Binomial Distribution Research Articles

The Impact of Residents’ Daily Internet Activities on the Spatial Distribution of Online Fraud: An Analysis Based on Mobile Phone Application Usage

In recent years, there has been a sharp increase in the number of online fraud cases. However, research on crime geography has paid little attention to online crimes, especially to the influencing factors behind their spatial distributions. Online fraud is closely related to people’s daily internet use. The existing literature has explored the impact of internet use on online crimes based on small samples of individual interviews. There is a lack of large-scale studies from a community perspective. This study applies the routine activity theory to online activities to test the relationship between online fraud alert data and the usage durations of different types of mobile phone users’ applications (apps) for communities in ZG City. It builds negative binomial regression models for analyzing the impact of the usage of different types of apps on the spatial distribution of online fraud. The results reveal that the online fraud crime rate and the online time spent on a financial management app share the most similar spatial distribution. While financial management, online education, transportation, and search engine app usages have a significant positive association with online fraud, the use of a financial management app has the greatest impact. Additionally, time spent on social media, online shopping and entertainment, and mobile reading apps have a significant negative association with online fraud. As not all online activities lead to cybercrime, crime prevention efforts should target specific types of apps, such as financial management, online education, transportation, and search engines.

Evaluation of statistical methods applied in theses and dissertations in an Open, Distance and e-Learning University.

The appropriate application of research methods and statistical analyses used in the studies directly affects the quality of scientific studies. Due to the possibility of employing an incorrect statistical technique, it is crucial to choose a statistical method based on the study's data and research objectives. This study aimed to evaluate whether statistical techniques applied in the theses and dissertations were appropriate for planning surveys or experiments and analyzing data, and to identify common mistakes that master's and doctoral students made when using statistical techniques for the intended goals. The study reviewed 139 master's theses and doctoral dissertations submitted to seven agricultural and environmental sciences disciplines at a leading Open, Distance and e-learning university in Africa between 2015 and 2020. These dissertations and theses used mixed and quantitative research methods. The analysis of variance test was the most often used statistical test, according to the results, followed by the student t-test and the Chi-square test. At least one blatant methodological error was found in 41.0% of theses and dissertations, either in the data collection process or in the data analysis. Examples of these errors include the use of a simple random sampling technique despite the heterogeneous population units, the conversion of count responses to binary responses and percentages for fitting logistic and general binomial regression models, and the incorrect modeling of correlated data using generalized linear models. The results of this study will create greater awareness of the common errors that postgraduate students make when using statistical methods to design experiments or sample surveys and analyse data. In addition, the findings inform the university management to plan for specific training in statistical methods appropriate for a range of academic fields.

Ukrainian Educational and Scientific Potential After the Full-Scale Invasion: Socieconomic Challenges and Prospects

For Ukraine, which has historically been a hub of scientific and technological expertise, the paradigm of the knowledge economy has been a cornerstone of national advancement. However, the full-scale Russian invasion of 2022 has significantly disrupted the country’s development, posing severe challenges to education, research, and technological innovation. In particular, the war has led to the destruction of critical infrastructure, the displacement of skilled professionals, and a decline in government funding for scientific institutions. The educational sector, already grappling with pre-existing structural issues such as underfunding, has been further weakened by the conflict, resulting in declining global rankings and significant changes in student and researcher demographics. Universities and research institutions have had to rapidly adapt to new realities, with many shifting to online education, forming international collaborations, and securing external funding to sustain operations. The present article analyzes the key aspects of the functioning of the knowledge economy and education as its component in Ukraine under the conditions of ongoing military actions. Using data from the State Statistics Service of Ukraine, the World Bank, and Scopus, we analyze shifts in the funding structure of research projects. Special attention is given to demographic changes in higher education; employing a Bayesian binomial model with a beta prior, we quantify shifts in gender composition among university students and perform the evaluation of the statistical significance of the changes. In addition, the strategies employed by Ukrainian companies and educational institutions to adapt to the new conditions are analyzed. Particular emphasis is given to government and private initiatives supporting key sectors of the knowledge economy, as well as their importance for the recovery of Ukraine’s economy after the war. The article explores the prospects for the post-war recovery of the country’s scientific and innovative potential, emphasizing the need for investments in education, science, and the development of technological infrastructure. Possible development scenarios are presented, including the creation of innovative clusters and the active use of international experience to accelerate recovery and enhance Ukraine’s competitiveness in the global knowledge economy.

