Search

Summary: Instrumental variables are widely used for estimating causal effects in the presence of unmeasured confounding. Under the standard instrumental variable model, however, the average treatment effect is only partially identifiable. To address this, we propose novel assumptions that enable identification of the average treatment effect. Our identification assumptions are clearly separated from model assumptions that are needed for estimation, so researchers are not required to commit to a specific observed data model in establishing identification. We then construct multiple estimators that are consistent under three different observed data models, and multiply robust estimators that are consistent in the union of these observed data models. We pay special attention to the case of binary outcomes, for which we obtain bounded estimators of the average treatment effect that are guaranteed to lie between −1 and 1. Our approaches are illustrated with simulations and a data analysis evaluating the causal effect of education on earnings. [ABSTRACT FROM AUTHOR]

In many epidemiology studies, family data with survival endpoints are collected to investigate the association between risk factors and disease incidence. Sometimes the risk of the disease may change when a certain risk factor exceeds a certain threshold. Finding this threshold value could be important for disease risk prediction and diseases prevention. In this work, we propose a change-point proportional hazards model for clustered event data. The model incorporates the unknown threshold of a continuous variable as a change point in the regression. The marginal pseudo-partial likelihood functions are maximized for estimating the regression coefficients and the unknown change point. We develop a supremum test based on robust score statistics to test the existence of the change point. The inference for the change point is based on the m out of n bootstrap. We establish the consistency and asymptotic distributions of the proposed estimators. The finite-sample performance of the proposed method is demonstrated via extensive simulation studies. Finally, the Strong Heart Family Study dataset is analyzed to illustrate the methods. [ABSTRACT FROM AUTHOR]

Introduction or background: Crowdfunding and crowdsourcing of medical research has emerged as a novel paradigm for many biomedical disciplines to rapidly collect, process and interpret data from high-throughput and highdimensional experiments. The novelty and promise of these approaches have led to fundamental discoveries about RNA mechanisms, microbiome dynamics and even patient interpretation of test results. However, these methods require robust training protocols, uniform sampling methods and experimental rigor in order to be useful for subsequent research efforts. Executed correctly, crowdfunding and crowdsourcing can leverage public resources and engagement to generate support for scientific endeavors that would otherwise be impossible due to funding constraints and or the large number of participants needed for data collection. Sources of data: We conducted a comprehensive literature review of scientific studies that utilized crowdsourcing and crowdfunding to generate data. We also discuss our own experiences conducting citizen-science research initiatives (MetaSUB and PathoMap) in ensuring data robustness, educational outreach and public engagement. Areas of agreement: We demonstrate the efficacy of crowdsourcing mechanisms for revolutionizing microbiome and metagenomic research to better elucidate the microbial and genetic dynamics of cities around the world (as well as non-urban areas). Crowdsourced studies have been able to create an improved and unprecedented ability to monitor, design and measure changes at the microbial and macroscopic scale. Thus, the use of crowdsourcing strategies has dramatically altered certain genomics research to create global citizen-science initiatives that reveal new discoveries about the world's genetic dynamics. Areas of controversy: The effectiveness of crowdfunding and crowdsourcing is largely dependent on the study design and methodology. One point of contention for the present discussion is the validity and scientific rigor of data that are generated by non-scientists. Selection bias, limited sample sizes and limitations for scientists in enforcing standardized protocols are all challenges for those who engage in citizen-science initiatives. Growing points: Despite the aforementioned concerns, crowdsourced data allow for greater inroads into the field of personalized medicine, whereby community members take an active role in generating data about their personal and environmental health. Areas timely for developing research: Crowdsourced viral and metagenomic studies are the next step in elucidating the genomic and epigenomic characterization of urban population health. [ABSTRACT FROM AUTHOR]