Search

For the last two decades, high-dimensional data and methods have proliferated throughout the literature. Yet, the classical technique of linear regression has not lost its usefulness in applications. In fact, many high-dimensional estimation techniques can be seen as variable selection that leads to a smaller set of variables (a “submodel”) where classical linear regression applies. We analyze linear regression estimators resulting from model selection by proving estimation error and linear representation bounds uniformly over sets of submodels. Based on deterministic inequalities, our results provide “good” rates when applied to both independent and dependent data. These results are useful in meaningfully interpreting the linear regression estimator obtained after exploring and reducing the variables and also in justifying post-model-selection inference. All results are derived under no model assumptions and are nonasymptotic in nature.

We study a regression problem where for some part of the data we observe both the label variable ($Y$) and the predictors (${\bf X}$), while for other part of the data only the predictors are given. Such a problem arises, for example, when observations of the label variable are costly and may require a skilled human agent. When the conditional expectation $E[Y | {\bf X}]$ is not exactly linear, one can consider the best linear approximation to the conditional expectation, which can be estimated consistently by the least squares estimates (LSE). The latter depends only on the labeled data. We suggest improved alternative estimates to the LSE that use also the unlabeled data. Our estimation method can be easily implemented and has simply described asymptotic properties.The new estimates asymptotically dominate the usual standard procedures under certain non-linearity condition of $E[Y | {\bf X}]$; otherwise, they are asymptotically equivalent.The performance of the new estimator for small sample size is investigated in an extensive simulation study. A real data example of inferring homeless population is used to illustrate the new methodology.

