Michael Schweinberger, Jonathan Stewart.

Source: The Annals of Statistics, Volume 48, Number 1, 374--396.

Abstract:
Statistical inference for exponential-family models of random graphs with dependent edges is challenging. We stress the importance of additional structure and show that additional structure facilitates statistical inference. A simple example of a random graph with additional structure is a random graph with neighborhoods and local dependence within neighborhoods. We develop the first concentration and consistency results for maximum likelihood and $M$-estimators of a wide range of canonical and curved exponential-family models of random graphs with local dependence. All results are nonasymptotic and applicable to random graphs with finite populations of nodes, although asymptotic consistency results can be obtained as well. In addition, we show that additional structure can facilitate subgraph-to-graph estimation, and present concentration results for subgraph-to-graph estimators. As an application, we consider popular curved exponential-family models of random graphs, with local dependence induced by transitivity and parameter vectors whose dimensions depend on the number of nodes.

Lin Liu, Yuqi Qiu, Loki Natarajan, Karen Messer.

Source: The Annals of Applied Statistics, Volume 13, Number 3, 1370--1396.

Abstract:
It is common to encounter missing data among the potential predictor variables in the setting of model selection. For example, in a recent study we attempted to improve the US guidelines for risk stratification after screening colonoscopy ( Cancer Causes Control 27 (2016) 1175–1185), with the aim to help reduce both overuse and underuse of follow-on surveillance colonoscopy. The goal was to incorporate selected additional informative variables into a neoplasia risk-prediction model, going beyond the three currently established risk factors, using a large dataset pooled from seven different prospective studies in North America. Unfortunately, not all candidate variables were collected in all studies, so that one or more important potential predictors were missing on over half of the subjects. Thus, while variable selection was a main focus of the study, it was necessary to address the substantial amount of missing data. Multiple imputation can effectively address missing data, and there are also good approaches to incorporate the variable selection process into model-based confidence intervals. However, there is not consensus on appropriate methods of inference which address both issues simultaneously. Our goal here is to study the properties of model-based confidence intervals in the setting of imputation for missing data followed by variable selection. We use both simulation and theory to compare three approaches to such post-imputation-selection inference: a multiple-imputation approach based on Rubin’s Rules for variance estimation ( Comput. Statist. Data Anal. 71 (2014) 758–770); a single imputation-selection followed by bootstrap percentile confidence intervals; and a new bootstrap model-averaging approach presented here, following Efron ( J. Amer. Statist. Assoc. 109 (2014) 991–1007). We investigate relative strengths and weaknesses of each method. The “Rubin’s Rules” multiple imputation estimator can have severe undercoverage, and is not recommended. The imputation-selection estimator with bootstrap percentile confidence intervals works well. The bootstrap-model-averaged estimator, with the “Efron’s Rules” estimated variance, may be preferred if the true effect sizes are moderate. We apply these results to the colorectal neoplasia risk-prediction problem which motivated the present work.

Zhuang Ma, Xiaodong Li.

Source: Bernoulli, Volume 26, Number 1, 432--470.

Abstract:
Canonical correlation analysis (CCA) is a fundamental statistical tool for exploring the correlation structure between two sets of random variables. In this paper, motivated by the recent success of applying CCA to learn low dimensional representations of high dimensional objects, we propose two losses based on the principal angles between the model spaces spanned by the sample canonical variates and their population correspondents, respectively. We further characterize the non-asymptotic error bounds for the estimation risks under the proposed error metrics, which reveal how the performance of sample CCA depends adaptively on key quantities including the dimensions, the sample size, the condition number of the covariance matrices and particularly the population canonical correlation coefficients. The optimality of our uniform upper bounds is also justified by lower-bound analysis based on stringent and localized parameter spaces. To the best of our knowledge, for the first time our paper separates $p_{1}$ and $p_{2}$ for the first order term in the upper bounds without assuming the residual correlations are zeros. More significantly, our paper derives $(1-lambda_{k}^{2})(1-lambda_{k+1}^{2})/(lambda_{k}-lambda_{k+1})^{2}$ for the first time in the non-asymptotic CCA estimation convergence rates, which is essential to understand the behavior of CCA when the leading canonical correlation coefficients are close to $1$.

Scott Marion, who consults states on testing, talks about why it's important for vendors and public officials to work cooperatively in renegotiating contracts amid assessment cancellations caused by COVID-19.

The post How States, Assessment Companies Can Work Together Amid Coronavirus Testing Cancellations appeared first on Market Brief.

Boeing CEO Dave Calhoun said the company was aiming to resume production this month, despite the ongoing grounding and coronavirus pandemic.

For millions of Americans, working at home isn't an option. NBC News identified seven occupations in which employees are at especially high risk of COVID-19.

