Robust Regression Model Research Articles

A quantile regression approach to identify risk factors for high blood glucose levels among Bangladeshi individuals.

Diabetes mellitus, characterized by high blood glucose, is an overwhelming public health concern globally, including in Bangladesh. The implication of this trend may pose a significant challenge to the health systems due to the lack of awareness and improper management of this chronic disease. To formulate strategies for public health planning, this study aims to explore the potential risk factors for elevated blood glucose levels among Bangladeshi individuals using advanced statistical methods and a nationally representative data set. This study utilized data from the 2017-18 Bangladesh Demographic and Health Survey and included 11,863 individuals. A nonparametric Kruskal-Wallis test assessed the significant association between fasting plasma glucose levelsand various risk factors. Additionally, a robust quantile regression model was applied to examine the net effects of each risk factor at different quantiles of the distribution. The prevalence of diabetes is 8.1% among individuals in the study population, with variations observed across different administrative divisions in the country. Respondents from the Dhaka division respondents had a higher likelihood (24.1%) of having elevated plasma glucose and the Rangpur division had a lower risk (10.3%) of developing diabetes disease. This study identified several potential risk factors associated with elevated blood glucose levels, including hypertensive disease, overweight and obese body mass index, higher economic status, reduced physical activities, and older age, significantly contributing to develop diabetes mellitus. This study recommends promoting healthy lifestyles, increased physical activity, effective hypertension management, obesity reduction, and nationwide screening programs to control diabetes and noncommunicable diseases in Bangladesh. These preventive measures are crucial for reducing the existing prevalence of diabetes and working towardachieving the Sustainable Development Goals by 2030.

Brain age gap, dementia risk factors and cognition in middle age

AbstractBackgroundBrain Age Gap (BAG) represents the difference between an individual’s predicted age, derived from machine learning models trained on neuroimaging data, and their chronological age. BAG has been associated with dementia and cognition in old age. Less is known relating BAG to dementia risk‐factors or cognitive performance in middle‐age.MethodCognitively healthy, middle‐aged (40‐59 years) subjects from PREVENT‐Dementia had an array of neuropsychological, neuroimaging and genetic assessments. Brain Ages were predicted from T1‐weighted 3T MRI scans. Cognition was assessed using COGNITO. Multiple linear robust regression models tested hypotheses that: (i) BAG is positively associated with dementia risk‐factors; (ii) increased BAG is associated with worse cognition; (iii) longitudinal BAG change is positively associated with longitudinal cognitive deterioration. A range of machine learning algorithms with nested cross‐validation was used to assess whether BAG and cognition could predict each other.Result552 middle‐aged participants (median age 52.8 years) had all baseline assessments; 68 had amyloid PET data and 138 had longitudinal data. Median BAG was ‐2.0 years with a range from ‐21.2 to 18.4 years (Figure 1). BAG in middle‐age was associated with hypertension (p = 0.007) and alcohol intake (p = 0.008) but not APOE4 carrier status (p = 0.14) or amyloid centiloids (p = 0.53). BAG was not associated with cognitive performance either cross‐sectionally (p = 0.74) or longitudinally (p = 0.30), and there was no added predictive value between BAG and cognition. More education was associated with better cognition (p = 4.7×10−11) but not with BAG (p = 0.32).ConclusionEven in midlife, substantial inter‐individual heterogeneity exists in the extent to which brains have aged. BAG in middle‐age is associated with modifiable dementia risk‐factors, suggesting that lifestyle risk‐factor modification needs to start at, or before, midlife to optimise brain health. BAG in middle‐age was not associated with risk‐factors for Alzheimer’s disease (APOE4, amyloid deposition) or cognitive performance, despite there being a plausible and expected association between more education and better cognitive performance. These results are important for understanding brain‐age in middle‐aged populations who might be the target of future dementia‐preventing therapies.

A Remote Sensing Approach for Assessing Daily Cumulative Evapotranspiration Integral in Wheat Genotype Screening for Drought Adaptation.

