Sarat B. Moka, Dirk P. Kroese.

Source: Bernoulli, Volume 26, Number 3, 2082--2104.

Abstract:
We present a perfect sampling algorithm for Gibbs point processes, based on the partial rejection sampling of Guo, Jerrum and Liu (In STOC’17 – Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing (2017) 342–355 ACM). Our particular focus is on pairwise interaction processes, penetrable spheres mixture models and area-interaction processes, with a finite interaction range. For an interaction range $2r$ of the target process, the proposed algorithm can generate a perfect sample with $O(log(1/r))$ expected running time complexity, provided that the intensity of the points is not too high and $Theta(1/r^{d})$ parallel processor units are available.

Arnak S. Dalalyan, Lionel Riou-Durand.

Source: Bernoulli, Volume 26, Number 3, 1956--1988.

Abstract:
Langevin diffusion processes and their discretizations are often used for sampling from a target density. The most convenient framework for assessing the quality of such a sampling scheme corresponds to smooth and strongly log-concave densities defined on $mathbb{R}^{p}$. The present work focuses on this framework and studies the behavior of the Monte Carlo algorithm based on discretizations of the kinetic Langevin diffusion. We first prove the geometric mixing property of the kinetic Langevin diffusion with a mixing rate that is optimal in terms of its dependence on the condition number. We then use this result for obtaining improved guarantees of sampling using the kinetic Langevin Monte Carlo method, when the quality of sampling is measured by the Wasserstein distance. We also consider the situation where the Hessian of the log-density of the target distribution is Lipschitz-continuous. In this case, we introduce a new discretization of the kinetic Langevin diffusion and prove that this leads to a substantial improvement of the upper bound on the sampling error measured in Wasserstein distance.

Jason M. Klusowski, Yihong Wu.

Source: Bernoulli, Volume 26, Number 3, 1635--1664.

Abstract:
Learning properties of large graphs from samples has been an important problem in statistical network analysis since the early work of Goodman ( Ann. Math. Stat. 20 (1949) 572–579) and Frank ( Scand. J. Stat. 5 (1978) 177–188). We revisit a problem formulated by Frank ( Scand. J. Stat. 5 (1978) 177–188) of estimating the number of connected components in a large graph based on the subgraph sampling model, in which we randomly sample a subset of the vertices and observe the induced subgraph. The key question is whether accurate estimation is achievable in the sublinear regime where only a vanishing fraction of the vertices are sampled. We show that it is impossible if the parent graph is allowed to contain high-degree vertices or long induced cycles. For the class of chordal graphs, where induced cycles of length four or above are forbidden, we characterize the optimal sample complexity within constant factors and construct linear-time estimators that provably achieve these bounds. This significantly expands the scope of previous results which have focused on unbiased estimators and special classes of graphs such as forests or cliques. Both the construction and the analysis of the proposed methodology rely on combinatorial properties of chordal graphs and identities of induced subgraph counts. They, in turn, also play a key role in proving minimax lower bounds based on construction of random instances of graphs with matching structures of small subgraphs.

Pier Luigi Conti, Daniela Marella, Fulvia Mecatti, Federico Andreis.

Source: Bernoulli, Volume 26, Number 2, 1044--1069.

Abstract:
In this paper, a class of resampling techniques for finite populations under $pi $ps sampling design is introduced. The basic idea on which they rest is a two-step procedure consisting in: (i) constructing a “pseudo-population” on the basis of sample data; (ii) drawing a sample from the predicted population according to an appropriate resampling design. From a logical point of view, this approach is essentially based on the plug-in principle by Efron, at the “sampling design level”. Theoretical justifications based on large sample theory are provided. New approaches to construct pseudo populations based on various forms of calibrations are proposed. Finally, a simulation study is performed.

Matthew R. Williams, Terrance D. Savitsky.

Source: Bayesian Analysis, Volume 15, Number 1, 57--77.

Abstract:
An informative sampling design leads to unit inclusion probabilities that are correlated with the response variable of interest. However, multistage sampling designs may also induce higher order dependencies, which are ignored in the literature when establishing consistency of estimators for survey data under a condition requiring asymptotic independence among the unit inclusion probabilities. This paper constructs new theoretical conditions that guarantee that the pseudo-posterior, which uses sampling weights based on first order inclusion probabilities to exponentiate the likelihood, is consistent not only for survey designs which have asymptotic factorization, but also for survey designs that induce residual or unattenuated dependence among sampled units. The use of the survey-weighted pseudo-posterior, together with our relaxed requirements for the survey design, establish a wide variety of analysis models that can be applied to a broad class of survey data sets. Using the complex sampling design of the National Survey on Drug Use and Health, we demonstrate our new theoretical result on multistage designs characterized by a cluster sampling step that expresses within-cluster dependence. We explore the impact of multistage designs and order based sampling.

