Search

In this paper, we propose two new methods for computing confidence intervals for the difference of two independent binomial proportions in small sample cases. Several test-based exact confidence intervals have been developed to guarantee the nominal coverage probability in small sample cases. However, these methods are sometimes unnecessarily too conservative because they use the exact p-value for constructing confidence intervals by maximizing the tail probability to account for the worst configuration. In order to reduce conservatism, our new methods adopt the p-value weighted by two types of functions instead of the maximum p-value. Our proposed methods can be regarded as quasi-exact methods. The performance evaluation results showed that our methods are much less conservative than the exact method. Compared with other existing quasi-exact methods, generally, our methods possess coverage probabilities closer to the nominal confidence level and shorter expected confidence widths. In particular, the beta weighing method provides the most reasonable balance between accurate coverage probability and short interval width in small sample cases., (Copyright © 2014 John Wiley & Sons, Ltd.)

Aim: Radio‐Taiso, a traditional exercise program in Japan, may serve as a coping strategy for older adults with frailty during the COVID‐19 pandemic. This phase II trial tested program adherence and safety and explored the potential effectiveness of a home‐based Radio‐Taiso. Methods: This assessor‐blind parallel randomized controlled trial included community‐dwelling Jolder Japanese adults with frailty and pre‐frailty. Fifty‐eight eligible participants were randomly allocated to intervention and control groups. Intervention participants performed 3–5‐min sessions of Radio‐Taiso one to four times per day for 12 weeks. Feasibility criteria were set at practice and retention rates of ≥75%. Safety was monitored by assessing all adverse events reported by participants during the intervention period, irrespective of causality. Potential effectiveness was exploratorily assessed using items that allow clinical interpretation of changes: mobility and health‐related quality of life (HR‐QoL), assessed using the modified short physical performance battery (SPPB) and the SF‐36, respectively. Results: Both practice (83%) and retention rates (100%) met the predetermined feasibility criteria. Eleven adverse events were reported but were supposedly unrelated to the intervention. In the intention‐to‐treat analysis, there was no clinically significant difference in the change in SPPB score between groups (−0.4 points, 95% confidence interval [CI], −1.2, 0.3); however, the intervention group scored higher in the mental component of HR‐QoL than did the control group (3.4 points, 95% CI: −1.1, 7.8). Conclusions: The preliminary data indicate that a phase III trial is feasible, focusing on the mental aspect of HR‐QoL as the primary outcome. Geriatr Gerontol Int 2023; 23: 32–37. [ABSTRACT FROM AUTHOR]

Aim: This study examined the relationship between continuity of social participation and progression of frailty among community‐dwelling older adults, by baseline frailty level. Methods: This study was part of a 3‐year community‐based cohort study among adults aged ≥65 years, living independently in a rural municipality in Japan. Mail surveys were carried out in 2016, 2018 and 2019. This study involved 2799 participants who responded to the question about social participation in every survey. Frailty was evaluated by Kihon Checklist total scores. Social participation was categorized into consistent non‐participation, interrupted recent non‐participation, interrupted recent participation and consistent participation. We assessed the relationship between social participation and change in frailty scores using general linear regression analysis, stratifying the participants into groups by their frailty level at baseline. Results: There was a smaller frailty score increase in the robust (β −0.61, 95% CI −0.99 to −0.22) and prefrail groups (β −0.73, 95% CI −1.18 to −0.27) for consistent participation than consistent non‐participation. Interrupted recent participation showed significant suppression in the prefrail group (β −0.96, 95% CI −1.60 to −0.32). Social participation had no clear effect on progression in the frail group. Conclusions: Consistent social participation might reduce the progression of frailty in robust and prefrail people. Inconsistent participation might also help to reduce progression in prefrail older adults. It is important for prefrail older adults to return to their social activities and continue to engage as long as possible, even if their participation was intermittent in the past. Geriatr Gerontol Int 2023; 23: 25–31. [ABSTRACT FROM AUTHOR]