Association between maternal smoking during pregnancy and smoking behaviors in adult offspring.

Maternal smoking during pregnancy (MSP) is associated with offspring smoking. However, there is still scant evidence to support the association between MSP and smoking behaviors in adult offspring. This is a prospective cohort study based on the UK Biobank. Maternal smoking around birth was reported by the offspring through a questionnaire. Participants with unknown maternal smoking status were classified as having missing values. Logistic regression, linear regression and negative binomial regression models were used to estimate the associations of exposure to maternal smoking around birth with four outcomes of offspring smoking behaviors, including smoking status, age started smoking, pack years of smoking, and number of unsuccessful stop-smoking attempts. We included 156,604, 101,204, 96,466, and 70,308 participants in the analyses of smoking status, age started smoking, pack years of smoking, and number of unsuccessful stop-smoking attempts, respectively. After adjusted for potential confounders, MSP demonstrated significant associations with offspring smoking (OR: 1.08 [95% CI: 1.07, 1.10]), age started smoking (beta per year: -0.83 [95% CI: -0.89, -0.77]), pack years of smoking (beta per pack-year: 3.51 [95% CI: 3.28, 3.74]) and number of unsuccessful stop-smoking attempts (IRR: 1.11 [95% CI 1.09, 1.13]). Subgroup analysis showed the excessive risks for smoking status and age started smoking in females, pack years of smoking in males, and for number of unsuccessful stop-smoking attempts in the non-breastfeeding group. The unfavorable effects of maternal smoking around birth might reach at least up to offspring's middle even older age. Smoking cessation before pregnancy should be encouraged to prevent the transmission to the next generation.

Market-Level Features May Influence a Hospital's Decision to Perform Robotic Radical Cystectomy in Florida.

Adoption of robotic radical cystectomy (RC) occurred before the availability of randomized data supporting oncologic noninferiority of this approach. We hypothesized that market-level features may have influenced a hospital's likelihood of offering robotic RC. We used the Florida Inpatient Discharge data set to identify patients who underwent RC for bladder cancer from 2013 to 2020 and compared characteristics between facilities that performed robotic or only open RC. Market features assessed included hospital operating margin, mean per capita income, and the Herfindahl-Hirschman index-a measure of market concentration. Multivariable logistic and negative binomial regression models were fit to evaluate features associated with robotic RC. We identified 4723 patients, of whom 891 (19%) underwent robotic RC. Among the 96 hospitals, 45 (47%) performed at least 1 robotic RC. After multivariable adjustment, features associated with increased odds of offering robotic RC were increasing mean per capita income of the health service area (odds ratio [OR], 1.05, 95% CI: 1.0-1.1, P = .04), a positive hospital operating margin (OR, 6.6, 95% CI: 1.0-43, P = .05), and a higher average annual cystectomy volume (OR, 9.6, 95% CI: 2.1-45, P = .004). Increasing hospital size (incidence rate ratio, 1.12, 95% CI: 1.11-1.13) and mean per capita income (incidence rate ratio 1.05, 95% CI: 1.04-1.07) were significantly associated with a higher number of robotic RC performed (P < .001). In Florida, local market demand and available financial resources were associated with hospitals offering robotic RC, although market competitiveness was not. These data may be of interest to policymakers investigating adoption patterns of new surgical technology.

A hospital-based special care unit for dementia decreased hospital readmission rates for behaviour while reducing rates of falls and occupational violence across medical wards.