Autorzy: Abe K., Adrich P., Aihara H., Akutsu, R., Alekseev I., Ali A. , Ameli F., Anghel I., Anthony L. H. V., Antonova M. , Araya A., Asaoka Y., Ashida Y., Aushev V., Ballester F., Bandac I., Barbi M., Barker G. J., Barr G., Batkiewicz-Kwasniak M., Bellato M., Berardi V., Bergevin M., Bernard L., Bernardini E., Berns L., Bhadra S., Bian J., Blanchet A., Blaszczyk F. d. M., Blonde A., Boiano A., Bolognesi S., Bonavera L., Booth N., Borjabad S., Boschi, T., Bose D., Boyd S . B., Bozza C., Bravar A., Bravo-Berguño D., Bronner C., Brown L., Bubak Arkadiusz, Buchowicz A., Buizza Avanzini M., Cafagna F. S., Calabria N. F., Calvo-Mozota J. M., Cao S., Cartwright S.L., Carroll A., Catanesi M. G., Cebriàn, S., Chabera M., Chakraborty, S., Checchia C., Choi J.H., Choubey S., Cicerchia M., Coleman J., Collazuol G., Cook L., Cowan G., Cuen-Rochin, S., Danilov M., Díaz López G., De la Fuente E., de Perio P., De Rosa G., Dealtry T., Densham C. J., Dergacheva A., Deshmukh N., Devi M. M., Di Lodovico F., Di Meo, P., Di Palma I., Doyle T. A., Drakopoulou E., Drapier O., Dumarchez J., Dunne P., Dziewiecki M., Eklund L., El Hedri S., Ellis J., Emery S., Esmaili A., Esteve R., Evangelisti A., Feely M., Fedotov S., Feng J., Fernandez P., Fernández-Martinez E., Ferrario P., Ferrazzi,B., Feusels T., Finch A., Finley C., Fiorentini A., Fiorillo G., Fitton M., Frankiewicz K., Friend M., Fujii Y., Fukuda Y., Galinski G., Gao J., Garde C., Garfagnini A., Garode S., Gialanella L., Giganti C., Gomez-Cadenas J.J., Gonin M., González-Nuevo J., Gorin A., Gornea R., Gousy-Leblanc V. Gramegna F. Grassi M. Grella G. Guigue M. Gumplinger P. Hadley D.R. Harada M., Hartfiel B., Hartz M., Hassani S., Hastings N.C., Hayato Y., Hernando-Morata J.A., Herrero V., Hill J., Hiraide K., Hirota S., Holin A., Horiuchi S., Hoshina K., Hultqvist K., Iacob F., Ichikawa A.K., Idrissi Ibnsalih W., Iijima T., Ikeda M., Inomoto M., Inoue K., Insler J., Ioannisian A., Ishida T., Ishidoshiro K., Ishino H., Ishitsuka M., Ito H., Ito S., Itow Y., Iwamoto K., Izmaylov A., Izumi N., Izumiyama S., Jakkapu M., Jamieson B., Jang H.I., Jang J.S., Jenkins S.J., Jeon S.H., Jiang M., Jo H.S., Jonsson P., Joo K.K., Kajita T., Kakuno H., Kameda J., Kano Y., Kalaczynski P., Karlen D., Kasperek J., Kataoka Y., Kato A., Katori T., Kazarian N., Kearns E., Khabibullin M., Khotjantsev A., Kikawa T., Kekic M., Kim J.H., Kim J.Y., Kim S.B., Kim S.Y., King S., Kinoshita T., Kisiel Jan, Klekotko A., Kobayashi T., Koch L., Koga M., Koerich L., Kolev N., Konaka A., Kormos L.L., Koshio Y., Korzenev A., Kotsar Y., Kouzakov K.A., Kowalik K.L., Kravchuk L., Kryukov A.P., Kudenko Y., Kumita T., Kurjata R., Kutter T., Kuze M., Kwak K., La Commara M., Labarga L., Lagoda J., Lamers James J., Lamoureux M., Laveder M., Lavitola L., Lawe M., Learned J.G., Lee J., Leitner R., Lezaun V., Lim I.T., Lindner T., Litchfield R.P., Long K.R., Longhin A., Loverre P., Lu X., Ludovici L., Maekawa Y., Magaletti L., Magar K., Mahn K., Makida Y., Malek M., Malinský M., Marchi T., Maret L., Mariani C., Marinelli A., Martens K., Marti L., Martin J.F. Martin D., Marzec J., Matsubara T., Matsumoto R., Matsuno S., Matusiak M., Mazzucato E., McCarthy M., McCauley N., McElwee J., McGrew C., Mefodiev A., Medhi A., Mehta P., Mellet L., Menjo H., Mermod P., Metelko C., Mezzetto M., Migenda J., Migliozzi P., Mijakowski P., Miki S., Miller E.W., Minakata H., Minamino A., Mine S., Mineev O., Mitra A., Miura M., Moharana R., Mollo C.M., Mondal T., Mongelli M., Monrabal F., Moon D.H., Moon C.S., Mora F.J., Moriyama S., Mueller Th.A., Munteanu L., Murase K., Nagao Y., Nakadaira T., Nakagiri K., Nakahata M., Nakai S., Nakajima Y., Nakamura