Ioannis Ntzoufras, Claudia Tarantola, Monia Lupparelli.

Source: Bayesian Analysis, Volume 14, Number 3, 797--823.

Abstract:
We introduce a novel Bayesian approach for quantitative learning for graphical log-linear marginal models. These models belong to curved exponential families that are difficult to handle from a Bayesian perspective. The likelihood cannot be analytically expressed as a function of the marginal log-linear interactions, but only in terms of cell counts or probabilities. Posterior distributions cannot be directly obtained, and Markov Chain Monte Carlo (MCMC) methods are needed. Finally, a well-defined model requires parameter values that lead to compatible marginal probabilities. Hence, any MCMC should account for this important restriction. We construct a fully automatic and efficient MCMC strategy for quantitative learning for such models that handles these problems. While the prior is expressed in terms of the marginal log-linear interactions, we build an MCMC algorithm that employs a proposal on the probability parameter space. The corresponding proposal on the marginal log-linear interactions is obtained via parameter transformation. We exploit a conditional conjugate setup to build an efficient proposal on probability parameters. The proposed methodology is illustrated by a simulation study and a real dataset.

L. F. South, A. N. Pettitt, C. C. Drovandi.

Source: Bayesian Analysis, Volume 14, Number 3, 773--796.

Abstract:
Sequential Monte Carlo (SMC) methods for sampling from the posterior of static Bayesian models are flexible, parallelisable and capable of handling complex targets. However, it is common practice to adopt a Markov chain Monte Carlo (MCMC) kernel with a multivariate normal random walk (RW) proposal in the move step, which can be both inefficient and detrimental for exploring challenging posterior distributions. We develop new SMC methods with independent proposals which allow recycling of all candidates generated in the SMC process and are embarrassingly parallelisable. A novel evidence estimator that is easily computed from the output of our independent SMC is proposed. Our independent proposals are constructed via flexible copula-type models calibrated with the population of SMC particles. We demonstrate through several examples that more precise estimates of posterior expectations and the marginal likelihood can be obtained using fewer likelihood evaluations than the more standard RW approach.

Qingyuan Zhao, Jingshu Wang, Wes Spiller, Jack Bowden, Dylan S. Small.

Source: Statistical Science, Volume 34, Number 2, 317--333.

Abstract:
Instrumental variable analysis is a widely used method to estimate causal effects in the presence of unmeasured confounding. When the instruments, exposure and outcome are not measured in the same sample, Angrist and Krueger ( J. Amer. Statist. Assoc. 87 (1992) 328–336) suggested to use two-sample instrumental variable (TSIV) estimators that use sample moments from an instrument-exposure sample and an instrument-outcome sample. However, this method is biased if the two samples are from heterogeneous populations so that the distributions of the instruments are different. In linear structural equation models, we derive a new class of TSIV estimators that are robust to heterogeneous samples under the key assumption that the structural relations in the two samples are the same. The widely used two-sample two-stage least squares estimator belongs to this class. It is generally not asymptotically efficient, although we find that it performs similarly to the optimal TSIV estimator in most practical situations. We then attempt to relax the linearity assumption. We find that, unlike one-sample analyses, the TSIV estimator is not robust to misspecified exposure model. Additionally, to nonparametrically identify the magnitude of the causal effect, the noise in the exposure must have the same distributions in the two samples. However, this assumption is in general untestable because the exposure is not observed in one sample. Nonetheless, we may still identify the sign of the causal effect in the absence of homogeneity of the noise.

Víctor Elvira, Luca Martino, David Luengo, Mónica F. Bugallo.

Source: Statistical Science, Volume 34, Number 1, 129--155.

Abstract:
Importance sampling (IS) methods are broadly used to approximate posterior distributions or their moments. In the standard IS approach, samples are drawn from a single proposal distribution and weighted adequately. However, since the performance in IS depends on the mismatch between the targeted and the proposal distributions, several proposal densities are often employed for the generation of samples. Under this multiple importance sampling (MIS) scenario, extensive literature has addressed the selection and adaptation of the proposal distributions, interpreting the sampling and weighting steps in different ways. In this paper, we establish a novel general framework with sampling and weighting procedures when more than one proposal is available. The new framework encompasses most relevant MIS schemes in the literature, and novel valid schemes appear naturally. All the MIS schemes are compared and ranked in terms of the variance of the associated estimators. Finally, we provide illustrative examples revealing that, even with a good choice of the proposal densities, a careful interpretation of the sampling and weighting procedures can make a significant difference in the performance of the method.