Hospital-based Special Care Units (SCU) for dementia show promise as effective models of care. However, limited research describes hospital-wide benefits. To describe patient-level outcomes and hospital service-level outcomes of a SCU. Pre-post analyses of SCU-patient data and hospital service-unit incident report data. 2-years of SCU-patient admissions and 4-years of hospital incident-reports from four medical wards (2-years pre-post SCU). Admission and discharge severity of SCU-patients' behaviour was prospectively measured by specialist SCU nurses. One-year hospitalisation rates, length-of-stay, diagnosis and patient demographics were retrospectively obtained from medical records. Hospital service-unit data included 4 years of monthly incident report rates for falls, pressure injury and occupational violence (OV) across four medical wards. Analysis of count data used Poisson and Negative Binomial Regression models. 121 SCU admissions involved 107 unique patients. Median SCU LoS was 23days (interquartile range [IQR], 13-50), and stabilisation of behaviour severity took 11days (IQR 6-12). Barriers to discharge related to substitute decision-making and care facility availability. After SCU discharge, yearly hospitalisation rates for 'all-reasons' decreased by 68% (Incident Rate Ratio [IRR], 0.32, 95% CI, 0.23-0.43), and 83% for behaviour-related admissions (IRR 0.17, 95% CI, 0.11-0.28). For hospital service-unit outcomes, falls-per-month decreased by 21% (IRR 0.79, 95% CI 0.64-0.99) after SCU implementation and OV by 26% (IRR, 0.74, 95% CI 0.59-0.94). A hospital-based SCU reduced hospital health service demand through decreased SCU-patient readmissions and was associated with decreased falls and OV rates across hospital medical wards.

The association between 2017 American College of Cardiology/American Heart Association guideline for hypertension and neonatal outcomes in Kenya: a retrospective study

BackgroundHypertension in pregnancy serves to screen for adverse perinatal outcomes. In 2017, the American College of Cardiology and American Heart Association recommended a new blood pressure category with lower hypertension thresholds, excluding pregnancy. This study aimed to explore the association between the 2017 redefined blood pressure categories in pregnancy and neonatal outcomes such as preterm birth and low birth weight.MethodsThis retrospective study used electronic records of the Maternal and Child Health Handbook registered by the Women and Infant Registration System. All women who had at least one antenatal care visit and delivery between January 2017 and April 2020 and between May and December 2022 were included in the study. A birth of less than 37 weeks was defined as preterm delivery. LBW was identified based on a newborn’s birthweight of less than 2500 g. The maximum blood pressure across all antenatal care visits was classified based on the newly recommended criteria. A generalized linear model with binomial distribution and logit link function was used to evaluate the association between new blood pressure categories and neonatal outcomes at different levels of health facilities.ResultsWe analyzed data from 825 women. Of these, the prevalence was 13.7% for elevated blood pressure, 15.2% for stage 1 hypertension, 4.5% for non-severe stage 2 hypertension and 1.2% for severe stage 2 hypertension. For lower-level facilities, no significant associations were identified between the redefined blood pressure category and preterm birth or low birthweight. At higher-level facilities, preterm birth was only significantly associated with severe stage 2 hypertension (adjusted odds ratio:10.94; 95% confidence interval:1.08–110.93; P = 0.04) and low birthweight showed no association with the redefined category.ConclusionThis study revealed no association between redefined lower blood pressure threshold and preterm birth and low birthweight in under-resourced settings. However, previous studies in well-resourced countries with larger sample sizes also reported a significant association. Therefore, further investigations are required.

A hurdle and negative binomial model approach to analyzing the gender differences in diagnostic imaging utilization under high-deductible health plans.

High-Deductible Health Plans (HDHPs) have been increasingly adopted as a cost-containment strategy in healthcare. However, their impact on the utilization of diagnostic imaging services, particularly across different genders, remains underexplored. This study explores how HDHPs enrollment affect imaging utilization rates and usage patterns among patients of different genders, and it examines the associated gender disparities across various imaging modalities. Using data from the 2010 Thomson-Reuters MarketScan Commercial Database, we conducted a quantitative analysis employing Negative Binomial Regression and Hurdle models. The models assessed the association between HDHPs enrollment and diagnostic imaging utilization, with a focus on gender-based differences in usage patterns. The analysis revealed that males generally utilize diagnostic imaging services less frequently than females. After HDHPs enrollment, overall imaging utilization declined by 7%, with a more pronounced reduction observed among male enrollees. Specifically, the likelihood of initial ultrasound utilization among males dropped by 8.2% more than among females. However, once at least one imaging procedure had been initiated, gender differences in utilization among HDHPs enrollees were no longer significant. The findings suggest that HDHPs have a gender-differentiated effects on diagnostic imaging utilization, with males experiencing a more significant reduction, especially in the initial use of diagnostic imaging and in the use of ultrasound services. These results highlight the need for gender-sensitive approaches in health insurance policy design and emphasize the importance of targeted patient education to promote equitable access and resource allocation.

Worldwide Trend Observation and Analysis of Sheep Pox and Goat Pox Disease: A Descriptive 18-Year Study.

