Traditional Statistics Research Articles

Eculizumab exposure in children and young adults: indications, practice patterns, and outcomes-a Pediatric Nephrology Research Consortium study.

Eculizumab is approved for the treatment of atypical hemolytic uremic syndrome (aHUS). Its use off-label is frequently reported. The aim of this study was to describe the broader use and outcomes of a cohort of pediatric patients exposed to eculizumab. A retrospective, cohort analysis was performed on the clinical and biomarker characteristics of eculizumab-exposed patients < 25 years of age seen across 21 centers of the Pediatric Nephrology Research Consortium. Patients were included if they received at least one dose of eculizumab between 2008 and 2015. Traditional summary statistics were applied to demographic and clinical data. A total of 152 patients were identified, mean age 9.1 (+/-6.8) years. Eculizumab was used "off-label" in 44% of cases. The most common diagnoses were aHUS (47.4%), Shiga toxin-producing Escherichia coli HUS (12%), unspecified thrombotic microangiopathies (9%), and glomerulonephritis (9%). Genetic testing was available for 60% of patients; 20% had gene variants. Dosing regimens were variable. Kidney outcomes tended to vary according to diagnosis. Infectious adverse events were the most common adverse event (33.5%). No cases of meningitis were reported. Nine patients died of noninfectious causes while on therapy. This multi-center retrospective cohort analysis indicates that a significant number of children and young adults are being exposed to C5 blockade for off-label indications. Dosing schedules were highly variable, limiting outcome conclusions. Attributable adverse events appeared to be low. Cohort mortality (6.6%) was not insignificant. Prospective studies in homogenous disease cohorts are needed to support the role of C5 blockade in kidney outcomes.

A Geographical Analysis of Socioeconomic and Ideological Drivers of Hate Crime in the United States

Criminal activities motivated by hate are the most extreme form of bias against people. While hating a class of people and organizing in hate groups to express feelings against those people are not illegal, hate crimes, violent and non-violent, are illegal. However, there remains much to be learned about geographic patterns of hate crimes and facilitating environments. This exploratory research examines hate crime occurrences aggregated to counties in the conterminous United States and attempts to explain resulting patterns using socioeconomic and ideological correlates with traditional and spatial statistics. Geographical patterns of hate crimes in the Unites States are found to be a complicated phenomenon.

Finding Your Feet: A Gaussian Process Model for Estimating the Abilities of Batsmen in Test Cricket

Abstract In the sport of cricket, a player’s batting ability is traditionally measured using the batting average. However, the batting average fails to measure both short-term changes in ability that occur during an innings and long-term changes in ability that occur between innings due to factors such as age and experience in various match conditions. We derive and fit a Bayesian parametric model that employs a Gaussian process to measure and predict how the batting abilities of cricket players vary and fluctuate over the course of entire playing careers. The results allow us to better quantify and predict the batting ability of a player, compared with both traditional cricket statistics, such as the batting average, and more complex models, such as the official International Cricket Council ratings.

Exploring the latest Pantheon SN Ia dataset by using three kinds of statistics techniques

In this work, we explore the cosmological consequences of the latest Type Ia supernova (SN Ia) dataset, Pantheon, by adopting the wCDM model. The Pantheon dataset currently contains the largest number of SN Ia samples, which contains 1048 supernovae on the redshift range 0 < z < 2.3. Here we take into account three kinds of SN Ia statistics techniques, including: (1) magnitude statistics (MS), which is the traditional SN Ia statistics technique; (2) flux statistics (FS), which is based on the flux-averaging (FA) method; and (3) improved flux statistics (IFS), which combines the advantages of MS and FS. It should be mentioned that the IFS technique needs to scan the (z cut, Δz) parameters plane, where z cut and Δz are redshift cut-off and redshift interval of FA, respectively. The results are as follows. (1) Using the SN dataset only, the best FA recipe for IFS is (z cut, Δz) = (0.1, 0.08); (2) comparing to the old SN dataset, JLA, adopting the Pantheon dataset can reduce the 2σ error bars of equation of state w by 38%, 47% and 53% for MS, FS and IFS, respectively; (3) FS gives closer results to other observations, such as Baryon acoustic oscillations and cosmic microwave background; (4) compared with FS and IFS, MS more favors a Universe that will end in a ‘big rip’.