K., Nakamura KI., Nakamura H., Nakano Y., Nakaya T., Nakayama S., Nakayoshi K., Nascimento Machado L., Naseby C.E.R., Navarro-Garcia B., Needham M., Nicholls T., Niewczas K., Nishimura Y., Noah E., Nova F., Nugent J.C., Nunokawa H., Obrebski W., Ochoa-Ricoux J.P., O’Connor E., Ogawa N., Ogitsu T., Ohta K., Okamoto K., O’Keeffe H.M., Okumura K., Onishchuk Y., Orozco-Luna F., Oshlianskyi A., Ospina N., Ostrowski M., O’Sullivan E., O’Sullivan L., Ovsiannikova T., Oyama Y., Ozaki H., Pac M.Y., Paganini P., Palladino V., Paolone V., Pari M., Parsa S., Pasternak J., Pastore C., Pastuszak G., Patel D.A., Pavin M., Payne D., Peña-Garay C., Pidcott C., Pinzon Guerra E., Playfer S., Pointon B.W., Popov A., Popov B., Porwit Kamil, Posiadala-Zezula M., Poutissou J.M., Pozimski J., Pronost G., Prouse N.W., Przewlocki P., Quilain B., Quiroga A.A., Radicioni E., Radics B., Rajda P.J., Renner J., Rescigno M., Retiere F., Ricciardi G., Riccio C., Richards B., Rondio E., Rose H.J., Roskovec B., Roth S., Rott C., Rountree S.D., Rubbia A., Ruggeri A.C., Ruggles C., Russo S., Rychter A., Ryu D., Sakashita K., Samani S., Sánchez F., Sánchez M.L., Sanchez M.C., Sano S., Santos J.D., Santucci G., Sarmah P., Sashima I., Sato K., Scott M., Seiya Y., Sekiguchi T., Sekiya H., Seo J.W., Seo S.H., Sgalaberna D., Shaikhiev A., Shan Z., Shaykina A., Shimizu I., Shin C.D., Shinoki M., Shiozawa M., Sinnis G., Skrobova N., Skwarczynski K., Smy M.B., Sobczyk J., Sobel H.W., Soler F. J. P., Sonoda Y., Spina R., Spisso B., Spradlin B., Stankevich K.L., Stawarz L., Stellacci S.M., Stopa K., Studenikin A.I., Suárez Gómez S.L., Suganuma T., Suvorov S., Suwa Y., Suzuki A.T., Suzuki S.Y., Suzuki Y., Svirida D., Svoboda R., Taani M., Tada M., Takeda A., Takemoto Y., Takenaka A., Taketa A., Takeuchi Y., Takhistov V., Tanaka H., Tanaka H.A., Tanaka H.I., Tanaka M., Tashiro T., Thiesse M., Thompson L.F., Toledo J., Tomatani-Sánchez A.K., Tortone G., Tsui K.M., Tsukamoto T., Tzanov M., Uchida Y., Vagins M.R., Valder S., Valentino V., Vasseur G., Vijayvargi A., Vilela C., Vinning W. G. S., Vivolo D., Vladisavljevic T., Vogelaar R.B., Vyalkov M.M., Wachala T., Walker J., Wark D., Wascko M.O., Wendell R.A., Wilkes R.J., Wilking M.J., Wilson M.R., Wronka S., Xia J., Xie Z., Xin T., Yamaguchi Y., Yamamoto K., Yanagisawa C., Yano T., Yen S., Yershov N., Yeum D.N., Yokoyama M., Yonenaga M., Yoo J., Yu I., Yu M., Zakrzewski T., Zaldivar B., Zalipska J., Zaremba K., Zarnecki G., Ziembicki M., Zietara K., Zito M., Zsoldos S., Core-collapse supernovae are among the most magnificent events in the observable universe. They produce many of the chemical elements necessary for life to exist and their remnants-neutron stars and black holes-are interesting astrophysical objects in their own right. However, despite millennia of observations and almost a century of astrophysical study, the explosion mechanism of core-collapse supernovae is not yet well understood. Hyper-Kamiokande is a next-generation neutrino detector that will be able to observe the neutrino flux from the next galactic core-collapse supernova in unprecedented detail. We focus on the first 500 ms of the neutrino burst, corresponding to the accretion phase, and use a newly-developed, high-precision supernova event generator to simulate Hyper-Kamiokandeʼs response to five different supernova models. We show that Hyper-Kamiokande will be able to distinguish between these models with high accuracy for a supernova at a distance of up to 100 kpc. Once the next galactic supernova happens, this ability will be a powerful tool for guiding simulations toward a precise reproduction of the explosion mechanism observed in nature.

