data mechanism can be reduced. Finally, the feasibility of the procedure is demonstrated using data from a study to calibrate a medical disability scale.

Explore related subjects

Activities of Daily LivingBiasData CollectionDisability EvaluationHumansMathematical ComputingModels, StatisticalPsychometricsJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Rebecca Holman, Cees A W Glas. 2005. Modelling non-ignorable missing-data mechanisms with item response theory models.. https://doi.org/10.1348/000711005x47168

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

A pooled analysis of quality of life measures and adverse events data in north central cancer treatment group lung cancer clinical trials.

BACKGROUND: In this pooled analysis, the authors examined correlations between single-item and multiple-item quality of life (QOL) measures and assessed the agreement between clinically significant changes in QOL and patient-reported adverse events (AE). METHODS: Data from 6 lung cancer clinical trials that involved 358 patients were pooled. All trials incorporated the Uniscale and 1 of 3 multiple-item assessments: the Functional Assessment for Cancer Therapy-Lung, the Lung Cancer Symptom Scale, or the Symptom Distress Scale. Spearman rank correlations and a Bland-Altman approach were used to assess agreement. Time-to-event analysis was performed using the Kaplan-Meier method. RESULTS: Correlations between the Uniscale and multiple-item assessments were substantial (correlation coefficient = 0.49-0.66). At least 1 10-point decline was reported in the Uniscale and multiple-item assessments by 58% of patients and 39% of patients, respectively. At least 1 severe AE (grade >or=3) was reported in 35% of patients postbaseline. The percent agreement between experiencing a severe AE and a decline in QOL was 48% and 59% for the Uniscale and multiple-item assessments, respectively. The median time to the first 10-point decline in QOL for the Uniscale and multiple-item assessments was 67 days and 142 days, respectively, and the median time to the first occurrence of a severe AE was 304 days. CONCLUSIONS: Information gleaned from the single-item Uniscale assessment was comparable to that gleaned from multiple-item global measures. There was moderate agreement between QOL and AE. A 10-point decline in QOL occurred earlier than Common Toxicity Criteria AE reporting. This suggests the need for inclusion of a QOL instrument in lung cancer clinical trials.

Activities of Daily Living↗
PubMed2007

A pilot study of the vulnerable elders survey-13 compared with the comprehensive geriatric assessment for identifying disability in older patients with prostate cancer who receive androgen ablation.

BACKGROUND: Impairments in geriatric domains adversely affect health outcomes of the elderly. The Comprehensive Geriatric Assessment (CGA) is a key component of the treatment approach for older cancer patients, but it is time consuming. In this pilot study, the authors evaluated the validity of a brief, functionally based screening tool, the Vulnerable Elders Survey-13 (VES-13), for identifying older patients with prostate cancer (PCa) with impairment in the oncology clinic setting. METHODS: Patients with PCa aged >or=70 years who actively were receiving androgen ablation treatment and who were followed within the clinics at the University of Chicago were eligible. Patients self-completed the VES-13 and CGA instruments and repeated the VES-13 1 month later. Physical performance and cognitive assessments were administered by a research assistant. RESULTS: Of 50 participating patients, 50% were identified as impaired by the VES-13 (score >or=3). Sixty percent of patients scored as impaired on >or=2 tests within the CGA, exhibiting deficits in multiple domains. The reliability of the VES-13 (Pearson correlation coefficient) was 0.92. The cut-off score of 3 on the VES-13 had 72.7% sensitivity and 85.7% specificity for CGA deficits and was highly predictive for identifying impairment (area under the receiver operating characteristic curve, 0.90). Patients who had mean VES-13 scores >or=3 performed significantly worse on evaluations of activities of daily living (P = .001), physical performance (P = .002), comorbidity (P = .004), and cognitive impairment (P = .003). CONCLUSIONS: Functional and cognitive impairments are highly prevalent among older patients with PCa who receive androgen ablation in oncology clinics. The current results indicated that the brief VES-13 performed nearly as well as a conventional CGA in detecting geriatric impairment in this population.

Activities of Daily Living↗
PubMed2007

Health and motivation of elderly relocating to a suburban area in Japan.

In Japan, few studies have investigated the effects of moving residence among the elderly, despite the fact that Japanese elderly will be increasingly required to switch residence in the future. Here, we used representative sampling to examine the characteristics of elderly persons who had moved residence to a Tokyo suburb and compared results with those of non-moving residents of the suburb. Movers aged 65 years old or older who had relocated within the previous 2 years (movers) and residents aged 65 years old or older and had lived in the area longer than 5 years (non-movers) were surveyed by mail in 2004, with a focus on health and psychosocial measures. Compared with non-movers (N=117), movers (N=97) were more depressed, socially isolated, and fulfilled less active social roles among family members. The majority of movers had moved to find affordable housing or to live with or near family. Two factors preceded co-residence with family, namely retirement and imminent loss of functional independence. Our findings suggest that movers require community support to prevent social isolation, dependency and health declines.

Activities of Daily Living↗