Search

A nonparametric maximum likelihood estimator (NPMLE) of the underlying distribution in the presence of truncation, first published in the astronomy literature by Lynden-Bell in 1971, has received considerable attention in the statistics and biostatistics literature. A limitation of this useful estimator is that it relies on the independence of the variable of interest and of the truncation variable. In this paper, a generalization of this estimator is proposed, which expands the applicability of the estimator by allowing for dependence between the variable of interest and the truncation variable in the presence of a covariate. Weak convergence and asymptotic optimality in the Hajek-Beran sense (Beran, R, 1977, Estimating a distribution function. Annals of Statistics, 5, 400-404.) are shown for this generalized estimator process. A related estimator of the joint distribution of the covariate and the variable of interest is introduced, which shares the asymptotic normality and optimality of the previous estimator. Finally, simulation results are used to compare the generalization to the Lynden-Bell estimator in a variety of situations. [ABSTRACT FROM AUTHOR]

Objective: Studies suggest that parenteral MTX may be more efficacious than the oral form at equivalent doses for the treatment of rheumatoid arthritis. We carried out a meta-analysis to compare the efficacy of oral versus parenteral MTX in RA. Methods: PubMed, Web of Science and Embase were systematically searched from inception to June 8th 2017 and reviewed following PRISMA 2009 guidelines, by two independent reviewers. To be included, trials had to study adults with RA randomized to the same dose of either oral or parenteral MTX. The primary endpoint was ACR20 at 6 months. Intention-to-treat analysis results were used when possible. Data from direct comparisons between oral and parenteral methotrexate quantitatively analyzed using maximum likelihood random effects meta-analysis. Relative treatment effects were generated as an odds ratio [OR] (OR>1 indicated a benefit for parenteral therapy). Results: The search yielded 357 papers or abstracts. After review of titles or abstracts and full text papers, we found 4 that met inclusion criteria with 703 patients randomized. Dose of MTX started at 15mg/week and increased up to 25mg/week. The summary OR for achieving ACR20 using parenteral vs. oral MTX was 3.02 (95% CI 1.41, 6.46), with no significant difference in the risk for all adverse events. Conclusion: Parenteral MTX therapy had significantly higher odds than oral MTX of achieving reduction in disease activity. We propose that parenteral MTX is more effective than weekly oral MTX; its widespread use may lead to better control of disease and a decrease in demand for biologic agents. [ABSTRACT FROM AUTHOR]

Simulation studies provide an important statistical tool in evaluating survival methods, requiring an appropriate data-generating process to simulate data for an underlying statistical model. Many studies with time-to-event outcomes use the Cox proportional hazard model. While methods for simulating such data with time-invariant predictors have been described, methods for simulating data with time-varying covariates are sorely needed. Here, we describe an approach for generating data for the Cox proportional hazard model with time-varying covariates when event times follow an Exponential or Weibull distribution. For each distribution, we derive a closed-form expression to generate survival times and link the time-varying covariates with the hazard function. We consider a continuous time-varying covariate measured at regular intervals over time, as well as time-invariant covariates, in generating time-to-event data under a number of scenarios. Our results suggest this method can lead to simulation studies with reliable and robust estimation of the association parameter in Cox-Weibull and Cox-Exponential models. [ABSTRACT FROM AUTHOR]

Background. The ability to walk for short and prolonged periods of time is often measured with separate walking tests. It is unclear whether decline in the 2-minute walk coincides with decline in a shorter 20-m walk among older adults. Objective. The aim of this study was to describe patterns of change in the 20-m walk and 2-minute walk over 8 years among a large cohort of older adults. Should change be similar between tests of walking ability, separate retesting of prolonged walking may need to be reconsidered. Design. A longitudinal, observational cohort study was conducted. Methods. Data were from 1,893 older adults who were well-functioning (≥70 years of age). The 20-m walk and 2-minute walk were repeatedly measured over 8 years to measure change during short and prolonged periods of walking, respectively. Change was examined using a dual group-based trajectory model (dual model), and agreement between walking trajectories was quantified with a weighted kappa statistic. Results. Three trajectory groups for the 20-m walk and 2-minute walk were identified. More than 86% of the participants were in similar trajectory groups for both tests from the dual model. There was high chance-corrected agreement (kappa =.84; 95% confidence interval=.82, .86) between the 20-m walk and 2-minute walk trajectory groups. Limitations. One-third of the original Health, Aging and Body Composition (Health ABC) study cohort was excluded from analysis due to missing clinic visits, followed by being excluded for health reasons for performing the 2-minute walk, limiting generalizability to healthy older adults. Conclusions. Patterns of change in the 2-minute walk are similar to those in the 20-m walk. Thus, separate retesting of the 2-minute walk may need to be reconsidered to gauge change in prolonged walking. INSET: The Bottom Line. [ABSTRACT FROM AUTHOR]

Background Although increased volume of pericardial fat has been associated with decreased cardiac function, it is unclear whether this association is mediated by systemic overall obesity or direct regional fat interactions. We hypothesized that if local effects dominate, left ventricular (LV) function would be most strongly associated with pericardial fat that surrounds the left rather than the right ventricle (RV). Methods Female obese subjects (n = 60) had cardiovascular magnetic resonance (CMR) scans to obtain measures of LV function and pericardial fat volumes. LV function was obtained using the cine steady state free precession imaging in short axis orientation. The amount of pericardial fat was determined volumetrically by the cardiac gated T1 black blood imaging and normalized to body surface area. Results In this study cohort, LV fat correlated with several LV hemodynamic measurements including cardiac output (r = -0.41, p = 0.001) and stroke volume (r = -0.26, p = 0.05), as well as diastolic functional parameters including peak-early-filling rate (r = -0.38, p = 0.01), early late filling ratio (r = -0.34, p = 0.03), and time to peak-early-filling (r = 0.34, p = 0.03). These correlations remained significant even after adjusting for the body mass index and the blood pressure. However, similar correlations became weakened or even disappeared between RV fat and LV function. LV function was not correlated with systemic plasma factors, such as C-reactive protein (CRP), B-type natriuretic peptide (BNP), Interleukin-6 (IL-6), resistin and adiponectin (all p > 0.05). Conclusions LV hemodynamic and diastolic function was associated more with LV fat as compared to RV or total pericardial fat, but not with systemic inflammatory markers or adipokines. The correlations between LV function and pericardial fat remained significant even after adjusting for systemic factors. These findings suggest a site-specific influence of pericardial fat on LV function, which could imply local secretion of molecules into the underlying tissue or an anatomic effect, both mechanisms meriting future evaluation. [ABSTRACT FROM AUTHOR]