Modeling for Change of Daily Nurse Calls After Surgery in an Orthopedics Ward Using Bayesian Statistics.

Nurse call data may be used to evaluate the quality of nursing. However, traditional frequency-based statistics may not easily apply to nurse calls due to the large individual variability and daily call changes. We intended to propose a probabilistic modeling of nurse calls based on Bayesian statistics. We constructed the model including nurse call daily changes, individual variability, and adjustment according to characteristics (age and sex). Nurse call differences after surgery were analyzed based on data from the orthopedic ward from April 2014 to October 2017. Results show that there were differences in nurse calls from day 1 to day 10 after surgery between patients who had undergone orthopedic surgery and those who had undergone other surgeries such as tumor surgery. Furthermore, there were differences in nurse calls from day 1 to day 8 after surgery between patients who used extra pain relief medicine and those who did not. Although the analysis required multiple comparisons regarding daily nurse call changes and fixed data samples per day, our approach using Bayesian statistics could detect the periods and significant differences. This indicates that our nurse call modeling based on Bayesian statistics may be used to analyze nurse call changes.

Guilty, Innocent, or Just Not Proven? Bayesian Verdicts in the Case of Inhibitory Deficits

ABSTRACT Background: This study addresses two issues: Whether age-related differences in working memory (WM) can be studied in online samples, and whether such differences reflect an inhibitory deficit. Currently, the evidence is mixed, but the playing field was not level because traditional statistics cannot provide evidence for the null hypothesis. Experiment 1: MTurk workers (ages 19–74) performed simple and complex visuospatial WM tasks to determine whether a secondary task affected the rate of age-related decline. Performance on both tasks replicated previous laboratory studies, establishing that age-related differences in WM can be studied online. Bayesian analyses revealed it is ten times as likely that there is no inhibitory deficit on visuospatial WM tasks as that there is. Experiment 2: The effects of irrelevant location information on visuospatial WM were examined in older (M age = 64.0) and younger (M age = 25.0) MTurk workers. Irrelevant locations produced interference, but both groups were equally affected. Bayesian analyses provided support for the null hypothesis of no age difference. Conclusions: The results of both experiments on working memory not only revealed equivalent visuospatial inhibitory function in older and younger adults, they also demonstrated that age-related differences in visuospatial WM can be effectively studied online as well as in the laboratory.

CORR Synthesis: When Should the Orthopaedic Surgeon Use Artificial Intelligence, Machine Learning, and Deep Learning?

CORR Synthesis: When Should the Orthopaedic Surgeon Use Artificial Intelligence, Machine Learning, and Deep Learning?

A Comprehensive Way to Access Hospital Death Prediction Model for Acute Mesenteric Ischemia: A Combination of Traditional Statistics and Machine Learning.

PurposeThis study aimed to use traditional statistics and machine learning to develop and validate prediction models for predicting hospital death in patients with AMI and compare these models’ performance.Patients and MethodsData were retrieved from the Medical Information Mart for Intensive Care (MIMIC III) electronic clinical database. A total of 338 eligible AMI patients were divided into a training cohort (n = 238) and a validation cohort (n = 100), and all patients were divided into survival groups and nonsurvival groups according to patients’ hospital outcomes. The performance of the traditional statistics prediction model and the optimal machine learning prediction model was evaluated and compared with respect to discrimination, calibration, and clinical utility in the validation cohort.ResultsUnivariate and multivariate logistic regression analyses identified the following independent risk factors associated with hospital death for AMI in the training cohort, including diastolic blood pressure, blood lactate, blood creatinine, age, blood pH, and red blood cell distribution width. Both the nomogram (AUC = 77.0%, 67.9–86.1%) and optimal machine learning model (AUC = 82.9%, 74.9–91.0%) achieved good discrimination and calibration in the validation cohort. Decision curves analysis showed that the optimal machine learning model has a greater net benefit than that of nomogram in this study.ConclusionThe nomogram achieved a concise and relatively accurate prediction of hospital death in patients with AMI, the machine learning model also has good discrimination and seems to have better clinical utility. Traditional statistics may help infer the relationship between risk factors and hospital death, while machine learning may contribute to a more accurate prediction. Traditional statistics and machine learning are complementary in developing the prediction model for hospital death of AMI. Therefore, a combination of nomogram–machine learning (Nomo-ML) predictive model may improve care and help clinicians make AMI management-related decisions.

