Articles tagged with Statistical Analysis
A new statistical method called CLIMB provides a more efficient way to analyze genomic data across multiple conditions. The method combines principles from two traditional techniques, reducing computational intensity and producing biologically interpretable results.
A computational study found that adding more than two stratification factors to a phase 2 trial can significantly reduce its statistical power, making it harder to detect a positive result. For modestly sized trials with 84 participants, using four or six stratification factors resulted in power decreases of 13% and 25%, respectively.
A Rutgers-led study statistically evaluated government data to determine if COVID-19 vaccination increases the incidence of Guillain-Barré syndrome. The results show no significant association between any COVID-19 vaccinations and the disease.
A new study found that children infected with COVID-19 have a substantially higher risk of developing type 1 diabetes, with a 72% increase in new diagnoses in the six months following COVID diagnosis. Pediatricians and families should be alert for symptoms of diabetes following COVID.
A new University of Toronto study finds an additional 514 deaths should be added to the official Hurricane Maria death toll due to displaced Puerto Ricans in the US. The study suggests undercounting and highlights the need for equitable disaster preparedness and cross-jurisdiction data sharing.
A study by Hokkaido University researchers found a significant increase in suicide rates among women and younger age groups during the COVID-19 pandemic in Japan. Excess suicide deaths for men and women were recorded, with sub-group analyses revealing a positive correlation between increased mortality and specific age ranges.
A new study finds that climate data, particularly UV radiation levels, can help accurately model the spread of COVID-19. The research analyzed data from 196 countries and found that high UV radiation levels are strongly associated with reduced COVID-19 transmission rates.
Researchers at King Abdullah University of Science & Technology (KAUST) have developed a more robust and realistic general method for dealing with wind-driven phenomena in geostatistical modeling, which promises to greatly improve the accuracy of pollutant dispersion prediction.
A study by Duke-NUS Medical School and collaborators found that cooler ambient temperatures increased the risk of a specific type of myocardial infarction (heart attack) in Singapore. People aged 65 and above were particularly vulnerable to this risk, with a 20% higher risk compared to younger individuals.
Research in the American Journal of Preventive Medicine reveals a significant association between paid sick leave requirements and reduced mortality among US adult workers. The study found that state preemption laws hindering local mandates contribute to increased workforce mortality.
A new study sheds light on the ancestry of manatees, tracing their evolution back 47 million years to northern Africa. The research suggests that modern manatees migrated from South America to the Caribbean and North America around 34 million years ago, with some species thriving in communities for millions of years.
Researchers at Linköping University developed a new analysis model to estimate the number of wild animals harvested through hunting in Sweden. The model provides a better estimation of wild animal populations and reduces uncertainty, making it easier to track changes in ecosystems.
A multi-institutional team assessed the diagnostic criteria for canine glioma using the Comparative Brain Tumor Consortium's guidelines. The study found that consensus was achieved for 71 out of 85 cases (84%), with a moderate level of inter-pathologist agreement.
A study of environmental students from 41 countries found that SDGs are highly accepted globally, with significant differences in pillar ratings between countries. Lower-income nations rated the SDGs as more important than higher-income nations.
A nationwide analysis found that 88.9% of the population lives within 5 miles of a community pharmacy, but only 48.1% live within 1 mile. The study highlights the importance of pharmacies in providing access to healthcare services, particularly for rural residents.
A study of 17 African coastal countries found that those farther from the coast have lower standards of living, with fewer owning radios, TVs, and vehicles. Access to education and infrastructure are key factors in increasing prosperity near ports.
A new study from Dartmouth Cancer Center re-examines claims of high pediatric cancer rates in New Hampshire, revealing the Northeast region has a statistically significantly higher incidence of cancer compared to all other U.S. regions. Within the Northeastern states, no single state is an outlier, with significant variations in incide...
Researchers found that night-shift workers experience disrupted sleep quality and circadian rhythms, even after years of night shift work. Their study, published in eBioMedicine, used wearable tech to monitor 140 workers, revealing a significant impact on health.
A recent study by Xi'an Jiaotong-Liverpool University provides a method to help farmers and policymakers decide whether organic farming is beneficial for the environment. The researchers analyzed international studies to find a threshold where organic farming's biodiversity gain outweighs its land requirements.
Researchers at NJIT are developing a mixed-reality system that can provide coaches with real-time statistics, facial interpretation data, and remote access to trainers. The system aims to enhance training and decision-making in team sports.
