Kazushi Maruo

Comparison of bias-corrected covariance estimators for MMRM analysis in longitudinal data with dropouts.

In longitudinal clinical trials, some subjects will drop out before completing the trial, so their measurements towards the end of the trial are not obtained. Mixed-effects models for repeated measures (MMRM) analysis with “unstructured” (UN) covariance structure are increasingly common as a primary analysis for group comparisons in these trials. Furthermore, model-based covariance estimators have been routinely used for testing the group difference and estimating confidence intervals of the difference in the MMRM analysis using the UN covariance. However, using the MMRM analysis with the UN covariance could lead to convergence problems for numerical optimization, especially in trials with a small-sample size. Although the so-called sandwich covariance estimator is robust to misspecification of the covariance structure, its performance deteriorates in settings with small-sample size. We investigated the performance of the sandwich covariance estimator and covariance estimators adjusted for small-sample bias proposed by Kauermann and Carroll (J Am Stat Assoc 2001; 96: 1387–1396) and Mancl and DeRouen (Biometrics 2001; 57: 126–134) fitting simpler covariance structures through a simulation study. In terms of the type 1 error rate and coverage probability of confidence intervals, Mancl and DeRouen’s covariance estimator with compound symmetry, first-order autoregressive (AR(1)), heterogeneous AR(1), and antedependence structures performed better than the original sandwich estimator and Kauermann and Carroll’s estimator with these structures in the scenarios where the variance increased across visits. The performance based on Mancl and DeRouen’s estimator with these structures was nearly equivalent to that based on the Kenward–Roger method for adjusting the standard errors and degrees of freedom with the UN structure. The model-based covariance estimator with the UN structure under unadjustment of the degrees of freedom, which is frequently used in applications, resulted in substantial inflation of the type 1 error rate. We recommend the use of Mancl and DeRouen’s estimator in MMRM analysis if the number of subjects completing is (nu2009+u20095) or less, where n is the number of planned visits. Otherwise, the use of Kenward and Roger’s method with UN structure should be the best way.

Chronic sleep fragmentation exacerbates amyloid β deposition in Alzheimer’s disease model mice

Sleep fragmentation due to intermittent nocturnal arousal resulting in a reduction of total sleep time and sleep efficiency is a common symptom among people with Alzheimers disease (AD) and elderly people with normal cognitive function. Although epidemiological studies have indicated an association between sleep fragmentation and elevated risk of AD, a relevant disease model to elucidate the underlying mechanisms was lacking owing to technical limitations. Here we successfully induced chronic sleep fragmentation in AD model mice using a recently developed running-wheel-based device and demonstrate that chronic sleep fragmentation increases amyloid β deposition. Notably, the severity of amyloid β deposition exhibited a significant positive correlation with the extent of sleep fragmentation. These findings provide a useful contribution to the development of novel treatments that decelerate the disease course of AD in the patients, or decrease the risk of developing AD in healthy elderly people through the improvement of sleep quality.

Inference of median difference based on the Box–Cox model in randomized clinical trials

In randomized clinical trials, many medical and biological measurements are not normally distributed and are often skewed. The Box-Cox transformation is a powerful procedure for comparing two treatment groups for skewed continuous variables in terms of a statistical test. However, it is difficult to directly estimate and interpret the location difference between the two groups on the original scale of the measurement. We propose a helpful method that infers the difference of the treatment effect on the original scale in a more easily interpretable form. We also provide statistical analysis packages that consistently include an estimate of the treatment effect, covariance adjustments, standard errors, and statistical hypothesis tests. The simulation study that focuses on randomized parallel group clinical trials with two treatment groups indicates that the performance of the proposed method is equivalent to or better than that of the existing non-parametric approaches in terms of the type-I error rate and power. We illustrate our method with cluster of differentiation 4 data in an acquired immune deficiency syndrome clinical trial.

Bartlett-type corrections and bootstrap adjustments of likelihood-based inference methods for network meta-analysis

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.

Interpretable inference on the mixed effect model with the Box-Cox transformation: K. MARUO ET AL.