Sheep and goat pox (SGP) are animal diseases of important economic impact which have been emerging into new geographic areas, including occasional incursions in disease free countries. The main objective of this study is to observe and analyse the global distribution of SGP during an 18-year period (2005-2022). Countries' SGP epidemiology was characterised by classifying them according to the frequency of reporting years. A negative binomial regression model was used to test for associations between the economic status of a country, the sheep and goat populations, the continent, and the likelihood of an SGP outbreak occurring. A change-point analysis was used to determine significant change points of outbreaks for 18 years. Countries which presented high endemic status were mostly located in the North African region, the Middle East, and Asia, in particular India and China. Economic status was found to be significant for outbreak occurrence in endemic countries, in contrast to countries with outbreaks occurring where other socio-economic factors influence the disease occurrence. The total sheep and goat population was found to be significantly associated with countries and regions. The change-point analysis showed that changes in outbreak occurrence were observed when countries with most reported outbreaks controlled the diseases. While the husbandry and social conditions that exist in certain regions, particularly of Africa and Asia, make the prospect of SGP eradication highly unlikely, an effective implementation of vaccination strategies and control policies would decrease the incidence of SGP, improving animal health and economics in affected countries.

Urinary total 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanonol is positively associated with tooth loss

Background/aimEpidemiological studies had confirmed a fundamental association between smoking and tooth loss, but it remains unclear whether metabolites of tobacco products such as total 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanonol (TNNAL) play a role in the incidence and progress of tooth loss. This study aims to investigate the relationship between TNNAL and tooth loss as well as how systemic inflammatory indexes mediate this process.MethodsThe cross-sectional study data were collected from the National Health and Nutrition Examination Survey conducted in the United States. After screening and comparing the baseline data, zero-inflated negative binomial regression models were utilized to evaluate the relationship between urinary TNNAL level and missing teeth among whole population and participants with different smoking status. Furthermore, bootstrapping was applied to test the mediation effect of systemic inflammatory indexes between TNNAL level and missing teeth.Results7726 participants were included, having 2958 individuals belonging to the TNNAL = 0 group and 4768 in the TNNAL > 0 group. In the model with covariates fully adjusted (model 3) among whole population, TNNAL level was found to be positively correlated with tooth loss [Incidence Rate Ratio (IRR) = 1.107, 95% confidence interval (95% CI) = 1.074–1.140], especially in the fourth quartile (Q4) of TNNAL level (IRR = 1.715; 95%CI = 1.535–1.916) compared to the Q1. Red blood cell distribution width (RDW) and monocyte/highdensity lipoprotein cholesterol ratio (MHR) played partial mediating role in the association between TNNAL and tooth loss, and the indirect effect of each was 0.0242 (RDW, 95%CI = 0.0076–0.0612) and 0.0151 (MHR, 95%CI = 0.0034–0.0426), respectively. The mediating effect was 0.393 (95%CI = 0.0179–0.958). In the regression model 3 among group of TNNAL > 0, higher concentration of urinary TNNAL was associated with increasing tooth loss (IRR = 1.079, 95%CI = 1.047–1.112). When group of TNNAL > 0 was further divided into subgroups according to the smoking status, a positive correlation was found between TNNAL and missing teeth among current active-smokers (Model 3: IRR = 1.508, 95%CI = 1.341–1.696), as well as passive former-smokers (Model 3: IRR = 1.127, 95%CI = 1.021–1.243).ConclusionsOur study revealed a positive relationship between urinary TNNAL and tooth loss, and further demonstrated the mediating role of RDW and MHR between the TNNAL and the number of missing teeth in the whole popualtion. These findings will provide new theoretical insights for policy formulation and clinical therapeutic for the target prevention and intervention of related diseases.

Association Between the Social Vulnerability Index and Adverse Pregnancy Outcomes.