A Concordia study analyzed gender patterns in AI over two decades, finding women are making strides despite underrepresentation. Notably, female-male collaboration has increased, while core positions held by women remain scarce, tied to factors like family obligations and male-dominated environments.
A study by Cornell University researchers found that online retail images of models have statistically lighter skin tones than videos of the same product and model. The discrepancy was also linked to 'tokenism,' where one model with darker skin is used to represent a range of diversity.
A new study uses machine learning to analyze temperament data from 4,438 babies to classify their age and gender. While algorithms struggle to distinguish between infants under 48 weeks old, accuracy improves as they age, suggesting that gender differences in infancy become more apparent around this time.
A new study reveals that urban residents have a simplistic understanding of coastal ecosystems and are less likely to take pro-environmental actions. The research highlights an issue known as urbanized knowledge syndrome, which can harm natural ecosystems and undermine community resilience.
Researchers at Eötvös Loránd University detected smallest earthquakes in micron-scale metals, exhibiting characteristics similar to seismic events. The findings reveal a two-level structure of strain bursts and demonstrate the correlation between acoustic signals and plastic deformation.
A new Concordia study reveals that climate change affects the province-wide analysis of landscape freeze-thaw cycles, leading to increased greenhouse gas emissions in northern regions and transitional days in southern areas. This can have significant impacts on infrastructure and greenhouse gas emissions.
A new study published in the Chinese Medical Journal assessed mortality risk in middle-aged and older Chinese individuals with multiple diseases. The study identified four multimorbidity patterns, with cardiometabolic being the most common, and found that individuals with these patterns had a significantly increased mortality risk.
A multicenter study found that only 42% of patients with a visualization score C on surveillance exams maintain the same score on follow-up exams. The study suggests that alternative surveillance strategies may be necessary for patients at risk for HCC, particularly those with severe steatosis and advanced cirrhosis.
Researchers from Tokyo University of Science analyzed usage patterns of bicycles in four major US cities to improve bicycle sharing system efficiency. They found temporal patterns and similarities between weekdays and weekends, contradicting previous studies.
Researchers used a contrast pattern mining algorithm on publicly available data from 16,000 participants in the T1D Exchange Clinic Registry. The study found individuals with an immediate family history of Type 1 diabetes were more frequently diagnosed with hypertension and other co-occurring conditions.
Brainwide association studies need thousands of individuals to yield higher reproducibility, as smaller samples often uncover strong but spurious associations. Larger sample sizes lead to more likely reproductions of correlations, with effect sizes decreasing as the number of participants increases.
A new study by Thomas Pepinsky challenges the idea that language shapes thought and behavior, finding no evidence that linguistic differences affect social and economic outcomes. The study reveals that statistical methodologies used in previous research are prone to producing false positives.
Research from satellite data analysis suggests that three-quarters of the Amazon forest has lost its ability to recover from perturbations since the early 2000s. This loss of resilience increases the risk of dieback and contributes to global warming, highlighting the urgent need for limiting logging and greenhouse gas emissions.
A study by Texas A&M researchers found that navigation systems frequently guide drivers to take paths with a greater risk of crashes, despite reducing travel time. The study analyzed road and traffic characteristics in five metropolitan areas and proposed a new system architecture for finding the safest route using navigation systems.
A new study co-authored by Indiana University professor M. Daniel Beneish finds that the M-Score model is still the most economically viable means of predicting corporate fraud. The model's success rate has been doubled, but at a higher cost of false positives, making it less practical for auditors to use in practice.
Researchers found that smartphone app usage patterns can be used to identify individuals with over 30% accuracy. The study analyzed data from 780 people and showed consistent patterns in application usage behaviors on a day-to-day basis. This highlights the potential risks to privacy when using apps automatically collected by smartphones.
A small study found statistically significant improvements in various symptoms, including fatigue and chest discomfort, after EECP therapy in long COVID patients. Researchers believe this is the most plausible explanation for the benefits derived from EECP and its link to long COVID.
KAUST researchers have developed a flexible statistical model to analyze environmental data, revealing niches where existing methods fall short. The study provides a new approach to modeling dependence structures, highlighting the importance of understanding model limitations and extrapolation beyond observed data.
A new method, ONEST, was developed to assess the performance of diagnostic tests with multiple observers. The method helps determine if adding more observers causes agreement to plateau, indicating an unreliable test or a minimum number needed for stable estimation.