We derived results for inference on parameters of the marginal model of the mixed effect model with the Box-Cox transformation based on the asymptotic theory approach. We also provided a robust variance estimator of the maximum likelihood estimator of the parameters of this model in consideration of the model misspecifications. Using these results, we developed an inference procedure for the difference of the model median between treatment groups at the specified occasion in the context of mixed effects models for repeated measures analysis for randomized clinical trials, which provided interpretable estimates of the treatment effect. From simulation studies, it was shown that our proposed method controlled type I error of the statistical test for the model median difference in almost all the situations and had moderate or high performance for power compared with the existing methods. We illustrated our method with cluster of differentiation 4 (CD4) data in an AIDS clinical trial, where the interpretability of the analysis results based on our proposed method is demonstrated. Copyright

Utilization of chi-square statistics for screening adverse drug-drug interactions in spontaneous reporting systems

PurposeWe proposed a statistical criterion to detect drug-drug interactions causing adverse drug reactions in spontaneous reporting systems.MethodsThe used criterion quantitatively measures the discrepancy between the observed and expected number of adverse events via chi-square statistics. We compared the performance of our method with that of Norén et al. (Stat Med 2008; 27 (16): 3057–3070) through a simulation study.ResultsWhen the number of events for a combination of two drugs was equal to or lower than two, the false positive rate for our method ranged from 0.01 to 0.08, whereas the rate for Norén’s method ranged from 0.01 to 0.06. The sensitivity for our method ranged from 0.09 to 0.29, whereas the sensitivity for Norén’s method ranged from 0.03 to 0.24. The area-under-the-receiver operating characteristic curve for our method was significantly larger than that for Norén’s methods regardless of simulation settings. The proposed method was also applied to the Food and Drug Administration Adverse Event Reporting System database, and a recognized drug-drug interaction was detected.ConclusionsThe proposed criterion controlled false positives at an acceptable level and had higher sensitivity than that of Norén’s method had when events were rare.

A comparative study of care practices for young boys with Duchenne muscular dystrophy between Japan and European countries: Implications of early diagnosis

Early diagnosis of Duchenne muscular dystrophy (DMD) is widely advocated to initiate proactive interventions and genetic counselling. Genetic testing now allows the diagnosis of DMD even prior to the onset of symptoms. However, little is known about care practices and their impact on young DMD boys and families after receiving an early diagnosis. We analysed 64 young boys (Japan, 19; the United Kingdom, 10; Germany, 18; Hungary, 6; Poland, 5; and the Czech Republic, 6) aged <5 years and diagnosed at ≤2 years old among the participants of the cross-sectional study about care practice in DMD. A combination of elevated serum creatine kinase and genetic testing usually led to the diagnosis (nu2009=u200931, 48%); 41 boys visited neuromuscular clinics more than once a year. Early diagnosis did not generally result in higher satisfaction among DMD families, and country-specific differences were observed. Psychosocial support following early diagnosis was perceived as insufficient in most countries, and deficits in access and uptake of genetic counselling resulted in lower satisfaction in the Japanese cohort. In conclusion, seamless and comprehensive support for DMD families following early diagnosis at presymptomatic stages should be taken into consideration if early genetic testing or newborn screening is made available more widely.

Confidence intervals based on some weighting functions for the difference of two binomial proportions

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.

An Efficient Procedure for Calculating Sample Size Through Statistical Simulations

ABSTRACT While planning clinical trials, when simple formulas are unavailable to calculate sample size, statistical simulations are used instead. However, one has to spend much computation time obtaining adequately precise and accurate simulated sample size estimates, especially when there are many scenarios for the planning and/or the specified statistical method is complicated. In this article, we summarize the theoretical aspect of statistical simulation-based sample size calculation. Then, we propose a new simulation procedure for sample size calculation by fitting the probit model to simulation result data. From the theoretical and simulation-based evaluations, it is suggested that the proposed simulation procedure provide more efficient and accurate sample size estimates than ordinary algorithm-based simulation procedure especially when estimated sample sizes are moderate to large, therefore it would help to dramatically reduce the computational time required to conduct clinical trial simulations.

Analysis of an incomplete longitudinal composite variable using a marginalized random effects model and multiple imputation

The total score, which is calculated as the sum of scores in multiple items or questions, is repeatedly measured in longitudinal clinical studies. A mixed effects model for repeated measures method is often used to analyze these data; however, if one or more individual items are not measured, the method cannot be directly applied to the total score. We develop two simple and interpretable procedures that infer fixed effects for a longitudinal continuous composite variable. These procedures consider that the items that compose the total score are multivariate longitudinal continuous data and, simultaneously, handle subject-level and item-level missing data. One procedure is based on a multivariate marginalized random effects model with a multiple of Kronecker product covariance matrices for serial time dependence and correlation among items. The other procedure is based on a multiple imputation approach with a multivariate normal model. In terms of the type-1 error rate and the bias of treatment effect in total score, the marginalized random effects model and multiple imputation procedures performed better than the standard mixed effects model for repeated measures analysis with listwise deletion and single imputations for handling item-level missing data. In particular, the mixed effects model for repeated measures with listwise deletion resulted in substantial inflation of the type-1 error rate. The marginalized random effects model and multiple imputation methods provide for a more efficient analysis by fully utilizing the partially available data, compared to the mixed effects model for repeated measures method with listwise deletion.