Han Hong, Jessie Li.

Source: The Annals of Statistics, Volume 48, Number 1, 397--412.

Abstract:
This paper proposes a numerical bootstrap method that is consistent in many cases where the standard bootstrap is known to fail and where the $m$-out-of-$n$ bootstrap and subsampling have been the most commonly used inference approaches. We provide asymptotic analysis under both fixed and drifting parameter sequences, and we compare the approximation error of the numerical bootstrap with that of the $m$-out-of-$n$ bootstrap and subsampling. Finally, we discuss applications of the numerical bootstrap, such as constrained and unconstrained M-estimators converging at both regular and nonstandard rates, Laplace-type estimators, and test statistics for partially identified models.

Xin Bing, Florentina Bunea, Marten Wegkamp.

Source: Bernoulli, Volume 26, Number 3, 1765--1796.

Abstract:
Topic models have become popular for the analysis of data that consists in a collection of n independent multinomial observations, with parameters $N_{i}inmathbb{N}$ and $Pi_{i}in[0,1]^{p}$ for $i=1,ldots,n$. The model links all cell probabilities, collected in a $p imes n$ matrix $Pi$, via the assumption that $Pi$ can be factorized as the product of two nonnegative matrices $Ain[0,1]^{p imes K}$ and $Win[0,1]^{K imes n}$. Topic models have been originally developed in text mining, when one browses through $n$ documents, based on a dictionary of $p$ words, and covering $K$ topics. In this terminology, the matrix $A$ is called the word-topic matrix, and is the main target of estimation. It can be viewed as a matrix of conditional probabilities, and it is uniquely defined, under appropriate separability assumptions, discussed in detail in this work. Notably, the unique $A$ is required to satisfy what is commonly known as the anchor word assumption, under which $A$ has an unknown number of rows respectively proportional to the canonical basis vectors in $mathbb{R}^{K}$. The indices of such rows are referred to as anchor words. Recent computationally feasible algorithms, with theoretical guarantees, utilize constructively this assumption by linking the estimation of the set of anchor words with that of estimating the $K$ vertices of a simplex. This crucial step in the estimation of $A$ requires $K$ to be known, and cannot be easily extended to the more realistic set-up when $K$ is unknown. This work takes a different view on anchor word estimation, and on the estimation of $A$. We propose a new method of estimation in topic models, that is not a variation on the existing simplex finding algorithms, and that estimates $K$ from the observed data. We derive new finite sample minimax lower bounds for the estimation of $A$, as well as new upper bounds for our proposed estimator. We describe the scenarios where our estimator is minimax adaptive. Our finite sample analysis is valid for any $n,N_{i},p$ and $K$, and both $p$ and $K$ are allowed to increase with $n$, a situation not handled well by previous analyses. We complement our theoretical results with a detailed simulation study. We illustrate that the new algorithm is faster and more accurate than the current ones, although we start out with a computational and theoretical disadvantage of not knowing the correct number of topics $K$, while we provide the competing methods with the correct value in our simulations.

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.

Monuments in winter

Magenta skies over Monument Valley at sunset.

A new book charts the history of counting the public, from the ancient censuses in Rome to the American version of decennial data collection

The new service will join others at the existing 811 HealthLine, helping connect people with their local food services and offering answers for those without access to online services.

There are now 176 confirmed cases of COVID-19 in northeastern Ontario, and seven deaths.

Manitoba health officials have an agreement with First Nations leaders to track and share COVID-19 data, but the public may never know specifics of what the unique agreement yields.

The province's networks of labs processed 15,179 tests in the last 24 hours, more than any of the three days previous but still short of the 16,000 tests per day target set back in April.

Politicians, pundits and other thoughtful westerners chat about the priorities, preoccupations and politics of Albertans and others who are West of Centre in this podcast series hosted by CBC Calgary's executive producer of news, Kathleen Petty.

As expected, the number of passengers at Berlin airports fell in January. Tegel and Schönefeld dealt with a total of 2,252,265 passengers, 6.9% fewer than in the same month last year.

Berlin’s airports are recording a drastic slump in passenger numbers. In March, a decline in passengers of 64.7 percent was recorded at Tegel and Schönefeld for the whole month. However, the number of passengers has continued to fall significantly over ...