Although the US has the highest health care prices in the world, the specific mechanisms commonly used by other countries to set and update prices are often overlooked, with a tendency to favor strategies such as reducing the use of fee-for-service reimbursement. Comparing policies in three high-income countries (France, Germany, and Japan), we describe how payers and physicians engage in structured fee negotiations and standardize prices in systems where fee-for-service is the main model of outpatient physician reimbursement. The parties involved, the frequency of fee schedule updates, and the scope of the negotiations vary, but all three countries attempt to balance the interests of payers with those of physician associations. Instead of looking for policy importation, this analysis demonstrates the benefits of structuring negotiations and standardizing fee-for-service payments independent of any specific reform proposal, such as single-payer reform and public insurance buy-ins.

International audience; Heliophysics data analysis often involves combining diverse science measurements, many of them captured as time series. Although there are now only a few commonly used data file formats, the diversity in mechanisms for automated access to and aggregation of such data holdings can make analysis that requires intercomparison of data from multiple data providers difficult. The Heliophysics Application Programmer's Interface (HAPI) is a recently developed standard for accessing distributed time series data to increase interoperability. The HAPI specification is based on the common elements of existing data services, and it standardizes the two main parts of a data service: the request interface and the response data structures. The interface is based on the REpresentational State Transfer (REST) or RESTful architecture style, and the HAPI specification defines five required REST endpoints. Data are returned via a streaming format that hides file boundaries; the metadata is detailed enough for the content to be scientifically useful, e.g., plotted with appropriate axes layout, units, and labels. Multiple mature HAPI-related open-source projects offer server-side implementation tools and client-side libraries for reading HAPI data in multiple languages (IDL, Java, MATLAB, and Python). Multiple data providers in the US and Europe have added HAPI access alongside their existing interfaces. Based on this experience, data can be served via HAPI with little or no information loss compared to similar existing web interfaces. Finally, HAPI has been recommended as a COSPAR standard for time series data delivery.

The adoption of a single-payer health care system, a recurring dream of progressive American reformers, now enjoys sustained attention in the run-up to the 2020 national elections. Some compelling arguments support the case for single payer, and its political prospects may indeed be on the rise, but myriad obstacles beset it, and a full-throated Democratic endorsement of it carries disquieting risks.

Modern oil and gas seismic surveys commonly use areal arrays that record continuously, and thus routinely collect “excess” data that are not needed for the conventional common reflection point imaging that is the primary goal of exploration. These excess data have recently been recognized to have utility not only in resource exploration but also for addressing a diverse range of scientific issues. Here we report processing of such discarded data from recent exploration surveys carried out in southeastern New Mexico. These have been used to produce new three-dimensional (3-D) seismic reflection imagery of a layered complex within the crystalline basement as well as elements of the underlying crust. This enigmatic basement layering is similar to that found on industry and academic seismic reflection surveys at many sites in the central United States. Correlation of these reflectors with similar features encountered by drilling in northwestern Texas suggest that they may be part of an extensive, continental-scale network of tabular mafic intrusions linked to Keweenawan rifting of the igneous eastcentral Unites States during the late Proterozoic. More importantly, this analysis clearly demonstrates that the new generation of continuously recorded 3-D exploration datasets represent a valuable source of fresh information on basement structure that should be examined rather than discarded. Such basement information is not only important to understanding crustal evolution, it is directly relevant to assessing risks associated with fossil fuel extractions, such as induced seismicity related to waste water injection.

Introduction and Objectives Surgical resection for lung cancer is physically and emotionally demanding for patients, with risks of complications and morbidity. Prehabilitation aims to maximise patients’ fitness, nutrition and wellbeing before treatment to improve outcomes. The existing literature on lung cancer prehabilitation points to improved functional capacity, post-operative length of stay & frequency of complications. As such, it is recommended in current guidelines.1 Methods Prehab4Cancer, a Greater Manchester (GM) Cancer funded project, is the first regional system in the UK to introduce large-scale prehab as a standard of care for cancer patients.2 Surgical lung cancer patients are rapidly assessed at one of 17 clinics. Tailored prehab interventions span exercise (re-HIIT: high intensity interval training and muscle strengthening), nutrition, and psychological support. It is delivered by ‘GM Active’, a collective of 12 community organisations utilising cancer rehabilitation-qualified exercise specialists. A 12-week post-op rehabilitation programme follows. Measures of fitness are recorded at baseline, pre-operatively, post-operatively, and after rehabilitation. Results Since April 2019, 380 lung cancer patients have been referred from 11 hospitals, with 75% participating. Average age was 70y; 53% were female. Median duration of prehab was 39 days, with mean 2.2 sessions/week. Physiological assessments such as incremental shuttle walk test (ISWT) improved from median 350 m at baseline to 380 m. Health-related quality of life measures also demonstrated improvement (see table 1). Conclusions Prehab4cancer has successfully implemented a regional cancer prehab programme that demonstrates feasibility and excellent uptake and improved patient experience. Collaboration has been key, between GM-wide healthcare professionals working together with the GM Cancer alliance, people affected by cancer and GM Active. Validated measures of fitness and quality of life show promising trends toward improvement among surgical lung cancer patients. References Batchelor TJP, et al.Guidelines for enhanced recovery after lung surgery: Recommendations of the Enhanced Recovery after Surgery (ERAS®) Society and the European Society of Thoracic Surgeons (ESTS). Eur J Cardio-thoracic Surg 2019;55:91–115. Moore J, Merchant Z, Rowlinson K, et al. Implementing a system-wide cancer prehabilitation programme: The journey of Greater Manchester’s ‘Prehab4cancer’. Eur J Surg OncolPublished Online First: 2020.

