Journal of the Royal Statistical Society Series A-Statistics in Society最新文献

Opioid misuse is a national epidemic and a significant drug related threat to the United States. While the scale of the problem is undeniable, estimates of the local prevalence of opioid misuse are lacking, despite their importance to policy-making and resource allocation. This is due, in part, to the challenge of directly measuring opioid misuse at a local level. In this paper, we develop a Bayesian hierarchical spatio-temporal abundance model that integrates indirect county-level data on opioid-related outcomes with state-level survey estimates on prevalence of opioid misuse to estimate the latent county-level prevalence and counts of people who misuse opioids. A simulation study shows that our integrated model accurately recovers the latent counts and prevalence. We apply our model to county-level surveillance data on opioid overdose deaths and treatment admissions from the state of Ohio. Our proposed framework can be applied to other applications of small area estimation for hard to reach populations, which is a common occurrence with many health conditions such as those related to illicit behaviors.

I would like to thank Sylvia for a wonderful Presidential Address tonight. It feels like a different world from my own Presidential address delivered in the first year of my presidency in June 2019. In it, I concluded that the RSS for nearly 200 years has at its heart been about using data for the public good, while developing the statistical science and building the statistical capacity required to do that. My Presidential predecessors had identified many challenges that are still with us. In addition, I opined that we faced important new challenges. These include providing health and social care for people with increasing levels of multimorbidity, coupled with the pensions' crisis as people are living longer lives and also the effects of climate change as two areas where statisticians can make contributions. Those challenges have not gone away but, as Sylvia so eloquently describes, we had no idea of the scale of new challenge that was about to hit us.

Just over 6 months later, the world changed beyond recognition with the advent of SARS-CoV-2. Statisticians, along with many others, tried to get to grips and contribute to a huge range of issues in timelines and in a context that is unprecedented. As President, I was hugely grateful to Sylvia and David Spiegelhalter for agreeing to co-chair the RSS's Covid-19 Task Force, which co-ordinated the Society's response, as well as the group undertaking fearsome amounts of work themselves. Sylvia's magisterial Presidential address documents and reflects on the extraordinary work done under their leadership.

Building on some of Sylvia's themes, I would like to make some personal reflections on how the scientific community, including statisticians, achieved such a lot in such a short time, and to me, the key is a firm grounding of principles and preparedness, coupled with flexibility and agility. Sylvia mentions the REACT studies, and to declare my interests, I was an investigator in those. The reason the team was able to mount those studies so well and so quickly was combination of prior experience in large population studies in other clinical areas, combined with a huge logistical exercise between academic, government and private partners, the scale of which I only now fully appreciate. The pace of data coming in, reports being drafted, headlines feeding into policy arenas, then full reports being put in the public domain within days was in complete contrast to the painstaking ways epidemiologists traditionally work, but gave rise to a huge sense of satisfaction. The Covid19 Task Force generously played a pivotal role at the development stage of the REACT protocols, giving helpful critical feedback to improve the study designs by return that would normally take months through the normal academic grant-giving process.

In my own presidential address, I had presciently flagged up adaptive platform trials, describing them as the evolution of the Rothamsted ‘long-term experiments’. Sylvi

The statistical community mobilised vigorously from the start of the 2020 SARS-CoV-2 pandemic, following the RSS's long tradition of offering our expertise to help society tackle important issues that require evidence-based decisions. This address aims to capture the highlights of our collective engagement in the pandemic, and the difficulties faced in delivering statistical design and analysis at pace and in communicating to the wider public the many complex issues that arose. I argue that these challenges gave impetus to fruitful new directions in the merging of statistical principles with constraints of agility, responsiveness and societal responsibilities. The lessons learned from this will strengthen the long-term impact of the discipline and of the Society. The need to evaluate policies even in emergency, and to strive for statistical interoperability in future disease surveillance systems is highlighted. In my final remarks, I look towards the future landscape for statistics in the fast-moving world of data science and outline a strategy of visible and growing engagement of the RSS with the data science ecosystem, building on the central position of statistics.

We propose a new framework to model the COVID-19 epidemic of the United Kingdom at the local authority level. The model fits within a general framework for semi-mechanistic Bayesian models of the epidemic based on renewal equations, with some important innovations, including a random walk modelling the reproduction number, incorporating information from different sources, including surveys to estimate the time-varying proportion of infections that lead to reported cases or deaths, and modelling the underlying infections as latent random variables. The model is designed to be updated daily using publicly available data. We envisage the model to be useful for now-casting and short-term projections of the epidemic as well as estimating historical trends. The model fits are available on a public website: https://imperialcollegelondon.github.io/covid19local. The model is currently being used by the Scottish government to inform their interventions.