The New York City police department (NYPD) is conducting an internal investigation into a May 2 incident involving the violent arrests of multiple people, allegedly members of a group who were not social distancing

Barack Obama said the “rule of law is at risk” following the justice department’s decision to drop charges against former Trump advisor Mike Flynn, as he issued a stark warning about the long-term impact on the American way of life by his successor.

Some Buckeyes are not comfortable being told by a "woman in power" to quarantine, one expert said.

Georgia is one of four states that doesn't have a hate crime law. Arbery's killing has reignited calls for legislation.

The Democracy Fund + UCLA Nationscape Project found some misinformation about the coronavirus is more widespread that you might think.

Khanh N. Dinh, Roman Jaksik, Marek Kimmel, Amaury Lambert, Simon Tavaré.

Source: Statistical Science, Volume 35, Number 1, 129--144.

Abstract:
Recent years have seen considerable work on inference about cancer evolution from mutations identified in cancer samples. Much of the modeling work has been based on classical models of population genetics, generalized to accommodate time-varying cell population size. Reverse-time, genealogical views of such models, commonly known as coalescents, have been used to infer aspects of the past of growing populations. Another approach is to use branching processes, the simplest scenario being the classical linear birth-death process. Inference from evolutionary models of DNA often exploits summary statistics of the sequence data, a common one being the so-called Site Frequency Spectrum (SFS). In a bulk tumor sequencing experiment, we can estimate for each site at which a novel somatic point mutation has arisen, the proportion of cells that carry that mutation. These numbers are then grouped into collections of sites which have similar mutant fractions. We examine how the SFS based on birth-death processes differs from those based on the coalescent model. This may stem from the different sampling mechanisms in the two approaches. However, we also show that despite this, they are quantitatively comparable for the range of parameters typical for tumor cell populations. We also present a model of tumor evolution with selective sweeps, and demonstrate how it may help in understanding the history of a tumor as well as the influence of data pre-processing. We illustrate the theory with applications to several examples from The Cancer Genome Atlas tumors.

Adam R. Brentnall, Jack Cuzick.

Source: Statistical Science, Volume 35, Number 1, 14--30.

Abstract:
Strategies to prevent cancer and diagnose it early when it is most treatable are needed to reduce the public health burden from rising disease incidence. Risk assessment is playing an increasingly important role in targeting individuals in need of such interventions. For breast cancer many individual risk factors have been well understood for a long time, but the development of a fully comprehensive risk model has not been straightforward, in part because there have been limited data where joint effects of an extensive set of risk factors may be estimated with precision. In this article we first review the approach taken to develop the IBIS (Tyrer–Cuzick) model, and describe recent updates. We then review and develop methods to assess calibration of models such as this one, where the risk of disease allowing for competing mortality over a long follow-up time or lifetime is estimated. The breast cancer risk model model and calibration assessment methods are demonstrated using a cohort of 132,139 women attending mammography screening in the State of Washington, USA.

[London?], 6th November 1989.

[London?], [199-?]

The reaction on social media has been fierce.

The chic sneaks are part of Zappos' massive Cyber Monday sale.

Peter M. Zygmunt
Jun 1, 2002; 22:4720-4727
Behavioral

Erin E. Hecht
Sep 25, 2019; 39:7748-7758
BehavioralSystemsCognitive

Catherine Orr
Mar 6, 2019; 39:1817-1827
BehavioralSystemsCognitive

Italian translation of the Press Release on the pre-release of two special chapters of the Annual Economic Report of the BIS, 17 June 2018. Trust is the missing link in today's cryptocurrencies - Cryptocurrencies' model of generating trust limits their potential to replace conventional money, the Bank for International Settlements (BIS) writes in its Annual Economic Report (AER), a new title launched this year.

More than any other factor, it is our asset that determines our adversary. For most of us, our asset is the corpus of sensitive personal details used for online transactions. This all comes down to how much data an adversary can glean from you, and how thoroughly it can analyze it. If your data passes through some software or hardware, its developer or maintainer enjoys some measure of control.

Does your customer relationship management strategy have what it takes to reach Generation Y? It's estimated that by 2021, an additional $394 billion in revenue could be gained from artificial intelligence adoption in CRM activities in the U.S. As companies grow and technology evolves at a faster-than-ever pace, collecting, storing and providing data is becoming a bigger and bigger task.

Customer attrition and churn are not new problems. Anyone who has spent time in the sales world has heard statistics around the cost of acquiring a new customer. It can be five to 25 times more expensive to acquire a new customer than to retain an existing one. Improving customer retention by just 5 percent can increase profits by 25-95 percent, depending on your industry and company size.

Merchants soon will be able to sell products on Google Shopping at no charge. Previously, they had to pay per click, but the cost was not fixed. There was no minimum, but they had to set a maximum for ad spend and Google would stop displaying their ads once the maximum was reached. Starting next week, search results on the Google Shopping tab will consist primarily of free product listings.