Interoperability between datasets in Heliophysics and Planetary archives is increasingly important to address complex science questions about space weather and planetary plasma environments. Yet fo...

Introduction: A patent ductus arteriosus (PDA) in a preterm infant can lead to respiratory insufficiency and chronic lung disease as well as necrotizing enterocolitis due to systemic hypoperfusion. Recently, catheter-based PDA closure has emerged as an appealing alternative to invasive surgical ligation in preterm infants; however, evidence to support this procedure in infancy, particularly in the premature population, is still evolving. Methods: A retrospective chart review was conducted to collect information regarding demographics, neonatal and maternal clinical characteristics, and procedural and post-catheterization data. Inclusion criteria included infants born at Results: Twenty-seven patients were included in our study. Indications for PDA closure in our patient population included hemodynamically significant PDA on echocardiogram, difficulty weaning respiratory support, poor feeding and weight gain, and development of NEC. Median gestational age and weight were 26 weeks and 820 g (ranging from 23 to 30 weeks and 400 to 1540 g, respectively). Most infants tolerated the procedure well and without serious adverse outcomes. One infant developed an intimal flap post-catheterization that resolved without invasive intervention, and 1 infant developed a PAH crisis after PDA closure with resolution of PAH prior to discharge. Statistically significant associations were found between PDA plug closures and decreased oxygen requirements, decreased pulmonary artery hypertension, decreased diuretic requirements, and decreased vasodilator requirements by time of discharge. Conclusions: Successful device closures of PDAs are feasible and safe, and preliminary findings show promising outcomes without mortality or long-term morbidity following transcatheter PDA closure.

Before his incoherent response to the COVID-19 pandemic, the focus of President Trump's health policy agenda was the elimination of the Patient Protection and Affordable Care Act (ACA), which he has called a ‘disaster’. The attacks on the ACA included proposals to repeal the law through the legislative process, to erode it through a series of executive actions, and to ask the courts to declare it unconstitutional. Despite these ongoing challenges, the ACA remains largely intact as the U.S. heads into the 2020 election. The longer term fate of the law, however, is uncertain and the outcome of the 2020 election is likely to have a dramatic effect on the direction of health policy in the U.S.

Although the US has the highest health care prices in the world, the specific mechanisms commonly used by other countries to set and update prices are often overlooked, with a tendency to favor strategies such as reducing the use of fee-for-service reimbursement. Comparing policies in three high-income countries (France, Germany, and Japan), we describe how payers and physicians engage in structured fee negotiations and standardize prices in systems where fee-for-service is the main model of outpatient physician reimbursement. The parties involved, the frequency of fee schedule updates, and the scope of the negotiations vary, but all three countries attempt to balance the interests of payers with those of physician associations. Instead of looking for policy importation, this analysis demonstrates the benefits of structuring negotiations and standardizing fee-for-service payments independent of any specific reform proposal, such as single-payer reform and public insurance buy-ins.

The ACA created a new type of nonprofit health insurance entity, the “Consumer Operated and Oriented Plan” (“co-op”). Most of the newly created co-ops soon lost money, and only 4 of the original 23 remain. We interviewed key stakeholders and conducted in-depth case studies of 3 of these co-ops. We discovered that politicians and regulators made it unlikely the program could succeed, that most of the co-ops did not have the management capacity to overcome these political obstacles, and that even those with good managers lacked the needed fiscal resilience. We also considered lessons suggested for those proposing a newly created “public option.” The main one is that a successful public option requires a supportive political environment, strong management, and significant fiscal capacity, none of which comes easily. A better route may be a quasi-public option in which the government subcontracts the operation of its newly created plan to a private firm. Although it is uncertain whether federal regulators have the capacity to hold such private for-profit firms accountable, pragmatism suggests that a combination of public-sector regulation and private-sector implementation may be the most direct path toward a US version of affordable universal coverage.

