Model Assessment Method Research Articles

Validating metabarcoding-based biodiversity assessments with multi-species occupancy models: A case study using coastal marine eDNA.

Environmental DNA (eDNA) metabarcoding is an increasingly popular method for rapid biodiversity assessment. As with any ecological survey, false negatives can arise during sampling and, if unaccounted for, lead to biased results and potentially misdiagnosed environmental assessments. We developed a multi-scale, multi-species occupancy model for the analysis of community biodiversity data resulting from eDNA metabarcoding; this model accounts for imperfect detection and additional sources of environmental and experimental variation. We present methods for model assessment and model comparison and demonstrate how these tools improve the inferential power of eDNA metabarcoding data using a case study in a coastal, marine environment. Using occupancy models to account for factors often overlooked in the analysis of eDNA metabarcoding data will dramatically improve ecological inference, sampling design, and methodologies, empowering practitioners with an approach to wield the high-resolution biodiversity data of next-generation sequencing platforms.

Modelling, Bayesian inference, and model assessment for nosocomial pathogens using whole-genome-sequence data.

Whole‐genome sequencing of pathogens in outbreaks of infectious disease provides the potential to reconstruct transmission pathways and enhance the information contained in conventional epidemiological data. In recent years, there have been numerous new methods and models developed to exploit such high‐resolution genetic data. However, corresponding methods for model assessment have been largely overlooked. In this article, we develop both new modelling methods and new model assessment methods, specifically by building on the work of Worby et al. Although the methods are generic in nature, we focus specifically on nosocomial pathogens and analyze a dataset collected during an outbreak of MRSA in a hospital setting.

Severity Grade Assessment Classifications for Both Insulin Resistance Syndrome and Status of Pancreatic Beta Cell Function in Clinical Practice Using Homeostasis Model Assessment Method Indices

Abstract This article aims to classify the severity grading assessments for both insulin resistance (IR) syndrome and status of pancreatic beta (β) islet cells’ function using the homeostasis model assessment method (that is; homeostasis model assessment-insulin resistance [HOMA-IR] and homeostasis model assessment-pancreatic beta (β) islet cells’ function [HOMA-B] indices) with the focus of disseminating this information rapidly for clinical use by physicians in their patients with dysfunctional regulation of glucose metabolism. It will also assist clinicians to prevent and screen for these individuals who are significantly at high risk for insulin resistance (IR) syndrome and impair pancreatic beta (β) islet cells’ function thereby alleviating the risk for associated comorbidities. Insulin resistance (IR) syndrome and pancreatic beta (β) islet cells’ dysfunction with accompanied insufficiency form two major important and crucial factors in the aetiology and pathogenesis of frank type 2 diabetes mellitus (type 2 DM). The pathophysiological process of insulin resistance (IR) syndrome can either be a compensatory or uncompesatory phase response phenomenon, depending on the extent of biochemical response and effect elicited by the pancreatic beta (β) islet cells to secrete insulin. The alteration mechanisms that underlie the pathophysiological processes and biochemical responses that occur during the onset or induction of peripheral IR can be divided into two phases, namely: Euglycaemic hyperinsulinemic phase (compensatory first phase), and Hyperglycaemic hypoinsulinemic phase (uncompensatory second phase). The euglycaemic hyperinsulinemic phase is characterized by relatively normal plasma glucose level with continuous elevated plasma or serum level of insulin release from an intact pancreatic beta (β) islet cell mass in order to compensate and prevent the occurrence of a sustained hyperglycaemic state. The euglycaemic hyperinsulinemic phase of peripheral IR syndrome is said to occur when the fasting plasma/serum insulin assay level is more than or equal to [≥] 25.00 mU/L with a relatively normal value for the fasting plasma glucose level that ranges from 3.60 mmol/L to 5.99 mmol/L. It can also be defined using the three-hour postprandial plasma/serum insulin assay level more than or equal to [≥] 25.00 mU/L with a relatively normal value for the two-hour postprandial plasma glucose level that is less than [

Increasing insulin resistance predicts adverse pregnancy outcomes in women with gestational diabetes mellitus.