This study considers critical aspects of water management and crop productivity in wheat cultivation, specifically examining the daily cumulative actual evapotranspiration (ETa). Traditionally, ETa surface energy balance models have provided estimates at discrete time points, lacking a holistic integrated approach. Field trials were conducted with 22 distinct wheat varieties, grown under both irrigated and rainfed conditions over a two-year span. Leaf area index prediction was enhanced through a robust multiple regression model, incorporating data acquired from an unmanned aerial vehicle using an RGB sensor, and resulting in a predictive model with an R2 value of 0.85. For estimation of the daily cumulative ETa integral, an integrated approach involving remote sensing and energy balance models was adopted. An examination of the relationships between crop yield and evapotranspiration (ETa), while considering factors like year, irrigation methods, and wheat cultivars, unveiled a pronounced positive asymptotic pattern. This suggests the presence of a threshold beyond which additional water application does not significantly enhance crop yield. However, a genetic analysis of the 22 wheat varieties showed no correlation between ETa and yield. This implies opportunities for selecting resource-efficient wheat varieties while minimizing water use. Significantly, substantial disparities in water productivity among the tested wheat varieties indicate the possibility of intentionally choosing lines that can optimize grain production while minimizing water usage within breeding programs. The results of this research lay the foundation for the development of resource-efficient agricultural practices and the cultivation of crop varieties finely attuned to water-scarce regions.

Five decades of productivity gains in the Louisiana sugar industry

AbstractThis study analyzed trends across five decades of productivity data from the Louisiana Sugar Industry, from 1969 to 2021, for sucrose content, cane yield, and sugar yield. Trends over the five decades were revealed using robust regression models, and the least square means allowed for decade‐wise comparisons of trends. Sucrose content increased 45%, from 80.9 ± 6.4 g kg−1 in the first (1969–1979) to 116.7 ± 4.8 g kg−1 in the fifth (2010–2021) decade, at 0.85 ± 0.06 g kg−1 per year. Cane yield increased slower (32.2%), from 57.7 ± 5.9 Mg ha −1 in the first to 76.3 ± 6.3 Mg ha−1 in the fifth decade, at 0.45 ± 0.07 Mg ha−1 per year. Sugar yield increased 93% from the first (4.6 ± Mg ha−1) to the fifth (8.9 ± 0.76 Mg ha−1) decade at 0.1 ± 0.01 Mg ha−1 per year. The gains were neither significant nor consistent when comparing successive decades, incremental rather than rapid, and maintained once achieved. Significant (p < 0.05) gains in all traits occurred only in the third decade (1990–1999) with yearly increases of 1.15 ± 0.30 g kg−1 for sucrose content, 3.00 ± 0.27 Mg ha −1 for cane yield, and 0.35 ± 0.05 Mg ha−1 for sugar yield. Comparisons of trait means between successive decades found both significant (p < 0.05) and nonsignificant (p > 0.05) differences; however, comparisons between noncontiguous decades were all significant (p < 0.05). Variety development accounted for 60% of the progress with sucrose content contributing more (10% more) compared with cane yield. The Louisiana sugar industry has experienced substantial productivity gains in the last five decades thanks to a combination of factors with variety development being the most impactful.

Abstract 17639: Association of Retinal Microvascular Changes With Incidence and Progression of Coronary Artery Calcium Score in Individuals With vs Without Diabetes Mellitus; Data From the Multi-Ethnic Study of Atherosclerosis

Introduction: Retinopathy (RP) is a microvascular complication of diabetes mellitus (DM); however, it is also increasingly recognized in persons without DM. Microvascular disease may play a prominent role in coronary heart disease (CHD) development. We performed this study to evaluate the association of grades of RP with incidence of CAC (Coronary Artery Calcium) among those with zero CAC at baseline. Hypothesis: We performed this study to evaluate the association of grades of RP with incidence of CAC among those with zero CAC at baseline and to Identify the association of grades of MA and RP with progression of CAC among those with positive CAC at baseline. Methods: We included 5709 subjects with and without DM from the Multi-Ethnic Study of Atherosclerosis (MESA), who had retinal photos and CAC score available. We analyzed the association of grades of RP with incidence and progression of CAC among subjects with and without DM with zero CAC and positive CAC at baseline from robust regression models. The grades of RP were defined as: no retinopathy, minimal non-proliferative R (NPR) (level 14 -20), early to moderate NPR (level 31-41) and severe NPR or proliferative RP (level 51-80). Results: Among those with zero CAC, in the diabetic group, early to moderate (95% CI [1.2, 2]) and severe (95% CI [1.3, 3]) NPR had significantly higher incident CAC risk than the non-retinopathy group. Among those with positive CAC at baseline, in the diabetic group, the early to moderate NPR group had higher CAC progression than the non-retinopathy group. (95% CI [-146, 228]). In the non-diabetic group, the minimal NPR group had significantly higher CAC progression than the non-retinopathy group (95% CI [1.8, 52.7]). Conclusions: In conclusion, after adjustment for major CHD risk factors, RP with any severity was associated with incident CAC in DM individuals, however only early to moderate NPDR was associated with CAC progression in them.