Investor relations officers (IROs) play a central role in corporate communications with Wall Street. We survey 610 IROs at publicly traded U.S. companies and conduct 14 follow-up interviews to gain insights into the nature of their interactions with sell-side analysts and institutional investors, and to deepen our understanding of the role of IROs in corporate disclosure events. Three important themes emerge from our results: (i) the value, nature, and timing of private communication between IROs, analysts, and investors; (ii) the significant influence IROs have on corporate disclosures; and (iii) the degree of “theater” involved in public earnings conference calls. We explore numerous topics that IROs are uniquely suited to address, and we provide new insights into the investor relations, analyst, institutional investor, and disclosure literatures.

Public health is politically paradoxical because its core conceptual components - the exercise of public authority and the promotion of population health - stand in practical tension that belies their theoretical promise. Across Western nations, public policymakers stand accused of failing properly to honor and support the crucial contributions that public health makes to the improvement of health outcomes and of overinvesting in acute medical care services, the need for which timely interventions in prevention and health promotion might have averted. The dramatic budgetary discrepancies in Western nations between the massive funds devoted to medical care and the minuscule sums allotted to public health are often taken as evidence that in such matters, political leaders are irrational (or perhaps uninformed, or captured by big-moneyed medical interests) and that good public policy would have epidemiologists and other public health experts running, or at least orchestrating, the show. This paper explores the sources of this tension between population health and political power within the concept of public health and seeks to show why these strains prove to be so durable, indeed irresolvable. The argument and evidence draw largely on the United States, but the supposition - yway, the hope - is that the analysis will also throw light on the politics of public health in other nations.

Academic medical centers (AMCs) are a familiar target of critics who charge the US health care system with indifference to the most pressing needs of the public. AMCs are frequently faulted, for example, for promoting specialization instead of primary care, for favoring high-tech services rather than the promotion of health and prevention of illness, and for failing to adequately meet the needs of the disadvantaged. An organizational perspective, with particular attention to the structure, mission, and environment of this institutional form, suggests that these critiques may misplace onto AMCs responsibility for solving problems with deep roots in the larger political economy of health care policy in the United States. By the same token, however, the pressures of that political economy (i.e., environment) on AMCs progressively strain their structure, mission, and (arguably) their capacity to serve the public interest.

The problem of estimating the mean of a normal vector with known but unequal variances introduces substantial difficulties that impair the adequacy of traditional empirical Bayes estimators. By taking a different approach, that treats the known variances as part of the random observations, we restore symmetry and thus the effectiveness of such methods. We suggest a group-linear empirical Bayes estimator, which collects observations with similar variances and applies a spherically symmetric estimator to each group separately. The proposed estimator is motivated by a new oracle rule which is stronger than the best linear rule, and thus provides a more ambitious benchmark than that considered in previous literature. Our estimator asymptotically achieves the new oracle risk (under appropriate conditions) and at the same time is minimax. The group-linear estimator is particularly advantageous in situations where the true means and observed variances are empirically dependent. To demonstrate the merits of the proposed methods in real applications, we analyze the baseball data used in Brown (2008), where the group-linear methods achieved the prediction error of the best nonparametric estimates that have been applied to the dataset, and significantly lower error than other parametric and semi-parametric empirical Bayes estimators.

The details of magma plumbing beneath active volcanoes remain a major challenge in geochemistry, geophysics and volcanic hazard evaluation. Here we apply a relatively novel variation of seismic interferometry, which we call Virtual Reflection Seismic Profiling (VRSP), to produce a high-resolution image of a known crustal magma body. The technique takes advantage of recent advances in both seismic instrumentation (dense arrays) and seismic analysis (seismic interferometry). We have applied this technique to data recently acquired at an iconic volcanic system, Krafla, which lies on the mid-Atlantic ridge as exposed in northern Iceland. What make this particular site exceptional are encounters with rhyolitic magma in two drillholes, K-39 and Iceland Deep Drilling Project-1 (IDDP-1). These known magma bodies represent a unique calibration opportunity for surface geophysical measurements of magma distribution at depth. In this study, we produced a stacked, seismic reflection section by applying common depth point processing techniques to virtual shot gathers derived from interferometry of P waves from microearthquakes generated by tectonic, magmatic and/or geothermal activity. We observe a strong, coherent reflection on the seismic section at a travel time corresponding to the depth at which magma was encountered in the IDDP-1 wellbore. We interpret this reflection to be from magma or magma-related fluids. Additional coherent reflections may correspond to other components of the magma plumbing beneath Krafla. These results represent a promising new technique for structural imaging with natural sources that can be applied to a wide array of geologic and energy problems that involve natural or induced seismic clusters.

