Sequential selection procedures and false discovery rate control G'Sell, Max Grazier; Wager, Stefan; Chouldechova, Alexandra ...
Journal of the Royal Statistical Society. Series B, Statistical methodology,
March 2016, Letnik:
78, Številka:
2
Journal Article
Recenzirano
Odprti dostop
We consider a multiple‐hypothesis testing setting where the hypotheses are ordered and one is only permitted to reject an initial contiguous block H1,…,Hk of hypotheses. A rejection rule in this ...setting amounts to a procedure for choosing the stopping point k. This setting is inspired by the sequential nature of many model selection problems, where choosing a stopping point or a model is equivalent to rejecting all hypotheses up to that point and none thereafter. We propose two new testing procedures and prove that they control the false discovery rate in the ordered testing setting. We also show how the methods can be applied to model selection by using recent results on p‐values in sequential model selection settings.
This article consists of a collection of slides from the author's conference presentation. Some of the specific areas/topics discussed include: smart grid interoperability panel; IEC 61850-3:2002; ...IEEE 1613.1; utility EMC standards; IEEE P1613; immunity tests; monitoring complexities; electrostatic discharge; radiated RF immunity; substations; electrical fast transient-bursts; conducted RF immunity; power frequency magnetic field; damped oscillatory magnetic fields; DC supply ripple; AC dips-interrupts; DC dips-interrupts; damped oscillatory wave; RFI hazards; intelligent electronic devices; electric power transmission facilities; and electric power distribution facilities.
We update a previous systematic review to inform new World Health Organization HIV self-testing (HIVST) recommendations. We compared the effects of HIVST to standard HIV testing services to ...understand which service delivery models are effective for key populations.
We did a systematic review of randomised controlled trials (RCTs) which compared HIVST to standard HIV testing in key populations, published from 1 January 2006 to 4 June 2019 in PubMed, Embase, Global Index Medicus, Social Policy and Practice, PsycINFO, Health Management Information Consortium, EBSCO CINAHL Plus, Cochrane Library and Web of Science. We extracted study characteristic and outcome data and conducted risk of bias assessments using the Cochrane ROB tool version 1. Random effects meta-analyses were conducted, and pooled effect estimates were assessed along with other evidence characteristics to determine the overall strength of the evidence using GRADE methodology.
After screening 5909 titles and abstracts, we identified 10 RCTs which reported on testing outcomes. These included 9679 participants, of whom 5486 were men who have sex with men (MSM), 72 were trans people and 4121 were female sex workers. Service delivery models included facility-based, online/mail and peer distribution. Support components were highly diverse and ranged from helplines to training and supervision. HIVST increased testing uptake by 1.45 times (RR=1.45 95% CI 1.20, 1.75). For MSM and small numbers of trans people, HIVST increased the mean number of HIV tests by 2.56 over follow-up (mean difference = 2.56; 95% CI 1.24, 3.88). There was no difference between HIVST and SoC in regard to positivity among tested overall (RR = 0.91; 95% CI 0.73, 1.15); in sensitivity analysis of positivity among randomised HIVST identified significantly more HIV infections among MSM and trans people (RR = 2.21; 95% CI 1.20, 4.08) and in online/mail distribution systems (RR = 2.21; 95% CI 1.14, 4.32). Yield of positive results in FSW was not significantly different between HIVST and SoC. HIVST reduced linkage to care by 17% compared to SoC overall (RR = 0.83; 95% CI 0.74, 0.92). Impacts on STI testing were mixed; two RCTs showed no decreases in STI testing while one showed significantly lower STI testing in the intervention arm. There were no negative impacts on condom use (RR = 0.95; 95% CI 0.83, 1.08), and social harm was very rare.
HIVST is safe and increases testing uptake and frequency as well as yield of positive results for MSM and trans people without negative effects on linkage to HIV care, STI testing, condom use or social harm. Testing uptake was increased for FSW, yield of positive results were not and linkage to HIV care was worse. Strategies to improve linkage to care outcomes for both groups are crucial for effective roll-out.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Internet of Things (IoT) systems are becoming prevalent in various domains, from healthcare to smart homes. Testing IoT systems is critical in ensuring their reliability. Previous papers studied ...separately the objectives, approaches, tools, and challenges of IoT systems testing. However, despite the rapid evolution of the IoT domain, no review has been undertaken to investigate all four aspects collectively. This paper presents a systematic literature review that aggregates, synthesizes, and discusses the results of 83 primary studies (PSs) concerning IoT testing objectives, approaches, tools, and challenges. We followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol to report our findings and answer research questions (RQs). To select PSs, we applied inclusion and exclusion criteria to relevant studies published between 2012 and 2022. We extracted and analyzed the data from PSs to understand IoT systems testing. The results reveal that IoT systems testing embraces traditional software quality attributes but also introduces new ones like connectivity, energy efficiency, device lifespan, distributivity, and dynamicity. They also show that existing IoT systems testing approaches are limited to specific aspects and should be expanded for more comprehensive testing. They also show 19 testing tools and 15 testbeds for testing IoT systems with their limitations, necessitating the development or enhancement for wider coverage. The large number of heterogeneous devices generating data in different formats, along with the need for testing in real-world scenarios, poses a challenge. Thus, our study offers insights into the testing objectives, approaches, tools, and challenges associated with IoT systems. Based on the results, we also provide practical guidance for IoT practitioners by cataloging existing tools and approaches, while also identifying new research opportunities for interested researchers.
