Empirical evaluation of the implementation of the EMA guideline on missing data in confirmatory clinical trials: Specification of mixed models for longitudinal data in study protocols

In confirmatory clinical trials, the prespecification of the primary analysis model is a universally accepted scientific principle to allow strict control of the type I error. Consequently, both the ICH E9 guideline and the European Medicines Agency (EMA) guideline on missing data in confirmatory clinical trials require that the primary analysis model is defined unambiguously. This requirement applies to mixed models for longitudinal data handling missing data implicitly. To evaluate the compliance with the EMA guideline, we evaluated the model specifications in those clinical study protocols from development phases II and III submitted between 2015 and 2018 to the Ethics Committee at Hannover Medical School under the German Medicinal Products Act, which planned to use a mixed model for longitudinal data in the confirmatory testing strategy. Overall, 39 trials from different types of sponsors and a wide range of therapeutic areas were evaluated. While nearly all protocols specify the fixed and random effects of the analysis model (95%), only 77% give the structure of the covariance matrix used for modeling the repeated measurements. Moreover, the testing method (36%), the estimation method (28%), the computation method (3%), and the fallback strategy (18%) are given by less than half the study protocols. Subgroup analyses indicate that these findings are universal and not specific to clinical trial phases or size of company. Altogether, our results show that guideline compliance is to various degrees poor and consequently, strict type I error rate control at the intended level is not guaranteed.     

On a control chart for the Gini index with simulations

In this work we suggest the use of the Gini index on control charts. The asymptotic properties of Gini index are presented and the control charts based on appropriate confidence intervals are constructed. The suitability of the proposed charts are investigated by means of extensive simulations.     

Kernel naive Bayes discrimination for high‐dimensional pattern recognition

Kernel discriminant analysis translates the original classification problem into feature space and solves the problem with dimension and sample size interchanged. In high‐dimension low sample size (HDLSS) settings, this reduces the ‘dimension’ to that of the sample size. For HDLSS two‐class problems we modify Mika's kernel Fisher discriminant function which – in general – remains ill‐posed even in a kernel setting; see Mika et al. (1999). We propose a kernel naive Bayes discriminant function and its smoothed version, using first‐ and second‐degree polynomial kernels. For fixed sample size and increasing dimension, we present asymptotic expressions for the kernel discriminant functions, discriminant directions and for the error probability of our kernel discriminant functions. The theoretical calculations are complemented by simulations which show the convergence of the estimators to the population quantities as the dimension grows. We illustrate the performance of the new discriminant rules, which are easy to implement, on real HDLSS data. For such data, our results clearly demonstrate the superior performance of the new discriminant rules, and especially their smoothed versions, over Mika's kernel Fisher version, and typically also over the commonly used naive Bayes discriminant rule.     

Problem Gambling and Delinquent Behaviours Among Adolescents: A Scoping Review

Despite many studies indicating an association between problem gambling and delinquent behaviours among adolescents, there has been no effort to systematically analyze the state of the literature on this relationship. To fill this gap, we conducted a scoping review of the literature published between 2000 and 2016 on problem gambling and delinquent behaviours among adolescents. We searched twelve databases and reviewed reference lists to identify eligible studies. Search terms included a combination of medical subject headings and keywords for gambling, youth, and delinquency, which were combined with the Boolean operator “AND”. 1795 studies were identified through the literature search. Nine studies were eligible for inclusion. All of the studies were conducted in North America, with primarily male participants, and most of the data were cross-sectional. No qualitative studies met the inclusion criteria. Screening tools used to measure problem gambling were inconsistent, making comparisons across studies difficult. We found a consistent moderate to strong association between problem gambling and delinquent behaviour. Only one study presented associations by socio-economic status and none considered gender, sex or ethnic differences. Studies in the review showed that problem gambling is associated with both violent and non-violent behaviours among adolescents. These associations may suggest that problem gambling and delinquent behaviours have common risk factors and reflect a syndrome of risky behaviours best targeted through prevention and treatment that is holistic and considers the context in which the youth is situated. Further research is warranted to better understand the relationship between problem gambling and delinquent behaviours.     

Barriers and Facilitators of Responding to Problem Gambling: Perspectives from Australian Mental Health Services

Despite high rates of comorbidity between problem gambling and mental health disorders, few studies have examined barriers or facilitators to the implementation of screening for problem gambling in mental health services. This exploratory qualitative study identified key themes associated with screening in mental health services. Semi-structured interviews were undertaken with 30 clinicians and managers from 11 mental health services in Victoria, Australia. Major themes and subthemes were identified using qualitative content analysis. Six themes emerged including competing priorities, importance of routine screening, access to appropriate screening tools, resources, patient responsiveness and workforce development. Barriers to screening included a focus on immediate risk as well as gambling being often considered as a longer-term concern. Clinicians perceived problem gambling as a relatively rare condition, but did acknowledge the need for brief screening. Facilitators to screening were changes to system processes, such as identification of an appropriate brief screening instrument, mandating its use as part of routine screening, as well as funded workforce development activities in the identification and management of problem gambling.     

Understanding engagement in the Program of Assertive Community Treatment (PACT) from the perspectives of individuals receiving treatment

ABSTRACT

Engagement of individuals with serious mental illnesses in community mental health services is a significant challenge. The Program of Assertive Community Treatment (PACT) is an individual-centered and self-contained mental health program that provides psychiatric treatment, rehabilitation, and support services to persons with serious mental illness who have a history of or likelihood of disengagement with services. Understanding what helps and hinders consumers’ involvement in PACT services may provide information on how to tailor engagement strategies to individuals based on their treatment needs and preferences. The current study builds on existing studies by exploring factors that help and hinder engagement in PACT services from the perspectives of individuals receiving treatment. We conducted open-ended, semi-structured interviews with 17 individuals receiving PACT services. Nine themes were identified through thematic analysis: Desirable qualities of PACT, Focusing on positive outcomes, PACT as a safety net, Recovery orientation, Practical barriers, Conflictual relationships, and Medication side-effects. We conclude that the development of a trusting, therapeutic relationship that is collaborative and person-centered and that is facilitated by both practical and emotional support is critical to engaging individuals in treatment and maximizing positive outcomes.     

On Comparing Alternative Advertising Policies of Pulsation*

In this paper, five alternative advertising policies that belong to the advertising pulsation class are compared analytically for linear and concave response functions using a modified version of the Vidale-Wolfe model. The results of the research show that (1) For both linear and concave response functions, advertising pulsing/maintenance policy dominates advertising pulsing policy but is dominated by the Uniform Advertising Policy. For convex response functions, the order of dominance is reversed. (2) For linear response functions, uniform advertising policy dominates the impulse advertising policy but is dominated by the chattering advertising policy. (3) For concave response functions, uniform advertising policy dominates both the impulse advertising policy and the chattering advertising policy. (4) For convex response functions, chattering advertising policy dominates both the advertising pulsing policy and the impulse advertising policy. The Vidale-Wolfe model is estimated using the well-known Lydia Pinkham data. Optimality analysis shows that the company was overadvertising about half of the time studied. Overadvertising seems to have produced appreciable gain in sales and created significant barriers to competitive entry at a little cost in terms of foregone profits.     

Faculty Performance Evaluation: Modeling to Improve Personnel Decisions*

Based on likely future changes in faculty evaluation practices, this paper examines how institutions of higher education might operationalize performance evaluation as related to research, teaching, and service. A model is developed that allows coupling performance evaluation and relevant market considerations with merit pay, tenure, and promotion decisions. The approach is specifically applicable to tenure-track faculty members in colleges and universities.