Researchers at Boston University developed a real-time method for projecting COVID-19 quarantine needs in congregate housing settings ten days in advance. The team's findings were published in the American Journal of Public Health and can be used as a predictive tool to allocate resources.
A global competition between approximation methods for analyzing large spatial datasets shed light on their statistical efficiency. The competition compared various methods using synthetic spatial datasets and revealed the performance of different approaches, providing a unified framework for understanding existing approximation methods.
Researchers at Penn State developed a new risk score system that uses genetic data to predict obesity in young children. The scores, called polygenic risk scores, can be easily interpreted and have been shown to be effective in identifying children most at risk for developing obesity.
A study by sociologist Dr. Ansgar Hudde found that city dwellers with high education levels cycle significantly more than those living in rural areas, with a strong correlation between education level and bicycle mobility. This trend is attributed to the perceived status and health benefits associated with cycling.
A study by University of Leeds researchers found that compulsory mask wearing in Bangladesh led to an increase in mobility and a rise in COVID-19 cases. The study analyzed Google community mobility data and found statistically significant evidence of risk compensation, where people adopted riskier behavior if they felt safer with masks.
A recent study reveals that narwhals are highly affected by noise pollution from ships and seismic airgun pulses, triggering stress and altering their behavior. Researchers hope that better management of noise pollution will protect these unique Arctic animals.
A team developed statistical models to predict the risk of early death in patients with non-intensive AML therapy. The models incorporated various health measures and quality-of-life scores, showing modest success in predicting outcomes.
Researchers from Harvard University and others have found that large-scale COVID-19 vaccination surveys were off by up to 17 percentage points due to systematic biases in the data. The 'Big Data Paradox' highlights how big data sets can minimize one type of error while magnifying another, leading to misleading results.
New Cornell University research suggests that social connections can distort voting behavior, favoring minority candidates. The study found that complacency and dejectedness – conditions caused by social connections – can skew election outcomes.
A new statistical analysis supports the notion that COVID-19 became more lethal in the UK in late 2020, with increased lethality attributed to factors beyond just the alpha variant of the virus. The study used Bayesian inference to draw stronger conclusions from weekly data on cases and deaths.
A Dartmouth study found that the stratified approach to statistical modeling in health services research can lead to inaccurate conclusions about disparities and inequities in healthcare. Joint modeling, on the other hand, provides a more accurate estimate of physician treatment patterns across different patient types.
Research in Japan found a link between financial knowledge, age, and gender, suggesting potential policy targets to improve financial health. While men had higher financial literacy, women reported more sound financial behaviors, indicating that policies may need to focus on supporting women's financial decision-making.
Eukaryotic plankton are highly diverse taxonomically, phylogenetically, and ecologically. The study found that ocean currents significantly influence their biogeography, with smaller organisms being more sensitive to local environmental conditions.
Researchers identified 23 genes contributing to congenital heart disease, including 12 previously unknown, using a new algorithm called M-DATA. This method combines genetic data from people with related conditions, increasing the power to identify risk factors and potentially leading to improved treatments.
Damaged coral reefs exhibit a two-phase recovery pattern, with the first phase lasting up to six years, and the second phase being faster. This pattern was observed in 60% of severely disturbed reefs on the Great Barrier Reef.
Researchers at Boston University have developed a new online risk prediction model for breast cancer in Black women, suitable for use in primary care settings. The model is well-calibrated and discriminatory accurate, with the highest accuracy for women under age 40.
Researchers launched an open competition to benchmark existing and novel methods for quantifying anomalous diffusion. The analysis of results provided an objective assessment of method performance, contributing to the definition of standard tools for trajectory analysis.
A new analysis spanning 10,000 years of history and ten major world regions found that world population size, major technological advances, and geographical connectivity are key drivers of military technology evolution. The study's methodology employed a resource called Seshat: Global History Databank to empirically test prior hypotheses.
The study found that advances in iron metallurgy, horse riding, and agricultural productivity played a significant role in the development of military machines. Mega-empires emerged as societies supporting tens of millions of inhabitants and covering vast territories.
A study of 2,329 academic journals found a significant gender gap in manuscript submissions during the first COVID-19 wave, with women submitting fewer papers than men, especially in health and medicine.
The study identifies promising topics for scientific collaboration, including medicine, engineering, computer science, and agricultural sciences. BRICS Plus countries have significant growth potential in research and development, with some already ranking among the top 30 countries globally.