Using Charge Determination Design of Experiments to Develop A Refrigerant Charge Health Status Model for Heat Pump Systems

Refrigerant based heat pump systems are becoming an integral system in electric vehicle architectures due to their high efficiencies in providing heating and cooling to people and components within the car. An important component in heat pump systems that determines optimal efficiency is the amount of refrigerant. As such, the capability to model refrigerant charge helps quantify the health status of the heat pump system, whereby the lack or over abundance of refrigerant in a heat pump refrigerant system leads to various other component failures, e.g., liquid slugging, compressor overheating, material fatigue in heat exchanger, and degraded/stuck expansion valves. In designing a heat pump system, engineers need to perform a set of design of experiments to determine an optimal refrigerant charge based on a set of performance metrics in the presence of certain noise factors. This optimal refrigerant charge provides conditions where the heat pump system operates efficiently in both heating and cooling, in addition to facilitating operational conditions that will not lead to secondary component degradation or damage. The search for optimal refrigerant charge is classified as refrigerant charge determination, whereby engineers incrementally increase the refrigerant in the heat pump system in operation of heating/cooling and collect data about performance metrics. Some of the key performance metrics used to determine efficiency of a heat pump system include i) compressor inlet superheat temperature, ii) condenser outlet subcool temperature, iii) compressor high side pressure, iv) compressor low side pressure, v) condenser outlet pressure, and vi) condenser quality estimate. Furthermore, this process follows design of experiments concepts and is performed for both heating and cooling modes of operation. In this paper, we leverage refrigerant charge determination as a training data source to develop refrigerant charge models, where several performance metrics are health indicators used as model inputs and the amount of refrigerant added to the heat pump system are ground truth refrigerant charges used as model outputs. In this paper we develop regression models to estimate the total refrigerant charge, which is used to classify different health states of refrigerant based on levels of performance degradation corresponding to specific refrigerant charge thresholds. We trained a robust linear regression model using this charge determination data and found that the worst case estimation error was less than 10% with respect to the refrigerant charge grouth truth.

Pregnancies and births in times of COVID-19

Objective Identify the profile of births of pregnancies of women with internet access who were infected with SARS-CoV-2 and their outcomes. Methods Cross-sectional study integrated into a prospective cohort, with collection between August 2021 and February 2022, based on the responses of 304 women who had pregnancies and/or deliveries during the pandemic period. Results Of the total, 25.7% of the interviewees had COVID-19, with a predominance of diagnoses in the third quarter. Complaints of anosmia, fatigue and headache prevailed as related to the infection. The variables using the Unified Health System for care (p = 0.084); gestational diabetes (p = 0.141); low birth weight (p = 0.117); need for admission to a neonatal unit (p = 0.120) were included in the regression model because they had p values lower than 0.20. The variable referring to the type of delivery (p=1.000) was inserted in the model because it is a variable of interest and with a description of relevance in the literature. Prematurity was the only variable that was statistically associated with SARS-CoV-2 infection during pregnancy (p = 0.008) in the bivariate analysis, explaining the outcome of infection during pregnancy (<0.001), confirmed in the Poisson Robust Regression model. Conclusion There was a high prevalence of COVID-19 in the sample, with varying symptoms and a predominance of operative deliveries. However, SARS-CoV-2 infection only explained the higher occurrence of premature births.