Aim: Identification of modifiable intrinsic factors for occupational falls is required for initiating effective fall prevention strategies for older workers. This study aimed to identify modifiable intrinsic factors related to falls during occupational activities among older workers. Methods: This retrospective study involved 1164 older workers (aged ≥60 years, workdays ≥4/month) sampled from 18 public employment agencies for seniors in Saitama, Japan. Participants were assessed regarding the following 10 modifiable intrinsic factors: multimorbidity, polypharmacy, fall‐risk‐increasing medication use, self‐rated vision and hearing, functional strength, bilateral stepping, standing balance, executive function and visuospatial ability. The number of falls during occupational activities in the past year was also recorded. Results: In total, 111 falls occurred in 73 of the 1164 participants during occupational activities in the past year. A negative binomial regression model showed that use of fall‐risk‐increasing medications (incidence rate ratio [IRR]: 2.23, 95% confidence interval [CI]: 1.08, 4.60, P = 0.031), reduced functional strength (IRR: 1.81, 95% CI: 1.02, 3.21, P = 0.042), poor standing balance (IRR: 1.83, 95% CI: 1.09, 3.09, P = 0.023) and poor visuospatial ability (IRR: 1.56, 95% CI: 1.03, 2.36, P = 0.034) were independently associated with occupational falls. Conclusions: Our findings suggest that the assessment of medication use, functional strength, standing balance and visuospatial ability in regular health checks in the workplace may be useful for screening older workers at risk of occupational falls. Geriatr Gerontol Int 2022; 22: 338–343. [ABSTRACT FROM AUTHOR]

Summary: Mixed‐effects models for repeated measures (MMRMs) with an 'unstructured' (UN) covariance structure are frequently used in primary analyses for group comparisons of incomplete continuous longitudinal data from drug development trials. However, MMRM‐UN analysis could lead to convergence problems in numerical optimisation, especially in trials with a small sample size or high dropout rate. Although the so‐called sandwich covariance estimator is robust against the misspecification of the covariance structure, its performance deteriorates for small sample sizes. We review eight modified covariance estimators adjusted for small‐sample bias and compare their performances in the framework of MMRM analysis through simulations. In terms of the type 1 error rate and coverage probability of confidence intervals for group comparisons, Mancl and DeRouen's covariance estimator (MD) shows the best performance among the modified covariance estimators, followed by Fay and Graubard's estimator. The performance of MD is nearly equivalent to that of the Kenward–Roger method with a UN structure. The Kenward–Roger method with first‐order autoregressive structure results in substantial inflation of the type 1 error rate in the scenario where the variance of measurements increases across visits. In summary, we recommend the use of MD in MMRM analysis if the convergence problem involving a UN structure occurs in small clinical trials. [ABSTRACT FROM AUTHOR]

Objectives: To examine factors that may affect the use and duration of seclusion and restraint (SR) in psychiatric inpatient settings. Methods: First, multivariable logistic regression analysis was used to examine factors associated with the use of SR in an unmatched case-control study, comparing SR cases and controls. Second, for patients that underwent SR, multivariable linear regression analysis was used to determine factors contributing to the duration of SR. Results: Out of 213 patients, 58 underwent SR. An F00 diagnosis, a history of epilepsy, antipsychotics usage and antidepressants usage were significantly associated with the use of SR (odds ratio = 7.98; 95% CI = 1.11–57.50, odds ratio = 4.89; 95% CI = 1.12–21.36, odds ratio = 4.59; 95% CI = 1.54–13.68 and odds ratio = 0.29; 95% CI = 0.10–0.86, respectively). An F00 and F32 diagnosis significantly extended the duration of SR (coefficient = 13.10; 95% CI = 2.11–24.11 and coefficient = 20.52; 95% CI = 9.68–31.37, respectively). Conclusions: A variety of factors are associated with the use and longer duration of SR. Given the potentially harmful effects of these practices, further studies with larger samples and a wider range of quantitative outcome measures are warranted. An F00 diagnosis, a history of epilepsy and antipsychotics usage may increase the use of SR. Antidepressants may decrease the use of SR. An F00 and F32 diagnosis may extend the duration of SR. [ABSTRACT FROM AUTHOR]