Priming refers to the influence that a previously encountered object exerts on future responses to similar objects. For many years, visual priming has been known as a facilitation and sometimes an inhibition effect that lasts for an extended period of time. It contrasts with the recent finding of an oscillated priming effect where facilitation and inhibition alternate over time periodically. Here we developed a computational model of visual priming that combines rhythmic sampling of the environment (attentional oscillation) with active preparation for future events (temporal expectation). Counterintuitively, it shows that both the sustained and oscillated priming effects can emerge from an interaction between attentional oscillation and temporal expectation. The interaction also leads to novel predictions, such as the change of visual priming effects with temporal expectation and attentional oscillation. Reanalysis of two published datasets and the results of two new experiments of visual priming tasks with male and female human participants provide support for the model's relevance to human behavior. More generally, our model offers a new perspective that may unify the increasing findings of behavioral and neural oscillations with the classic findings in visual perception and attention.

SIGNIFICANCE STATEMENT There is increasing behavioral and neural evidence that visual attention is a periodic process that sequentially samples different alternatives in the theta frequency range. It contrasts with the classic findings of sustained facilitatory or inhibitory attention effects. How can an oscillatory perceptual process give rise to sustained attention effects? Here we make this connection by proposing a computational model for a "fruit fly" visual priming task and showing both the sustained and oscillated priming effects can have the same origin: an interaction between rhythmic sampling of the environment and active preparation for future events. One unique contribution of our model is to predict how temporal contexts affects priming. It also opens up the possibility of reinterpreting other attention-related classic phenomena.

Dopaminergic neurons innervate extensive areas of the brain and release dopamine (DA) onto a wide range of target neurons. However, DA release is also precisely regulated. In Drosophila melanogaster brain explant preparations, DA is released specifically onto α3/α'3 compartments of mushroom body (MB) neurons that have been coincidentally activated by cholinergic and glutamatergic inputs. The mechanism for this precise release has been unclear. Here we found that coincidentally activated MB neurons generate carbon monoxide (CO), which functions as a retrograde signal evoking local DA release from presynaptic terminals. CO production depends on activity of heme oxygenase in postsynaptic MB neurons, and CO-evoked DA release requires Ca²⁺ efflux through ryanodine receptors in DA terminals. CO is only produced in MB areas receiving coincident activation, and removal of CO using scavengers blocks DA release. We propose that DA neurons use two distinct modes of transmission to produce global and local DA signaling.

SIGNIFICANCE STATEMENT Dopamine (DA) is needed for various higher brain functions, including memory formation. However, DA neurons form extensive synaptic connections, while memory formation requires highly specific and localized DA release. Here we identify a mechanism through which DA release from presynaptic terminals is controlled by postsynaptic activity. Postsynaptic neurons activated by cholinergic and glutamatergic inputs generate carbon monoxide, which acts as a retrograde messenger inducing presynaptic DA release. Released DA is required for memory-associated plasticity. Our work identifies a novel mechanism that restricts DA release to the specific postsynaptic sites that require DA during memory formation.

Have you ever wondered if you are getting adequate nutrients from the food you eat? It is a common misconception that malnutrition means not getting enough food. This is, however, incorrect! People who take in insufficient food can be malnourished, but also those who consume too much face the same risks. Malnutrition is defined as “An abnormal physiological condition caused by [...]

At the Rio+20 Conference on Sustainable Development in June 2012, UN Secretary-General Ban Ki-moon announced a new global challenge for world leaders and individuals from all sectors: create a world where no one is hungry. He emphasized that there is enough food in the world to feed our population, so the challenge comes from making sure that everyone has access [...]

Forests are one of the Earth’s greatest natural resources. There is a reason why we often figuratively speak of ‘the tree of life’; forests are key to supporting life on Earth. Eight thousand years ago, half of the Earth’s land surface was covered by forests or wooded areas. Today, these areas represent less than one third. Forests are home to 80% [...]

Smallholders and people living in rural areas in Africa grow a huge variety of edible plants other than rice, wheat or maize. These crops, including the African yam bean, have long been neglected although they represent an excellent alternative food supplement to most diets. Grown in pockets of tropical Central, West and East Africa, the African yam bean (Sphenostylis stenocarpa) [...]

Elvis Cortés Hernández grabs his lunch and sits down with his friends. We’re at the General Lázaro Cárdenas school in Ajalpan, deep in the heart of Mexico’s Puebla province and the ten–year–old is chatting about the school’s vegetable garden, one element of its progressive food policy. “I like to eat in the school dining room because they give me carrots, [...]

Supai is so remote, mail is delivered by mule train

An independent survey finds that although NPS's annual budget is around $3 billion, Americans are willing to pay much more

Early conservation research and scientific expeditions laid the groundwork and helped to convince the public national parks were a good idea

For the first time, the indigenous community is allowed to gather the cherished plant on protected land