Conventional statistical modeling in criminology assumes proper model specification. Very strong and unrebutted criticisms have existed for decades. Some respond that although the criticisms are correct, there is for observational data no alternative. In this paper, we provide an alternative. We draw on work in econometrics and statistics from several decades ago, updated with the most recent thinking to provide a way to properly work with misspecified models. We show how asymptotically, unbiased regression estimates can be obtained along with valid standard errors. Conventional statistical inference can follow. If one is prepared to work with explicit approximations of a “true” model, defensible analyses can be obtained. The alternative is working with models about which all of the usual criticisms hold.

The Mw 5.8 earthquake that occurred in Louisa County, Virginia, on 23 August 2011 provided an opportunity to record with several “high density” seismic arrays, in addition to traditional, sparse temporary seismic networks. Traditional aftershock networks consist of a few dozen stations spread over tens of kilometers. As a result, the recorded seismic waveforms suffer from spatial aliasing that is so severe that many types of waveform processing are not applicable. Here we report the results of recording with a large number of oil industry-type instruments deployed at a spacing that is an order of magnitude closer than in traditional deployments. The objective was to image subsurface structure with array methods, using the aftershocks as sources. The dense array recorded continuously for 12 days and consisted of 172 vertical component seismometers that were placed at 200–400 m and a 60 km long three-component regional profile with stations every 2 km. We demonstrate how processing techniques from Vertical Seismic Profiling can produce high-resolution 3-D reflection images of structure beneath the array. These images display reflectivity that correlates with that observed on a nearby deep reflection survey collected by the U.S. Geological Survey. Of particular interest is a strong reflector imaged across multiple profiles. Our analysis demonstrates how a surface array of seismometers can provide 3-D images of structure using microearthquake sources when wavefields are sampled sufficiently densely.

The Heliophysics Application Programmer’s Interface (HAPI) represents a grass-roots effort to develop a common interface that data providers can use to offer time series data for computer-to-computer data access. Multiple data centers with Heliophysics and Planetary data are adopting this emerging standard. Several scientific analysis packages (Autoplot, SPEDAS) seamlessly pull from HAPI servers, and we have created and are enhancing Python libraries that can be used to read HAPI data into useful data structures within personalized analysis code. The HAPI specification and supporting software are available on GitHub. We will discuss the latest developments of the HAPI specification, current server and client implementations, all in the context of the push for increased interoperability within Heliophysics and Planetary data analysis. https://hapi-server.github.io/

In the early 1980s Halbert White inaugurated a "model-robust'' form of statistical inference based on the "sandwich estimator'' of standard error. This estimator is known to be "heteroskedasticity-consistent", but it is less well-known to be "nonlinearity-consistent'' as well. Nonlinearity, however, raises fundamental issues because in its presence regressors are not ancillary, hence can't be treated as fixed. The consequences are deep: (1)~population slopes need to be re-interpreted as statistical functionals obtained from OLS fits to largely arbitrary joint $\xy$~distributions; (2)~the meaning of slope parameters needs to be rethought; (3)~the regressor distribution affects the slope parameters; (4)~randomness of the regressors becomes a source of sampling variability in slope estimates; (5)~inference needs to be based on model-robust standard errors, including sandwich estimators or the $\xy$~bootstrap. In theory, model-robust and model-trusting standard errors can deviate by arbitrary magnitudes either way. In practice, significant deviations between them can be detected with a diagnostic test., Comment: Submitted