[London?], [199-?]

Once you try them, you’ll never want to wear anything else

View these vivid illustrations by Japanese artist Kōkichi Tsunoi of the varieties of trees presented to the United States in 1912

“Listening to their testimonies, I’ve begun to envision their stories as a collection of clues, a series of scenes revealing the fingerprints of something—or Someone—beyond our deepest imagination,” says Chris. “The people I talked with hail from a variety of backgrounds—atheist German to Cambodian Buddhist—but the tapestries of their lives reveal the same beautiful threads, pointing unmistakably to a Designer.“

Following in the footsteps of Apple Card, and in the shadow of a rumored debit card solution from Google, Samsung on Thursday announced plans to field a physical debit card product in partnership with finance company SoFi.

Jonathan Mahler’s piece on the Osama bin Laden raid is as much about the nature of journalism as it is about the facts surrounding the event.

German translation of the BIS Press Release on the presentation of the Annual Report (25 June 2017)

5G tablets are on the way, and Samsung's Galaxy Tab S6 could be repackaged as one of the first. The South Korean company accidentally listed the 5G-ready model on its website. Now, it's only a matter of time before the Galaxy Tab S6 5G goes official.

“Scotland”, declared a young Alex Salmond in May 1975, “knows from bitter experience what treatment is in store for a powerless region of a common market.”

BORIS Johnson has said Britain needs the "same spirit of national endeavour" to defeat the coronavirus as Second World War veterans demonstrated to topple Adolf Hitler.

Two recent studies of Teach to One: Math highlight the tension in math between grade-level-based accountability systems and approaches to instruction that enable more personalized paths to college and career readiness.

RIGHT now, Tori Amos says, the big thing is to resist despondency. “That is an illness,” she tells me near the end of our conversation. “That is cancerous. And it can spread through your whole being and you don’t even realise. You’re in a mental war and you don’t know how to get out of it, and you do have to have words with yourself.”

Little is known about the pharmacokinetics and required dosage of metronidazole in preterm neonates.

In this study the pharmacokinetics of metronidazole in preterm neonates was investigated by measurement of the drug in dried blood-spot samples. A dosage regimen is proposed that should result in more appropriate, less frequent dosing in the most preterm neonates. (Read the full article)

Media reports suggest that adolescents are being charged with sex crimes and even placed on sex offender registries because of participating in the "sexting" of sexual images, but the nature and outcomes of such incidents have not been described empirically.

This is the first study to examine types of sexting cases handled by police. It informs clinicians by identifying characteristics of "aggravated" versus milder incidents and finding that most youth were not arrested. Sex offender registration was rare. (Read the full article)

Although there is some older literature examining how arrest prevalence accumulates through adolescence and adulthood, there is no contemporary research examining the arrest histories of a representative sample of American youth.

Using a contemporary US sample of adolescents and young adults, we estimated the cumulative arrest prevalence through age 23. The results suggest a substantial increase in the cumulative prevalence of arrest since the 1960s. (Read the full article)

Newborn screening (NBS) programs may store bloodspot samples and use them for secondary purposes, such as research. Recent public controversies and lawsuits over storage and secondary uses underscore the need to engage the public on these issues.

This public engagement study identifies values underlying citizens’ acceptance of and discomfort with research from NBS samples. Well-designed methods of public education and civic discourse on the risks and benefits of storage and secondary uses of NBS samples are required. (Read the full article)

Research has highlighted an important relationship between motor coordination and emotional functioning in children and adolescents. Few studies have provided support for this idea; research is therefore needed to further understand the relationship between the motor and emotional domains.

The results suggest that the relationship between motor coordination and emotional functioning (anxious and depressive symptoms) in an adolescent sample may be understood in terms of a mechanism whereby motor coordination has an indirect impact on emotional functioning via self-perceptions. (Read the full article)

Known rates of nonsuicidal self-injury, hurting oneself without the intent to die, are between ~7% and 24% in samples of early adolescents and older adolescents, yet research has not reported rates for youth younger than 11 years old.

Children as young as 7 years old report engaging in nonsuicidal self-injury. There is a grade by gender interaction for nonsuicidal self-injury, such that ninth-grade girls report the greatest rates of engagement and do so by cutting themselves. (Read the full article)

Physical punishment is associated with aggression, delinquency, and internalizing conditions in childhood, as well as a range of Axis I mental disorders in adulthood. More research is needed on the possible long-term relationship between physical punishment and mental health.