To assess the association between the Social Vulnerability Index (SVI) and racial disparities in pregnancy outcomes across U.S. counties and to quantify these racial disparities. This was a cross-sectional study using restricted Centers for Disease Control and Prevention data sets, including natality data sets, fetal death data sets, and all-cause mortality data sets from 2016 to 2021. We limited analyses to Black or White individuals aged 15-44 years from 3,114 U.S. counties. Participants were categorized into quartiles based on county-level SVI. The primary outcome was maternal mortality rate while pregnant or within 42 days of the end of pregnancy, and secondary outcomes were pregnancy-related mortality while pregnant or within 365 days of the end of pregnancy, stillbirth, and preterm birth. Mixed-effect generalized linear models with negative binomial distribution were used to quantify disparities, using difference-in-difference analysis to measure the difference in outcomes between Black and White individuals across different levels of social vulnerability (first quartile as referent). A total of 20,189,328 individuals were included, distributed across SVI quartiles as follows: first quartile 2,558,131, second quartile 4,945,774, third quartile 6,827,503, and fourth quartile 5,857,920. Black individuals experienced significantly higher rates of maternal mortality, pregnancy-related mortality, stillbirth, and preterm birth compared with White individuals regardless of SVI quartiles. Difference-in-difference analyses demonstrated that disparities in maternal mortality rate were significantly larger in the second, third, and fourth quartiles compared with the first quartile (difference-in-difference 14.22 [95% CI, 2.11-26.33], 12.53 [95% CI, 1.26-23.81], and 18.82 [95% CI, 6.67-30.98], respectively). A worsening disparity in pregnancy-related mortality was observed in the fourth quartile, whereas disparities in stillbirth and preterm birth did not show significant differences across SVI quartiles. Racial disparities in maternal mortality intensified in counties with higher social vulnerability. These findings underscore the need for targeted interventions to address social determinants of health.

Pediatric antibiotic use associated with respiratory syncytial virus and influenza in the United States, 2008-2018.

Understanding of the contributions of respiratory syncytial virus (RSV) and influenza infections to pediatric antibiotic use is limited. We aimed to estimate the proportions and incidence of outpatient antibiotic prescriptions associated with RSV and influenza infections in a sample of commercially-insured US children. We conducted a retrospective study of outpatient antibiotic prescriptions dispensed to children in the Optum Clinformatics™ DataMart from 2008-2018. We used negative binomial time-series models regressing weekly antibiotic prescriptions against RSV and influenza circulation measures to estimate counterfactual rates of antibiotic prescriptions in the presence and absence of RSV and influenza circulation overall, by age group, census division, and antibiotic class. We considered both syndromic (medical claims) and laboratory (National Respiratory and Enteric Virus Surveillance System) RSV and influenza measures and controlled for age, division, 13-valent pneumococcal conjugate vaccine introduction, and seasonal and secular trends. An estimated 6.3% (95% confidence interval 5.2-7.3%) and 3.4% (3.1-3.8%) of antibiotic prescriptions were associated with RSV and influenza, respectively. These estimates translate to 72.6 (59.7-85.9) RSV-associated and 40.0 (35.1-45.1) influenza-associated antibiotic prescriptions per 1000 children annually. RSV-associated antibiotic prescription incidence was highest among children aged ≤5 years while influenza-associated antibiotic prescriptions were highest among children >5 years. Macrolides were the antibiotic class for which RSV and influenza accounted for the greatest share of prescribing. RSV and influenza account for meaningful proportions of pediatric antibiotic prescriptions. Measures to prevent RSV and influenza infections in children, including immunization, may reduce antibiotic use and aid in mitigating antibiotic resistance.

INVESTIGATING FACTORS AFFECTING ABSENTEEISM DUE TO HEALTH PROBLEMS USING COUNT DATA MODELS

This study aims to determine the factors affecting the number of days individuals are absent from work due to health problems in the last 12 months by using the Poisson Regression Model, Negative Binomial Regression Model, Zero-Inflated Poisson Regression Model, and Zero-Inflated Negative Binomial Regression Model using the micro data sets of the Turkey Health Survey conducted by the Turkish Statistical Institute in 2022. The model results indicate that the variables of age, marital status, education level, general health status, occupation, receiving psycho-social support health services from primary health care institutions, illness lasting/expected to last 6 months, and hypertension in the last 12 months are significant. It was found that women were absent from work more days than men, that the number of days individuals were absent from work decreased as their age increased, and that individuals were absent from work more as their general health worsened.

Seroepidemiological investigation of SARS-CoV-2 infection and risk factors in Indonesia before mass COVID-19 vaccination.