We propose a general semi-supervised inference framework focused on the estimation of the population mean. As usual in semi-supervised settings, there exists an unlabeled sample of covariate vectors and a labeled sample consisting of covariate vectors along with real-valued responses (“labels”). Otherwise, the formulation is “assumption-lean” in that no major conditions are imposed on the statistical or functional form of the data. We consider both the ideal semi-supervised setting where infinitely many unlabeled samples are available, as well as the ordinary semi-supervised setting in which only a finite number of unlabeled samples is available. ¶ Estimators are proposed along with corresponding confidence intervals for the population mean. Theoretical analysis on both the asymptotic distribution and $\ell_{2}$-risk for the proposed procedures are given. Surprisingly, the proposed estimators, based on a simple form of the least squares method, outperform the ordinary sample mean. The simple, transparent form of the estimator lends confidence to the perception that its asymptotic improvement over the ordinary sample mean also nearly holds even for moderate size samples. The method is further extended to a nonparametric setting, in which the oracle rate can be achieved asymptotically. The proposed estimators are further illustrated by simulation studies and a real data example involving estimation of the homeless population.

Knowledge of the crustal structure is important for understanding the tectonic framework and geological evolution of southeastern China and adjacent areas. In this study, we integrated the datasets from the TAIGER (TAiwan Integrated GEodynamic Research) and ATSEE (Across Taiwan Strait Explosion Experiment) projects to resolve onshore-offshore deep crustal seismic profiles from the Wuyi-Yunkai orogen to the Taiwan orogen in southeastern China. Three seismic profiles were resolved, and the longest profile was 850 km. Unlike 2D and 3D first arrival travel-time tomography from previous studies, we used both refracted and reflected phases (Pg, Pn, PcP, and PmP) to model the crustal structures and the crustal reflectors. In total, data from 40 shots, 2 earthquakes, and approximately 1,950 stations were used; 15,612 arrivals were selected among three transects. Using these data, we determined the complex crustal evolution since the Paleozoic era , involving the closed Paleozoic rift basin in central Fujian, the Cenozoic extension due to the South China Sea opening beneath the coastline of southern Fujian, and the on-going collision of the Taiwan orogen. The shape of the Moho, which also reflects the crustal evolution, can be summarized as follows: ~ 30 km deep to the west of Fujian, deepening toward central Fujian (~ 35 km), becoming shallower toward the Taiwan Strait (~ 28 km), deepening again toward the mountain belt of Taiwan (~ 42 km), and becoming shallower toward the Pacific Ocean (~ 10 km).

A new multichannel seismic reflection profile collected across the Sichuan Basin in southern China by SINOPROBE images prominent reflectors that originate within the lower crust and penetrate well into the underlying mantle. The geometry of these mantle reflectors is very similar to those observed on other deep reflection profiles that have been interpreted as relicts of ancient subduction. Considering the geological history of the basement beneath and surrounding Sichuan Basin and ages of granites encountered in nearby wells, we propose that these newly revealed reflectors are the remnants of Neo-Proterozoic subduction that occurred along the NW margin of the Yangtze Craton. This interpretation is consistent with geochemical studies from a gneissic complex at the west margin of the Sichuan Basin. Moreover, preservation of these reflectors supports the idea that the Sichuan lithosphere served as a consolidated tectonic buttress against which the Tibetan Plateau has impinged to produce the Longmenshan orogenic belt.

A multivariate semiparametric partial linear model for both xed and random design cases is considered. The xed design case is shown to be, in eect, a semiparametric random eld model. In either case, the model is analyzed us- ing a dierence sequence approach. The linear component is estimated based on the dierences of observations and the functional component is estimated using a multivariate Nadaraya-Watson kernel smoother of the residuals of the linear t. We show that both components can be asymptotically estimated as well as if the other component were known. The estimator of the linear component is shown to be asymptotically normal and ecient if the length of the dierence sequence used goes to innity at a certain rate. The functional component estimator is shown to be rate optimal if the Lipschitz smoothness index exceeds half the dimensionality of the functional component argument. We also develop a test for linear combi- nations of regression coecients whose asymptotic power does not depend on the functional component. All of the proposed procedures are easy to implement. Fi- nally, numerical performance of all the procedures is studied using simulated data.