To our knowledge, this is the first nationally representative examination of physical punishment and a range of Axis I and II disorders, gender interactions, and proportion of mental disorders in the general population that may be attributable to physical punishment. (Read the full article)

Lifestyle and vulnerability associated with food allergy might predispose affected children to being bullied. Our previous parent survey identified high rates of bullying in this population, but child reports and emotional impact were not assessed.

Bullying was common, often involving threats with food. Bullied food-allergic children, compared with nonbullied, report higher anxiety and lower quality of life. Parental awareness of bullying (~50% of cases) was associated with better social and emotional functioning in the child. (Read the full article)

Routine screening of potentially abused children with hepatic transaminases has been recommended, using a threshold of 80 IU/L to determine the need for further testing, but practice is variable, and this threshold has not been validated.

This study identified abdominal injury in a significant fraction of potentially abused children with transaminases >80 IU/L. (Read the full article)

Most studies focus on health of foster children or local samples of young children. One previous study examined a national cohort longitudinally but did not address the full age group or range of conditions at the time of initial investigation.

Using 2 approaches to assess children (aged 0–17.5 years) who have chronic health conditions, we found that regardless of placement, investigated children had much higher rates of these conditions than the general population at the time of initial assessment. (Read the full article)

Health insurance is associated with improved health for children, but gay and lesbian parents face barriers to adding their children to private health insurance. Little is known about the extent to which insurance disparities exist for children with same-sex parents.

Children with same-sex parents are less likely to have private health insurance. When children live in states in which legal same-sex marriage, civil unions, domestic partnerships, or second-parent adoptions are available, disparities in private insurance diminish for children with same-sex parents. (Read the full article)

Prematurely born infants commonly have abnormal metabolic screens.

Both gestational and chronological age influence metabolic profiles used to screen for inborn errors of metabolism. (Read the full article)

Apple is thought to be planning a merger of its app platforms, which means a developer can develop an app once and have it automatically run on iPhone, iPad, and Mac without any extra work. The initiative is called 'Marzipan.'

Boys and girls start out on the same biological footing when it comes to math, according to the first neuroimaging study of math gender differences in children.

The Samsung Galaxy Note 10+ is a big, powerful phone that's good for artists and note-takers.

The 256GB Samsung EVO Select microSDXC card is back at just $39.99, the Echo Dot is half off, and the MacBook Air is $150 off.

Snag the Samsung EVO Select 512GB microSDXC card for $88, one of its lowest prices ever. Also, the 75-inch Samsung QLED 4K TV is more than $1,000 off and a Dell XPS 15 is $300 off.

The start of November has brought a ton of great deals, with some matching last year's Black Friday prices. The 512GB Samsung EVO Select microSDXC card is only $78.

The 1TB Samsung 860 EVO m.2 SSD is just $119 today, the 10.2-inch iPad is back in stock with a 15 percent discount, and you can save $250 on the 13-inch MacBook Pro.

This is a 2018 model, but it's got tons of bells and whistles such as 4K ultra high-definition (2160p) picture, built-in Wi-Fi and smart functionality, and High Dynamic Range support.

Use the coupon code below to snag the 55-inch model for just $1,249 (down from $1,999.99) or the 65-inch model for $1,549 (down from $2,799.99).

At Amazon right now, you can save up to 47 percent on a Samsung Q60 series QLED 4K Ultra HD smart TV with HDR support and Alexa and Google Assistant compatibility.

Save on a new TV, soundbar, or media streamer for the Big Game. Plus, the best deals of the week, including discounts on AirPods, Roombas, and Dell's XPS 13 laptop, are all still available.

Samsung will announce the next-generation foldable phone later this month; however, a newly-leaked hands-on video reveals exactly how its Galaxy Z Flip will perform in the real world.

The Samsung Galaxy Z Flip is the first folding phone to really work, but it's still a costly and potentially fragile fashion object rather than a mainstream hit.

The Galaxy S20 Ultra has the potential to become the best phone you can buy, but it's not worth $1,400 until Samsung fixes some bugs.

The Samsung Galaxy S20 is the most manageable of the S20 lineup in terms of size and price, but it may get left behind with future 5G upgrades.

Crisis Group mourns the passing today of Sandy Berger, a tremendous friend and colleague who worked tirelessly to promote greater peace and security in a troubled world. He died of cancer at the age of 70.