Profit-efficiency analysis of forest ecosystem services in the southeastern US

Technical, allocative, and profit efficiency of longleaf pine (Pinus palustris. Mill) forests in the southeastern United States, producing ecosystem services such as timber, tree biodiversity, water, and carbon sequestration, were estimated. This study employed a non-parametric two-stage approach involving data envelopment analysis (DEA) and robust linear regression. Utilizing data from the Forest Inventory and Analysis (FIA) program spanning 1977–2015 and covering 2,282 forest plots, most longleaf pine forest plots were technically and profit inefficient in ecosystem service production. The inefficiency in profit appeared more attributable to allocative rather than technical inefficiency. Furthermore, the impact of various exogenous variables on inefficiency scores was assessed through robust linear regression. The findings suggested that forest disturbances under private ownership could reduce technical inefficiency. Surprisingly, contrary to stochastic frontier analysis (SFA) results, the robust regression model, considering geographical factors, disturbance, ownership, management, and time in the presence of outliers/influential observations, indicated that disturbances often increased technical inefficiency. Therefore, forest management strategies aiming to mimic or replicate the effects of forest disturbances might compromise the efficiency of ecosystem service provision.

Folic Acid Supplementation during Pregnancy and Its Association with Telomere Length in Children at Four Years: Results from the INMA Birth Cohort Study.

This study examined the association between folic acid supplements (FAs) during different periods of pregnancy and offspring telomere length (TL) at age four in 666 children from the INMA study. FAs were self-reported using food-structured questionnaires during three periods of pregnancy (the first three months of pregnancy, from month fourth onward, and the whole pregnancy). For each period, the average daily dosage of FAs was categorised into (i) <400 μg/d, (ii) ≥400 to 999 μg/d, (iii) ≥1000 to 4999 μg/d, and (iv) ≥5000 μg/d. Leucocyte TL at age four was measured using quantitative PCR methods. Multiple robust linear log-level regression models were used to report the % difference among FA categories. During the first period, and compared with children whose mothers were classified in the reference group (<400 μg/d), children whose mothers took higher dosages of FAs showed shorter TL at age four (≥5000 μg/d). When the first and the second periods were mutually adjusted, children whose mothers self-reported ≥5000 μg/d during the first period of pregnancy had a statistically significant shorter TL than their counterparts (% difference: -7.28% [95% CI: -14.42 to -0.13]). Similar trends were observed for the whole period of pregnancy. When the analysis was stratified by sex, the association was more evident in boys (% difference: -13.5% [95% CI: -23.0 to -4.04]), whereas no association was observed in girls. This study suggests that high dosages of FAs in the first pregnancy period may be associated with a shorter TL in children at age four, particularly among boys. Further studies should confirm these results.

Smashing verb learning through parental sound symbolic input in preterm and full-term children

ABSTRACT Sound symbolism, the iconic link between speech sounds and meanings, helps children’s verb learning. In sound symbolically rich languages such as Turkish, hearing sound symbolic words might facilitate early verb learning and later language-specific expressions of motion events, by providing an easier way to map verbs onto events. These links could be much stronger for children who had difficulties in word-referent mapping (e.g., preterm children). The current study examined the association of Turkish-speaking parents’ sound symbolic input at 20 months with children’s concurrent verb knowledge and later motion event descriptions at 48 months. Ninety-one parent-infant dyads (Mage = 19.92 months, SD = 1.38; 41 preterms) were observed at 20 months, where we measured sound symbolic input and verb knowledge. Sixty-four of these dyads participated in a motion event description task at 48 months (25 preterms, Mage = 48.79 months, SD = 1.68), where we coded how children use path (the trajectory of motion) and manner (how an action is performed) of a motion. Results from the robust regression models suggested that for preterm children, parents’ sound symbolic input used in adverb forms was positively and concurrently related to children’s verb knowledge. Only for full-term children, sound symbolic input (used as adverbs) predicted full-term children’s use of both path and manner information in their descriptions at 48 months. Lack of replication of these findings with outlier-removed analyses could only suggest a trend toward the differential contributions of sound symbolic input in different child populations and the importance of sentential cues in sound symbolic input in verb learning.