Prospective evaluation of urinary steroids and prostate carcinoma-induced deviation: preliminary results.

Background The serum prostate-specific antigen is the most widespread biomarker for prostate disease. Its low specificity for prostatic malignancies is a matter of concern and the reason why new biomarkers for screening purposes are needed. The correlation between altered production of the main steroids and prostate carcinoma (PCa) occurrence is historically known. The purpose of this study is to evaluate the modifications of a comprehensive urinary endogenous steroidal profile (USP) induced by PCa, by multivariate statistical methods. Methods A total of 283 Italian subjects were included in the study, 139 controls and 144 PCa-affected patients. The USP, including 17 steroids and five urinary steroidal ratios, was quantitatively evaluated using gas chromatography coupled with single quadrupole mass spectrometry (GC-MS). The data were interpreted using a chemometric, multivariate approach (intrinsically more sensible to alterations with respect to traditional statistics) and a model for the discrimination of cancer-affected profiles was built. Results Two multivariate classification models were calculated, the former including three steroids with the highest statistical significance (e.g. testosterone, etiocholanolone and 7β-OH-DHEA) and PSA values, the latter considering the three steroids' levels only. Both models yielded high sensitivity and specificity scores near to 70%, resulting significantly higher than PSA alone. Conclusions Three USP steroids resulted significantly altered in our PCa population. These preliminary results, combined with the simplicity and low-cost of the analysis, open to further investigation of the potential role of this restricted USP in PCa diagnosis.

Modelling Accessibility to Urban Green Areas Using Open Earth Observations Data: A Novel Approach to Support the Urban SDG in Four European Cities

Cities are recognised as key enablers for the world’s sustainable future. Urban sprawl and inefficient use of land are important issues significantly impacting the provision and use of open green spaces. The United Nations Sustainable Development Goal (SDG) indicator 11.7.1 aims at globally monitoring the amount of land that is dedicated by cities for public space. In Europe, the indicator “Share of urban population without green urban areas in their neighbourhood” is supposed to correspond to the SDG11.7.1 but is currently on-hold due to methodological issues and lack of data. Moreover, to efficiently assess public space conditions, timely and spatially disaggregated information is essential but not yet widely adopted by urban practitioners. Hereafter, we use a combination of satellite and crowdsourced Earth Observations (EO) to model physical accessibility to urban green spaces in four European cities. Findings suggest that it is technically feasible to derive information on the share of urban population without green urban areas in their neighbourhood. Results demonstrate that the proposed methodology represents a consistent, valid, reliable, low-cost, timely and continuous source of information for sustainable urban development. Open and free EO data can be a good complement to enhance official and traditional statistics on urban areas facilitating EU reporting against the SDG indicator for better comparison between EU countries.

Automatic detection of influential actors in disinformation networks

The weaponization of digital communications and social media to conduct disinformation campaigns at immense scale, speed, and reach presents new challenges to identify and counter hostile influence operations (IOs). This paper presents an end-to-end framework to automate detection of disinformation narratives, networks, and influential actors. The framework integrates natural language processing, machine learning, graph analytics, and a network causal inference approach to quantify the impact of individual actors in spreading IO narratives. We demonstrate its capability on real-world hostile IO campaigns with Twitter datasets collected during the 2017 French presidential elections and known IO accounts disclosed by Twitter over a broad range of IO campaigns (May 2007 to February 2020), over 50,000 accounts, 17 countries, and different account types including both trolls and bots. Our system detects IO accounts with 96% precision, 79% recall, and 96% area-under-the precision-recall (P-R) curve; maps out salient network communities; and discovers high-impact accounts that escape the lens of traditional impact statistics based on activity counts and network centrality. Results are corroborated with independent sources of known IO accounts from US Congressional reports, investigative journalism, and IO datasets provided by Twitter.