At the onset of the coronavirus disease 2019 (COVID-19) pandemic in Indonesia, surveillance focused on finding and treating symptomatic cases. However, emerging evidence indicated that asymptomatic and pre-symptomatic individuals significantly contributed to viral transmission. This highlights the need for comprehensive surveillance to understand better the actual spread of SARS-CoV-2. Therefore, the aim of this study was to determine the seroprevalence of SARS-CoV-2 antibodies in the general population across Indonesia and identify risk factors associated with infection at the beginning of the pandemic. A cross-sectional survey was conducted across 17 provinces, 69 districts/cities, and 1,020 villages in Indonesia from December 22, 2020, to February 15, 2021. A multistage random sampling technique was employed. Serological testing using enzyme-linked immunosorbent assay (ELISA) was performed to detect anti-SARS-CoV-2. Complex sample analysis, adjusted for weights, was utilized to estimate the national seroprevalence and a generalized linear model with a binomial distribution was applied to identify risk factors. A total of 10,161 individuals were included in the final analysis, with the national seroprevalence being 14.8% (95% confidence interval (CI): 14.2-18.5). The prevalence was higher in females (16.8%; 95%CI: 12.5-22.3), individuals aged 46-59 years (18.6%; 95%CI: 14.2-24.0), and in urban areas (20.1%; 95%CI: 15.0-26.2). The highest prevalence was observed in North Maluku (35.6%; 95%CI: 29.3-42.5). Notably, 54.2% of seropositive individuals were asymptomatic, while 7.5% reported hypertension as a comorbidity. Factors associated with higher seroprevalence were being married (adjusted prevalence ratio (aPR): 1.47; 95%CI: 1.02-2.12), widow (aPR: 1.74; 95%CI: 1.01-3.00), and close contact with confirmed cases (aPR: 2.04; 95%CI: 1.52-2.73). This study revealed a COVID-19 prevalence significantly higher than official estimate in Indonesia, underscoring the need for improved surveillance system to more accurately track disease spread and to inform timely public health responses in the future.

Impact evaluation of an interdisciplinary approach to patients with chronic non-cancer pain in Chilean primary care

IntroductionChronic non-cancer pain affects one-third of the global population. In Chile, its prevalence is estimated at 34%, surpassing the prevalence of diabetes mellitus and hypertension. Its high costs reveal that clinical treatment causes the greatest economic impact, followed by days of work absenteeism.ObjectiveThis study aims to evaluate the impact on resource consumption, quality of life, and pain perception in patients with CNCP, an interdisciplinary approach implemented in Chilean primary care public health.MethodsA concurrent cohort study was conducted with patients aged 25 to 64 with chronic non-cancer musculoskeletal pain. The population studied was 698 patients receiving primary health services in centers with similar size and territorial proximity. The clinical intervention introduced patient-centered care, psychotherapy and physiotherapy from the perspective of the neuroscience of pain. The impact analysis was conducted using negative binomial regression models, generalized linear models, and ordered logistic regressions.ResultsResults show that the patients who were intervened increased the number of physician consultations at primary care (IRR: 1.56; 95% CI 1.30–1.87) and increased medication consumption (coef 2.38; 95% CI 2.10–2.67) compared to control patients. Intervened patients improved their quality of life (COEF 0.14; 95% CI 0.09–0.19), and pain perception was statistically significant. Despite the health system’s structural, cultural, and organizational barriers, the intervention was implemented and consolidated in daily operation, providing learnings for a further scale-up.ConclusionThe study demonstrates that an interdisciplinary approach to chronic non-cancer pain management in Chilean primary care improves quality of life and pain perception while increasing healthcare resource use. Despite system barriers, the intervention was successfully implemented and sustained within patient-centered care. These findings highlight the need for resource reallocation to ensure long-term sustainability and scalability through the public health system.

Spatio-temporal pattern and risk factors associated with cholera outbreaks in selected high-risk areas of Kenya.

Cholera is a public health challenge in Kenya. This study aimed at identifying the spatio-temporal pattern of cholera and its associated risk factors in high-risk areas to optimize resource use for targeted control. The study was conducted in Mukuru, an informal settlement, Dadaab refugee camp and counties bordering Lake Victoria. Cholera line list data from 32 subcounties (2013-2022) was sourced from Kenya's Ministry of Health. Population and water, sanitation and hygiene data came from the 2019 census. Space-time scan statistic (SaTScan) were used to carry out spatio-temporal analysis and a zero-inflated negative binomial regression model evaluated cholera risk factors. A total of 7316 cholera cases were reported across 22 (69%) subcounties, the highest numbers in 2015, 2016 and 2022 affecting 21, 12 and 3 subcounties, respectively, and none in 2014. Five high-risk space-time clusters encompassing 15 subcounties were identified, with Dadaab and Fafi showing persistent outbreaks. Improved sanitation was the only variable that suggested significant protective effects to cholera control (relative risk 0.9445, p=0.001). Dadaab and Fafi subcounties were extremely high-risk and improved sanitation significantly reduced cholera outbreaks. These data inform cholera intervention policies in vulnerable regions.