Factors associated with stunting status among under-5 years children in Bangladesh: Quantile regression modelling approach

ObjectivesChronic malnutrition has a detrimental impact on children’s health. Bangladesh has made considerable progress on children’s underweight and wasting health issues over the past two decades. However, the existing prevalence of stunting remains a significant concern for child health. This study investigates the extent of different determinants of stunting status among children under the age of 5 in Bangladesh by using the 2017–18 Bangladesh Demographic and Health Survey data. MethodsIn response to the violation of the parametric test assumptions, a non-parametric Kruskal-Wallis test has been carried out in bivariate analysis to test the equality of median stunting scores across different predictors. The robust quantile regression model is applied to examine the impact of various demographic, socio-cultural, and maternal health-related variables on children’s stunting status. ResultsAdministrative division, place of residence, household head, wealth status, media access, mothers age at recent birth, mother’s education, bank account, height, multiple children, body mass index, antenatal care, and place of delivery shows significant impact on children’s stunting status. Children from the Dhaka division, mothers with higher education, and urban areas exhibit significantly lower levels of stunting. The analysis reveals that mothers with higher body mass index, receiving antenatal care from medically trained providers, and delivered at health-facilitated places, significantly reduce the likelihood of stunting status of their child. ConclusionsEnhancing maternal status and prioritizing maternal well-being could play a crucial role in improving children’s nutritional outcomes. Policymakers may focus on the potential factors for designing effective strategies to reduce the existing stunting prevalence in Bangladesh.

Machine learning regression tools for erosion prediction of WC-10Co4Cr thermal spray coating

The prediction of erosion in WC-10Co4Cr thermal spray coating is predicted using regression machine learning technique. A pot tester helped to examine the erosion rate of WC-10Co4Cr thermal spray coatings. WC-10Co4Cr thermal spray powder was sprayed onto the SS316L steel. Different impingement conditions (30, 45, and 60°) were tested by using textures designed to simulate erosion. The collected data is used to construct a robust Gaussian Process Regression (GPR) model. The projected values are compared to the actual values obtained via experimentation. To further demonstrate the accuracy of the suggested model, the produced model is compared to various state-of-the-art machine learning methods. The GPR outperforms more commonplace methods of other regression techniques like decision trees, Ensemble boosted trees, and linear regression models. The erosion of coated and bare SS316L austenitic steel was effectively predicted using a GPR model.

ROBOUT: a conditional outlier detection methodology for high-dimensional data

This paper presents a methodology, called ROBOUT, to identify outliers conditional on a high-dimensional noisy information set. In particular, ROBOUT is able to identify observations with outlying conditional mean or variance when the dataset contains multivariate outliers in or besides the predictors, multi-collinearity, and a large variable dimension compared to the sample size. ROBOUT entails a pre-processing step, a preliminary robust imputation procedure that prevents anomalous instances from corrupting predictor recovery, a selection stage of the statistically relevant predictors (through cross-validated LASSO-penalized Huber loss regression), the estimation of a robust regression model based on the selected predictors (via MM regression), and a criterion to identify conditional outliers. We conduct a comprehensive simulation study in which the proposed algorithm is tested under a wide range of perturbation scenarios. The combination formed by LASSO-penalized Huber loss and MM regression turns out to be the best in terms of conditional outlier detection under the above described perturbed conditions, also compared to existing integrated methodologies like Sparse Least Trimmed Squares and Robust Least Angle Regression. Furthermore, the proposed methodology is applied to a granular supervisory banking dataset collected by the European Central Bank, in order to model the total assets of euro area banks.

Governance effectiveness and green bonds. An empirical evaluation

The study aims to assess the relationship between governance effectiveness, measured by the Worldwide Governance Indicators, and the use of green bonds worldwide. We apply panel data models with random effects and a robust linear regression model that allows us to identify the impact of the family of variables on green bonds. We found a statistically significant correlation between the quality of a government, measured as government effectiveness, and the value of green bond issuances. Thus, it is advised under New Public Governance to increase the effectiveness of their functioning, which may contribute to greater investor interest in environmental projects.