Sunk costs in the NBA: the salary cap and free agents

The previous research on the role sunk costs play in the National Basketball Association (NBA) has come to mixed conclusions. We use a direct measure of sunk costs, player compensation, and a quasi-experimental method that considers the endogenous relationship between compensation and productivity. Using the spike in salary cap for the 2016–2017 season, from new television broadcasting contracts, we find compensation has a significant effect on playing time. Specifically, we use players signing free agent contracts in 2015–2016 or 2016–2017. For both groups, we analyze the change in salary from the pre-contract season to the post-contract season. Using the difference-in-differences, we find the inflated salary cap, from the new television contracts, increased player compensation by 81.7%, on average. Instrumental variables estimations show the increase in compensation significantly affects playing time. The change in salary yields an additional 1.93 min played per game, which is approximately equal to the effect of a one-standard deviation increase in contemporaneous productivity. Furthermore, we find that our conclusions are robust to the use of various advanced analytical measures or traditional box-score statistics.

An Integrated Data Framework for Policy Guidance in Times of Dynamic Economic Shocks

Usually, offcial and survey-based statistics guide policy makers in their choice of response instruments to economic crises. However, in an early phase, after a sudden and unforeseen shock has caused incalculable and fast-changing dynamics, data from traditional statistics are only available with non-negligible time delays. This leaves policy makers uncertain about how to most effectively manage their economic countermeasures to support businesses, especially when they need to respond quickly, as in the COVID-19 pandemic. Given this information deficit, we propose a framework that guides policy makers throughout all stages of an unforeseen economic shock by providing timely and reliable data as a basis to make informed decisions. We do so by combining early stage ‘ad hoc’ web analyses, ‘follow-up’ business surveys, and ‘retrospective’ analyses of firm outcomes. A particular focus of our framework is on assessing the early effects of the pandemic, using highly dynamic and largescale data from corporate websites. Most notably, we show that textual references to the coronavirus pandemic published on a large sample of company websites and state-of-the-art text analysis methods allow to capture the heterogeneity of the crisis' effects at a very early stage and entail a leading indication on later movements in firm credit ratings.

Olfactory Phenotypes Differentiate Cognitively Unimpaired Seniors from Alzheimer's Disease and Mild Cognitive Impairment: A Combined Machine Learning and Traditional Statistical Approach.

Olfactory dysfunction (OD) is an early symptom of Alzheimer's disease (AD). However, olfactory testing is not commonly performed to test OD in the setting of AD. This work investigates objective OD as a non-invasive biomarker for accurately classifying subjects as cognitively unimpaired (CU), mild cognitive impairment (MCI), and AD. Patients with MCI (n = 24) and AD (n = 24), and CU (n = 33) controls completed two objective tests of olfaction (Affordable, Rapid, Olfactory Measurement Array -AROMA; Sniffin' Sticks Screening 12 Test -SST12). Demographic and subjective sinonasal and olfaction symptom information was also obtained. Analyses utilized traditional statistics and machine learning to determine olfactory variables, and combinations of variables, of importance for differentiating normal and disease states. Inability to correctly identify a scent after detection was a hallmark of MCI/AD. AROMA was superior to SST12 for differentiating MCI from AD. Performance on the clove scent was significantly different between all three groups. AROMA regression modeling yielded six scents with AUC of the ROC of 0.890 (p < 0.001). Random forest model machine learning algorithms considering AROMA olfactory data successfully predicted MCI versus AD disease state. Considering only AROMA data, machine learning algorithms were 87.5%accurate (95%CI 0.4735, 0.9968). Sensitivity and specificity were 100%and 75%, respectively with ROC of 0.875. When considering AROMA and subject demographic and subjective data, the AUC of the ROC increased to 0.9375. OD differentiates CUs from those with MCI and AD and can accurately predict MCI versus AD. Leveraging OD data may meaningfully guide management and research decisions.