Modeling Geographically Weighted Negative Binomial Regression on The Incidence of Adolescent Smoking in Indonesia

This study aims to determine the significant factors affecting adolescent smoking cases in Indonesia with the Geographically Weighted Negative Binomial Regression model. The research method uses a quantitative approach to identify the relationship of each variable and analyze the effect of a treatment. Data analysis was processed using the GWNBR model with the help of R-Studio. The results showed that the case of teenage smoking experienced overdispersion of data with factors that had a significant effect, namely the percentage of poor people, the level of education of parents, the price of cigarettes, the level of income and the percentage of working teenagers, with factors that had a significant effect spatially, namely the percentage of poor people and the percentage of working teenagers. So it can be concluded that the spatial pattern of smoking incidence in Indonesia based on the results of the spatial heterogeneity test shows significant variation across provinces, so that the spatial pattern of the incidence of adolescent smoking is heterogeneous.

Sales concentrations of digital brands

ABSTRACT This study compares the observed and theoretical sales concentration levels for over 200 digital brands in 18 diverse online categories and four countries. It applies the Pareto Share, ‘heavy half’ and Negative Binomial Distribution (NBD) to online brand purchase frequencies with a classic empirics-first approach. From the results, it emerged that, on average, the digital Pareto Share is 47% and the heavy half of a brand’s buyers contribute to 71% of its online sales. That is, the heaviest 20% of a brand’s online customers account for just under half its sales, and about seven in ten sales are from buyers who purchased the brand more often than the median frequency. These outcomes closely match the NBD’s theoretical expectations. Besides advancing empirical research on sales concentration for digital brands, this study provides valuable practical guidelines for effectively targeting (or ‘activating’) online buyers based on sales concentration levels.

The Pivotal Set of a Boolean Function

We define the pivotal set of a Boolean function and we prove a fundamental inequality on its expected size, when the inputs are independent random coins of parameter p. We give two complete proofs of this inequality. Along the way, we obtain the classical Margulis–Russo formula. We give a short proof of the classical Hoeffding inequality for i.i.d. Bernoulli random variables, and we use it to derive more complex deviations inequalities associated to the pivotal set. We finally follow Talagrand’s footsteps and we discuss a beautiful inequality that he proved in the uniform case.

Association between greenspace morphology and dengue fever in China

BackgroundAlthough the contribution of greenspace to dengue transmission has been reported, the complex role of greenspace morphology remains unclear. We aimed to investigate the relationship between greenspace morphology and dengue in China and to explore the interaction with urbanization and built environment characteristics.MethodsDengue data at the township level were collected from five provinces in southern China during 2017–2020. Metrics of greenspace morphology, including percentage, mean area, fragmentation, shape, aggregation, and connectedness, were calculated to quantify its structural characteristics. A negative binomial regression model combined with principal component analysis was conducted to assess the relationship between greenspace morphology and dengue. The modification effects of urbanization and built environment characteristics were evaluated using an interaction term in the model.ResultsPer-interquartile range increase in total percentage, mean area, area-weighted mean shape index, and aggregation index of greenspace were associated with 1.78 (95% confidence interval [CI] 1.57–2.01), 1.14 (1.10–1.20), 1.17 (1.06–1.29), and 1.18 (1.11–1.26) incidence rate ratios of dengue, respectively, while edge density was negatively related to the risk of dengue. In areas with high gross domestic product per capita and population size, the impact of greenspace morphology on the incidence of dengue was more pronounced. By contrast, the influence of greenspace morphology on dengue risk was diminished in regions characterized by higher urban isolation and fragmentation.ConclusionsGreenspace morphology had a bidirectional impact on the risk of dengue, with urbanization and built environment characteristics exerting diverse modification effects. Our study highlights the importance of a rational greenspace layout to prevent the spread of dengue.Graphical