Pest risk information, agricultural outcomes and food security: evidence from Ghana

This article investigates the short-term effects of an information intervention that provided early warning pest alerts and integrated pest management (IPM)-based advice to smallholder farmers. Specifically, this study focuses on fall armyworm (Spodoptera frugiperda) of maize in Ghana. We particularly examine the relationships between access to pest risk information and a number of outcomes, ranging from farmer’s knowledge to household food security. This study is based on survey data collected between December 2021 and January 2022 from 888 farm households operating 1305 maize fields. Results from doubly robust and switching regression models indicated that exposure to the pest risk information campaign was significantly (ρ < 0.05) associated with increases in the likelihood of optimal timing of fall armyworm control action and the adoption of multiple IPM practices, but it had no significant effect on pesticide use. Households who received the pest risk information obtained an average of 4% or 54 kg/ha (ρ < 0.01) gain in maize yield and were about 38% less likely (ρ < 0.01) than their non-recipient counterparts to report experiencing hunger, as measured by the household hunger scale. However, the pest risk information campaign was not associated with greater household dietary diversity. Further results indicated that households where the pest risk information was received by women, alone or together with their spouses, were more likely (ρ < 0.05) to achieve positive outcomes than if the recipient of information were male member of households. Overall, our findings imply that the dissemination of early warning pest alerts in combination with actionable IPM information to smallholder farmers can contribute to the adoption of sustainable crop protection technologies, and ultimately improve the standard of living of farm households.

A Novel Support Vector Regression Algorithm for Processing Experimental Data with Perturbation

Processing experimental data with uncertainty is a huge challenge for robust regression modeling and high-accuracy data forecasting. The objective of the present study is the development of a robust support vector regression model for processing observed data of independent variables containing polyhedral perturbation and achievement of high forecasting precision. Firstly, the conception of the data collection of polyhedral perturbation is given and analyzed. Secondly, a novel robust support vector regression model is constructed by replacing the original independent variables in a linear support vector regression model with the independent variables containing polyhedral perturbation. Thirdly, the novel robust linear support vector regression method is also expanded to the non-linear regression model. Both the two models are validated by the linear and nonlinear numerical regression experiments. Comparison of the experimental results show that the proposed method provide more accurate predictions than the traditional regression method for processing data with polyhedral perturbation.

Systematic review evaluating the influence of the prosthetic material and prosthetic design on the clinical outcomes of implant-supported multi-unit fixed dental prosthesis in the posterior area.

The objectives of the study were to assess the survival, failure, and technical complication rates of implant-supported fixed dental prosthesis (iFDPs) with pontic or splinted crown (iSp C) designs in the posterior area and compare the influence of prosthetic materials and prosthetic design on the outcomes. Electronic and manual searches were performed to identify randomized-, prospective-, and retrospective clinical trials with follow-up time of ≥12 months, evaluating the clinical outcomes of posterior iFDPs with pontic or iSp Cs. Survival and complication rates were analyzed using robust Poisson's regression models. Thirty-two studies reporting on 42 study arms were included in the present systematic review. The meta-analysis of the included studies indicated estimated 3-year survival rates of 98.3% (95%CI: 95.6-99.3%) for porcelain-fused-to-metal (PFM) iFDPs, 97.5% (95%CI: 95.5-98.7%) for veneered zirconia (Zr) iFDPs with pontic, 98.9% (95%CI: 96.8-99.6%) for monolithic or micro-veneered zirconia iFDPs with pontic, and 97.0% (95%CI: 84.8-99.9%) for lithium disilicate iFDPs with pontics. The survival rates for different material combination showed no statistically significant differences. Veneered restorations, overall, showed significantly (p < .01) higher ceramic fracture and chipping rates compared with monolithic restorations. Furthermore, there was no significant difference in survival rates (98.3% [95%CI: 95.6-99.3%] vs. 99.1% [95%CI: 97.6-99.7%]) and overall complication rates between PFM iFDPs with pontic and PFM iSp Cs. Based on the data identified by this systematic review, PFM, veneered Zr, and monolithic Zr iFDPs with pontic and iSp Cs showed similarly high short-term survival rates in the posterior area. Veneered restorations exhibit ceramic chipping more often than monolithic restorations, with the highest fracture rate reported for veneered Zr iFDPs.