Retracted] Application of Intelligent Optimization Technology for Territorial Spatial Planning Based on Edge Network

As a new type of planning after the national sectoral adjustment, there is an overall lack of methodological research on the preparation of territorial spatial planning, and scholars mainly focus on the endowment of natural resources themselves, using traditional statistics, spatial and survey data and statistical analysis, spatial analysis and inductive deduction to statically evaluate the spatial carrying capacity and suitability of the national and provincial level and to make a static evaluation of ecological red line, basic farmland protection line, and The existing studies, however, have not taken into account the human and the environment. However, the existing studies seldom consider the dynamic impact of human activities on the spatial utilization of national land and lack scientific arrangement of ecological space, agricultural space, and urban space under the new development trend. This paper introduces big data that can directly reflect the spatial and temporal changes of human activities and discusses the direction and specific methodological framework of edge network‐based optimization technology from four aspects: spatial suitability evaluation, ecological spatial planning, agricultural spatial planning, and urban spatial planning, emphasizing that “natural space” + “socio‐economic activities” are mutually beneficial. The scientific path of territorial spatial planning under the interaction of “natural space” + “socio‐economic activities” is emphasized.

The experience of using the mobile phone data in economic geographical researches in foreign

The era of "Big data" and the emergence of new sources of geo-information, including mobile phone data, have provided fundamentally new opportunities for research on many socio-economic processes. Compared to traditional statistical sources, mobile phone data has many unique features and advantages that attract scientists from various fields of knowledge. Extensive experience in the use of technologies for collecting and processing spatial information from mobile phones over the past 15 years has led to interest in them in order to improve demographic statistics, transport planning, analysis of settlement systems, tourism statistics, study of human behavior and emergency monitoring. The article demonstrates various cases of using mobile operator data in scientific and applied research in these areas using examples of foreign works. Foreign practice of using data from mobile operators demonstrates how data analysis can complement the results of censuses and population registers, allowing you to move from static to dynamic consideration of the settlement system. The combination of mobile telephony data with traditional statistics, as well as other types of "Big data", such as remote sensing, helps to improve the spatial and temporal resolution of geo-information in the study of demographic and socio-economic processes. At the same time, it can be observed that the potential use of this data source is not limited to supplementing the system of existing statistical indicators, but includes the creation of new socio-economic indicators. At the same time, the long-standing problem of national statistics lagging behind the leading countries of Europe and the United States can be largely offset by the incorporation of "Big data" into research practice.

An Adaptive Lasso Grey Model for Regional FDI Statistics Prediction

To overcome the deficiency of traditional mathematical statistics methods, an adaptive Lasso grey model algorithm for regional FDI (foreign direct investment) prediction is proposed in this paper, and its validity is analyzed. Firstly, the characteristics of the FDI data in six provinces of Central China are generalized, and the mixture model's constituent variables of the Lasso grey problem as well as the grey model are defined. Next, based on the influencing factors of regional FDI statistics (mean values of regional FDI and median values of regional FDI), an adaptive Lasso grey model algorithm for regional FDI was established. Then, an application test in Central China is taken as a case study to illustrate the feasibility of the adaptive Lasso grey model algorithm in regional FDI prediction. We also select RMSE (root mean square error) and MAE (mean absolute error) to demonstrate the convergence and the validity of the algorithm. Finally, we train this proposedal gorithm according to the regional FDI statistical data in six provinces in Central China from 2006 to 2018. We then use it to predict the regional FDI statistical data from 2019 to 2023 and show its changing tendency. The extended work for the adaptive Lasso grey model algorithm and its procedure to other regional economic fields is also discussed.

Policy Forum: The Real Concentration of Capital Gains in Canada—A Longitudinal Analysis

It is generally believed that the preferential treatment of capital gains for personal income tax purposes benefits primarily high-income taxpayers. However, since traditional tax statistics include capital gains in the total income of individuals, some individuals see their annual income artificially inflated by the one-time realization of a capital gain. The authors use Statistics Canada's Longitudinal Administrative Databank to better identify who &lt;i&gt;really&lt;/i&gt; benefits from the preferential treatment of capital gains in Canada and to determine their frequency of realization. Specifically, the authors measure the shift of taxpayers between five income groups depending on whether or not their capital gains are considered in their total income. While wealthier taxpayers do benefit disproportionately from the preferential treatment of capital gains, the exclusion of capital gains from total income significantly reduces this disproportion. Taxpayers with more modest incomes benefit more than one would expect from the preferential treatment of capital gains, especially when they are over 55 years old. Taxpayers with higher incomes also realize capital gains more frequently than those with lower incomes. That said, among taxable capital gain filers only, this gap is much smaller, indicating that once taxpayers report capital gains, they tend to do so frequently. Taxpayers who report capital gains with regularity remain a minority, although they realize a large share of the total value of capital gains.