The stress test is key to the clinical evaluation and management of patients with known or potential cardiovascular disease. By measuring the heart's ability to respond to external stress, it can ...provide vital insights into the general physical condition of patients, highlighting abnormalities in blood flow, risk of coronary artery disease, and more. The Pocket Guide to Stress Testing gives cardiology professionals a complete breakdown of this everyday procedure that they can carry with them and consult on the go.
This second edition has been fully revised to reflect the most up-to-date information available on the best approaches to conducting and interpreting various forms of stress test. With chapters spanning topics such as testing guidelines, nuclear imaging techniques, and emergency and aftercare protocols, the clear and practical contents cover all aspects of the subject.
Complex multivariate testing problems are frequently encountered in many scientific disciplines, such as engineering, medicine and the social sciences. As a result, modern statistics needs ...permutation testing for complex data with low sample size and many variables, especially in observational studies.
•We address the topic of fully automatic event-based testing of Android mobile apps.•We present a framework abstracting common characteristics of testing techniques.•We recast 38 existing Android ...online testing techniques according to the framework.•The framework is usable for designing experiments and comparing testing techniques.•We experimentally compare performance of automatic techniques using the framework.
As an increasing number of new techniques are developed for quality assurance of Android applications (apps), there is a need to evaluate and empirically compare them. Researchers as well as practitioners will be able to use the results of such comparative studies to answer questions such as, “What technique should I use to test my app?” Unfortunately, there is a severe lack of rigorous empirical studies on this subject. In this paper, for the first time, we present an empirical study comparing all existing fully automatic “online” testing techniques developed for the Android platform. We do so by first reformulating each technique within the context of a general framework. We recognize the commonalities between the techniques to develop the framework. We then use the salient features of each technique to develop parameters of the framework. The result is a general recasting of all existing approaches in a plug-in based formulation, allowing us to vary the parameters to create instances of each technique, and empirically evaluate them on a common set of subjects. Our results show that (1) the proposed general framework abstracts all the common characteristics of online testing techniques proposed in the literature, (2) it can be exploited to design experiments aimed at performing objective comparisons among different online testing approaches and (3) some parameters that we have identified influence the performance of the testing techniques.
Although awareness of familial hypercholesterolemia (FH) is increasing, this common, potentially fatal, treatable condition remains underdiagnosed. Despite FH being a genetic disorder, genetic ...testing is rarely used. The Familial Hypercholesterolemia Foundation convened an international expert panel to assess the utility of FH genetic testing. The rationale includes the following: 1) facilitation of definitive diagnosis; 2) pathogenic variants indicate higher cardiovascular risk, which indicates the potential need for more aggressive lipid lowering; 3) increase in initiation of and adherence to therapy; and 4) cascade testing of at-risk relatives. The Expert Consensus Panel recommends that FH genetic testing become the standard of care for patients with definite or probable FH, as well as for their at-risk relatives. Testing should include the genes encoding the low-density lipoprotein receptor (LDLR), apolipoprotein B (APOB), and proprotein convertase subtilisin/kexin 9 (PCSK9); other genes may also need to be considered for analysis based on patient phenotype. Expected outcomes include greater diagnoses, more effective cascade testing, initiation of therapies at earlier ages, and more accurate risk stratification.
The non-destructive testing of concrete structures with methods such as ultrasonic pulse velocity and Schmidt rebound hammer test is of utmost technical importance. Non-destructive testing methods do ...not require sampling, and they are simple, fast to perform, and efficient. However, these methods result in large dispersion of the values they estimate, with significant deviation from the actual (experimental) values of compressive strength. In this paper, the application of artificial neural networks (ANNs) for predicting the compressive strength of concrete in existing structures has been investigated. ANNs have been systematically used for predicting the compressive strength of concrete, utilizing both the ultrasonic pulse velocity and the Schmidt rebound hammer experimental results, which are available in the literature. The comparison of the ANN-derived results with the experimental findings, which are in very good agreement, demonstrates the ability of ANNs to estimate the compressive strength of concrete in a reliable and robust manner. Thus, the (quantitative) values of weights for the proposed neural network model are provided, so that the proposed model can be readily implemented in a spreadsheet and accessible to everyone interested in the procedure of simulation.