Temporal trends of stroke incidence over 14 years in Iran: Findings of a large-scale multi-centric hospital-based registry

Background: The burden of stroke is high worldwide, especially in low-middle income countries. We aim to explore the temporal trends of the incidence rate (IR) of stroke over 14 years in Iran’s central areas. Methods: Stroke registry as part of cardiovascular disease (CVD) registry in Isfahan that focused on hospitalized patients (≥15 years) with first or recurrent stroke from 2001 to 2015. Factors included date of symptoms, demographics, management, survival at 28 days, date of admission, history of stroke, and other CVD and clinical diagnosis according to Computer Tomography Scan. We calculated age-, sex, and place-of-residence-adjusted IR based on multiple reference populations. Data were analyzed by bootstrap robust zero-truncated negative binomial regression models using R Statistical Software. Results: From 19,174 registered patients with stroke assessed by ICD-10; 18,010 (93.93%) cases were identified based on WHO-MONICA. Approximately 51% of hospitalized stroke patients were women. The average annual increase in stroke incidence based on ICD-10 ranged from 1.56% (95% CI, 0.14, 2.97) to 2.67% (95% CI, 1.25, 4.09) for different reference populations. In addition, a similar trend was also observed for stroke IR based on WHO-MONICA during the study period for the whole reference population, with an average annual change of 2.5% (95% CI, 1.28, 3.72) to 3.64 % (95% CI, 2.47, 4.82). Conclusion: Given that temporal trends of stroke have increased in both sexes, especially in Iran’s urban areas, prevention programs are needed for public awareness and physician motivation in order to identify risk factors as well as primary and secondary prevention.

Survey on the influential demographic factors of Chinese undergraduate students’ critical thinking disposition: Evidence from plausible values

Critical thinking disposition (CTD), the facet of critical thinking, regarded as the basis to activate critical thinking skills, is the inclination to think critically. Previous studies on the factors influencing CTD in undergraduate students yielded inconsistent results, often examining these factors based on raw scores without considering plausible values (PVs) which can unbiasedly provide estimates that are closer to the truth. This study aims to explore the factors (e.g., gender, year of study, major, parents' educational level, family income, residence, and type of university) that potentially influence undergraduate students' CTD using PVs. This study involved 661 Chinese undergraduate students (female students represented 50.4%), utilizing the Employer–Employee–Supported Critical Thinking Disposition Inventory for data collection. After calculating PVs using item response theory, linear regression models through dummy variable regression on the PVs were conducted. The findings revealed that when the factors were examined individually, CTD may vary by type of university, year of study, parents’ educational level, and family income. However, when the factors were integrated into a comprehensive robust regression model, family income was identified as the unique factor influencing CTD, indicating that individuals from higher-income families exhibited higher CTD levels than students from lower-income families. Demographic factors accounted for 5%–10% of the variation. Future research should investigate additional factors that may substantially impact on college students’ CTD. It is crucial for educators to acknowledge the disparities in CTD prevalence based on family income and devise an effective way to promote CTD among individuals from low-income backgrounds.

Robust Regression Analysis of Full Overlapping Caffeine and Pyridoxine HCl UV-Vis Spectra in Pharmaceutical Tablet

The determination of caffeine and pyridoxine HCl in medicinal tablets has been successfully carried out. The mixture of caffeine and pyridoxine solution produces UV-Vis with full overlapping spectra. The full overlapping spectra can not be analyzed using conventional multicomponent analysis, as they do not have a distinct maximum wavelength. This research proposed a full overlapping spectra analysis using Robust regression. The regression models used in this research were based on Huber, RANSAC, and Theil-Sen Regression. Robust regression is a regression method that was not sensitive to the presence of outliers from the input or output data. Robust Regression models were trained using 25 standard solutions of caffeine and pyridoxine HCl at varied ratios. The models were validated using test solutions with known concentration ratios. The validated models were applied to determine the concentration of medicinal tablets. From this study, the recovery values of medicinal tablets obtained using Huber, RANSAC, and Theil-Sen Regression methods for caffeine were 96.94%, 97.19%, and 96.16% respectively, while the recoveries of pyridoxine HCl were 122.65%, 104.89%, and 107.48%.