Due to overwhelming response, Magnum Tonic Wine has expanded its TekChargeAYard Dance Challenge to Belize, Antigua and Barbuda, St Vincent and The Grenadines, and Guyana.The challenge was initially open to participants from Jamaica and Trinidad and Tobago.

Nagasaki, Japan :: Crewmembers serve with a local group of volunteers who provide food for the few homeless in Nagasaki.

Aluminum is ubiquitous and exposure is unavoidable. Adverse health effects have been associated with large exposures in workers or those with chronic kidney disease. There are no established age-specific reference ranges or toxicity data for populations of healthy children.

We demonstrate the wide variability of aluminum reference ranges in biological samples and that the ranges are not based on studies including healthy children. Further research is necessary to establish clinically relevant reference ranges for healthy children. (Read the full article)

Newborn screening for critical congenital heart defects (CCHDs) has been implemented in many hospitals, yet there is uncertainty about the number of infants with CCHDs that might be detected through universal implementation of newborn CCHD screening in the United States.

We estimated that ~875 infants with CCHDs might be detected, and ~880 missed, annually through universal CCHD screening in the United States. Increases in prenatal diagnosis are unlikely to substantially impact the number of infants detected through CCHD screening. (Read the full article)

Children with marked cerebral palsy (CP) are considered at greater risk of adverse events (AEs) after intramuscular injections of BoNT-A. To date there has been no randomized controlled trial examining safety of intramuscular BoNT-A injections in children with marked CP.

Children with nonambulatory CP had no greater risk of moderate or serious AEs after intramuscular injections of BoNT-A compared with a sham/control group. There was no greater risk of AEs for children receiving 2 compared with 1 episode of BoNT-A. (Read the full article)

History overwhelmingly favours Germany against Sweden on Friday, but in Pia Sundhage, Sweden are led by a coach bidding for a third successive Olympic gold.

Source: www.nbcnews.com - Saturday, May 09, 2020
The U.S. unemployment rate reached 14.7 percent for April - the worst monthly rate since the Great Depression. The White House has projected optimism, saying they expect the economy to rocket upward once coronavirus restrictions are lifted. But many experts think that is not a realistic expectation.

UEFA.com studies the statistics to find out which players are predicted for big Matchday 7 totals.

The intercollege minor in entrepreneurship and innovation (ENTI) continues to spread its influence as it graduates its largest number of students this spring with 153 across eight clusters.

As the dust settles on UEFA EURO 2016, we pick over the standout figures – from the quickest player to spot-kick woes and a rash of new records for Cristiano Ronaldo.

UEFA.com studies the statistics to find out which players are predicted for big Matchday 8 totals.

Source: www.geekwire.com - Friday, May 08, 2020
University of Washington researchers work with the virus that causes COVID-19 in a restricted lab. (UW Medicine via YouTube) In a newly published study, a University of Washington researcher argues that the eventual death toll from COVID-19 could be more than twice as high as the figures currently being discussed. The study was written by Anirban Basu, a health economist and statistician who’s the director of UW’s Comparative Health Outcomes, Policy and Economics Institute, also known as the CHOICE Institute . In his research paper , published online Thursday by the journal Health Affairs, Basu acknowledges there’s still lots of uncertainty surrounding the fatality rate for the disease caused by the coronavirus known as SARS-CoV-2. But he says there’s evidence that the U.S. death toll could amount to 350,000 to 1.2 million. Anirban Basu is the Stergachis Family Endowed Director of the CHOICE Institute at the University of Washington’s School of Pharmacy. (UW Photo) “This is a staggering number, which can only be brought down with sound public health measures,” Basu said in an interview with MedicalResearch.com . The latest projections from UW’s Institute for Health Metrics and Evaluation estimate that the U.S. death toll due to COVID-19 will amount to nearly 135,000 by Aug. 4. IHME’s projections are closely watched (and occasionally lowballed) by the White House. “We’ll be at 100,000” or 110,000 deaths, President Donald Trump to

The fifth daughter of a poor family, one girl thought she would never get an education. But thanks to OM’s new school, she has hope.