In network meta-analyses that synthesize direct and indirect comparison evidence concerning multiple treatments, multivariate random effects models have been routinely used for addressing between-studies heterogeneities. Although their standard inference methods depend on large sample approximations (eg, restricted maximum likelihood estimation) for the number of trials synthesized, the numbers of trials are often moderate or small. In these situations, standard estimators cannot be expected to behave in accordance with asymptotic theory; in particular, confidence intervals cannot be assumed to exhibit their nominal coverage probabilities (also, the type I error probabilities of the corresponding tests cannot be retained). The invalidity issue may seriously influence the overall conclusions of network meta-analyses. In this article, we develop several improved inference methods for network meta-analyses to resolve these problems. We first introduce 2 efficient likelihood-based inference methods, the likelihood ratio test-based and efficient score test-based methods, in a general framework of network meta-analysis. Then, to improve the small-sample inferences, we developed improved higher-order asymptotic methods using Bartlett-type corrections and bootstrap adjustment methods. The proposed methods adopt Monte Carlo approaches using parametric bootstraps to effectively circumvent complicated analytical calculations of case-by-case analyses and to permit flexible application to various statistical models network meta-analyses. These methods can also be straightforwardly applied to multivariate meta-regression analyses and to tests for the evaluation of inconsistency. In numerical evaluations via simulations, the proposed methods generally performed well compared with the ordinary restricted maximum likelihood-based inference method. Applications to 2 network meta-analysis datasets are provided. [ABSTRACT FROM AUTHOR]

The authors propose several estimation methods for the confidence interval of the percentile of the power-normal distribution, which specifies the distribution of the observed values before Box-Cox transformation and assumes that transformed distribution is the truncated normal distribution. Their approaches are based on the delta method and the inverse transformation method. Then the finite sample performance of each estimation method is compared through a simulation, and it is shown that the performance of the inverse transformation method is superior to the delta method. A reparametrization method of the power-normal distribution, which is useful parameter setting tool in simulations, is suggested. The authors also investigate the asymptotic behavior of the coverage probability of the confidence interval of the percentile of the power-normal distribution in the case wherein the variance inflation of the MLE associated with the estimation of the transformation parameter of the power-normal distribution is ignored. [ABSTRACT FROM AUTHOR]

• Frailty is a risk factor for insomnia, insomnia is also a risk factor for frailty. • Insomnia and frailty were equally associated with each other in all participants. • The primary potential cause of the association varied by sex. • Effect of frailty on insomnia was stronger than that of insomnia on frailty in men. • Impact of insomnia on frailty was greater than that of frailty on insomnia in women. Most previous studies that examined the association of insomnia with frailty used cross-sectional designs. The temporal relationship between these factors is therefore largely unknown. This study aimed to examine the bidirectional relationship between insomnia and frailty by sex. A 2-year longitudinal study involving all community-dwelling older adults living in a rural area in Japan (n = 3844). Validated measures of insomnia and frailty were employed. Insomnia was assessed using the Athens insomnia scale, and frailty using the Kihon checklist. We performed a cross-lagged panel model, adjusted for age, sex, years of education, employment status, self-rated health, complications (hypertension, diabetes, stroke, or osteoarthritis), BMI, physical activity, alcohol consumption, and smoking status, and assessed differences by sex. Poor sleep predicted the onset and worsening of frailty during follow up (standardized coefficient [95% confidence interval]: 0.076 [0.045, 0.107]). Frailty also predicted severe insomnia symptoms (0.074 [0.044, 0.104]). However, the temporal association between these conditions varied by sex. In older men, the effect of frailty on insomnia was stronger than that of insomnia on frailty. However, in women, the impact of insomnia on frailty was stronger than that of frailty on insomnia. The primary potential cause of the association between insomnia and frailty may vary by sex, being frailty in men and insomnia in women. Sex-specific interventions to improve sleep quality and duration, and maintain functional abilities in daily life may contribute to the prevention and management of both frailty and insomnia in older adults. [ABSTRACT FROM AUTHOR]