Economic Costs of Childhood Stunting to the Private Sector in Low- and Middle-Income Countries

Background: Stunting during childhood has long-term consequences on human capital, including decreased physical growth, and lower educational attainment, cognition, workforce productivity and wages. Literature has quantified the costs of stunting to national economies however few studies have focused on the private sector which employs nearly 90% of the workforce in many low- and middle-income countries (LMICs). We aimed to examine i) the impact of childhood stunting on income loss of private sector workforce in LMICs; ii) to quantify losses in sales to private firms in LMICs due to childhood stunting; and iii) to estimate potential gains (benefit-cost ratios) if stunting levels are reduced in select high prevalence countries Methods: This multiple-methods study engaged multi-disciplinary technical advisers, executed several literature reviews, used innovative statistical methods, and implemented health and labor economic models. We analyzed data from seven longitudinal datasets (up to 30+ years of follow-up), 109 private firm datasets, and many global datasets including Joint Malnutrition Estimates, and World Development Indicators to produce estimates for 120+ LMICs. We studied the impact of childhood stunting on adult cognition, education and height as pathways to wages/productivity in adulthood. We employed cloud-based artificial intelligence (AI) platforms, and conducted comparative analyses using three analytic approaches: traditional frequentist statistics, Bayesian inferential statistics and machine learning. We employed labour and health economic models to estimate wage losses to the private sector worker and firm revenue losses due to stunting. We also estimated benefit-cost ratios for countries investing in nutrition-specific interventions to prevent stunting. Findings: Across 95 LMICs, childhood stunting costs the private sector at least US$135.4 billion in sales annually. Firms from countries in Latin America and the Caribbean and East Asia and Pacific regions had the greatest losses. Totals sales losses to the private sector accumulated to 0.01% to 1.2% of national GDP across countries. Sectors most affected by childhood stunting were manufacturing (non-metallic mineral, fabricated metal, other), garments and food sectors. Sale losses were highest for larger size private firms. Across regions (representing 123 LMICs), US$700 million (Middle East and North Africa) to US$16.5 billion (East Asia and Pacific) monthly income was lost among private sector workers. Investing in stunting reduction interventions yields gains from US$2 to US$81 per $1 invested annually (or 100% to 8000% across countries). Across sectors, the highest returns were in elementary occupations (US$46) and the lowest were among agricultural workers (US$8). By gender, women incurred a higher income penalty from childhood stunting and earned less than men; due to their relatively higher earnings, the returns for investing in stunting reduction were consistently higher for men across most countries studied. Interpretation: Childhood stunting costs the private sector in LMICs billions of dollars in sales and earnings for the workforce annually. Returns to nutrition interventions show that there is an economic case to be made for investing in improvements to childhood nutrition, alongside a moral one. This research could be used to motivate the private sector to invest in childhood undernutrition for both short- and long-term gains. Funding Information: The Power of Nutrition (UK); Patrick J McGovern Foundation (USA). Declaration of Interests: We declare no competing interests.

The Eurostat business cycle clock: A complete overview of the tool

Fluctuations of the economy between periods of expansion and contraction have been subject to business cycle analysis for many years. However, the understanding of different cycles, such as business, growth and acceleration cycles, and their representation in an intuitive way is not straightforward. Moreover, users are confronted with large sets of economic indicators without having synthetic information on the current evolution of the economy. In this paper, we introduce the Eurostat business cycle clock (BCC), a visualization tool designed to complement traditional economic statistics. We will present the full methodological framework underlying the clock, including the statistical detection of turning points, empirical dating and assessment. The clock is available for the euro area and its member countries, although our presentation will focus on the euro area aggregate. Some brief considerations on the impact of the current COVID-19 crisis on the clock are included.