The 2017 results of the Program for the International Assessment of Adult Competencies finds that America's adult workforce is no more skillful in reading, math, or digital problem-solving than it was five years ago.

A record number of student startups from across Penn State campuses are getting ready for the 2020 Summer Founders program, a 13-week entrepreneurial bootcamp offering mentoring, networking, resources and $15,000 in funding to teams of Penn State student entrepreneurs from all campus locations and the World Campus.

The DJI Mavic Pro Platinum is the best small drone you can buy, and a fantastic choice for most aerial videographers and YouTubers.

Preschool-age children who frequently play number-related games at home show better math skills and growth by the end of kindergarten, finds a new study in the journal Child Development.

Dover’s Veterans Day Parade – Saturday, Nov. 4th at 9:30 am – Downtown Dover (Loockerman St. to Federal St.) The City of Dover is hosting this year’s Veterans Day Parade along with the Delaware Commission of Veterans Affairs. Please join us Saturday morning on November 4th at 9:30am. For those who are interested in participating, please […]

The Delaware General Assembly, the Delaware Commission of Veterans Affairs and the Delaware Heritage Commission will unveil a new monument this weekend honoring Delawareans who served in World War I and those who supported them on the home front

The Delaware General Assembly, the Delaware Commission of Veterans Affairs and the Delaware Heritage Commission unveiled a new monument in honor of those Delawareans who served their state and the nation in World War I.

When/Where:  Saturday, November 3, 2018 at 10:00 AM – Downtown Dover – W. Loockerman Street to Legislative Avenue When/Where:  Saturday, November 3, 2018 at 12:00 PM – Downtown Dover – Legislative Avenue & Martin Luther King Jr. Boulevard The Delaware General Assembly, the Delaware Department of State, the Delaware Commission of Veterans Affairs, the Delaware […]

५७ चेंडुंमध्ये वॉटसनने ११ चौकार आणि ८ षटकारांच्या सहाय्याने नाबाद ११७ धावांची खेळी केली.

Ancient Monuments and Archaeological Sites and Remains Act 1958

Ancient Monuments Preservation Act 1904

The Division of Public Health (DPH) is reporting two more flu-related deaths that occurred during the last two weeks of February, bringing the 2017-2018 season death total to 30. This number breaks the previous single-season record of 28 flu-related deaths, set in 2014-2015. The deceased were both females, 83 and 84 years old, from New Castle and Kent counties, respectively. Both had multiple underlying health conditions.

Statewide flu totals in Delaware decreased for the third week in a row, according to the Division of Public Health (DPH). During the week ending March 10, DPH reports 290 laboratory-confirmed flu cases, down from the prior week’s total of 381 confirmed cases. The latest numbers increase the total number of influenza cases for the season to 7,433. DPH is also reporting one additional flu-related death, a 62-year-old female from New Castle County with multiple underlying health conditions, bringing the number of flu-related deaths for the 2017-2018 flu season to 31.

On Thursday, the expert committee set up by the state said 105 persons infected by the virus had died, but just 33 of these died due to the virus.

Regular expressions are a powerful method for finding specific patterns in text. The syntax of regular expressions is intimidating, but once you've solved a few pattern-recognition problems with regex, you'll never go back to your old methods.

The post Convert a text-based measurement to a number in SAS appeared first on The SAS Dummy.

The Delaware Public Service Commission (PSC) and Delaware Division of the Public Advocate have received numerous complaints of third-party electricity suppliers “spoofing” phone numbers in an effort to sign up households for new service contracts.

As of February 15, 2020, there have been 5,047 confirmed cases of influenza in Delaware, including 267 hospitalizations. These numbers reflect only the number of lab-confirmed cases; the actual number of cases circulating statewide is likely much higher. By comparison, at the same time in the 2018-2019 season, there were 3,264 flu cases in Delaware, including 537 hospitalizations, and 13 flu-related deaths.

DNREC announced today it will take steps when necessary to limit the numbers of visitors within state parks and wildlife areas.

The fast growing nationalities of overseas students in the UK belong to the citizens of India, China, America and Saudi Arabia. The promising trendThere was a major increase in the number of Indian students pursuing their studies in the United Kingdom.…