This study aimed to investigate the association between maternal insulin resistance (IR) in the late second trimester and pregnancy outcomes, as well as to identify risk factors of IR among women with gestational diabetes mellitus (GDM). A retrospective study was conducted among 2647 women diagnosed with GDM. IR was evaluated using the homeostasis model assessment method for IR (HOMA-IR) in the late second trimester (between 24 and 28 weeks), and the lipid profiles were measured at the same time. Patients were divided into groups based on quartiles of HOMA-IR. The information on pregnancy outcomes and risk factors was extracted from the medical records of all participants and entered electronically. Logistic regression models were used to analyze the associations between HOMA-IR and pregnancy outcomes, as well as the associations between risk factors and HOMA-IR. Greater IR was associated with cesarean delivery, preterm delivery, macrosomia, and large for gestational age newborns, but only significantly associated with preterm delivery after adjustment for potential confounders (P < .001). Prepregnancy body mass index (BMI), weight gain before diagnosis of GDM, and triglycerides were significantly related with IR in the late second trimester (P < .001). Besides, the total area under the curve of the diagnostic 75-g oral glucose tolerance test and glycosylated hemoglobin A1c increased from the lowest to the highest HOMA-IR groups. Increasing IR in the late second trimester predicts adverse pregnancy outcomes especially for preterm delivery in women with GDM. Additionally, prepregnancy BMI and weight gain before diagnosis of GDM are independent risk factors for the development of IR.

Calculation method for the service life of Chinese historical reinforced concrete buildings

Almost all of the existed studies on the corrosion of rebars were based on round-section rebars. However, the square-section steel rebars were widely used in China from 1912 to 1949, and there was no specific calculation model or durability assessment method for this type of historical buildings. In this study, based on the original configuration design of this kind of structures, the experiments of the corrosion-induced cover cracking of a certain number of reinforced concrete members with square-section rebars were carried out with the electrochemical acceleration method. The average rust depths of the square-section rebars at the critical corrosion-induced cover cracking moment were obtained. Then, the calculation method of critical rust depth of steel rebars at the concrete cover cracking moment was presented with data fitting method. Finally, combining with predication of carbonization life of concrete, a calculation method of the service life for Chinese historical RC buildings using square-section rebars was proposed. The research results can provide the basis for the durability assessment and conservation for Chinese historical RC buildings.

P279 Subclinical left ventricular dysfunction in patients with insulin resistence and hypovitaminosis D

Abstract Introduction Patients with subclinical left ventricular diastolic and systolic dysfunction are at risc of future cardiac events. Insulin resistance (IR) has been reported to be a strong risk factor for cardiovascular disease (CVD). Hypovitaminosis D is associated with insulin resistance and beta cell dysfunction and vitamin D deficiency is also associated with increased risk of CVD, including hypertension, heart failure, and ischemic heart disease. Aim The aim has been to explore association of IR and vitamin D deficiency with subclinical left ventricular disfunction. Method The study consisted of 79 patients divided into two groups according IR, evaluated at baseline by the homeostasis model assessment method (HOMA-IR). v The HOMA1-IR index was calculated by the formula: HOMA1-IR = fasting plasma insulin (µU/ml) x fasting plasma glucose (mmol/L). The HOMA2-IR index was obtained by the program HOMA Calculator (free) download Windows version. The cut-off values for IR were: HOMA1-IR &amp;gt; 2.7 and HOMA2-IR &amp;gt; 1.8; group of 41 patients, and group od 38 patients without of IR. Parameters of left atrial and ventricular geometry were estimated by echocardiography. Tissue Doppler velocities were measured from medial and lateral annulus (e, a, s) including isovolumic contraction velocity (IVCv) and E/e Global longitudinal strain (GLS) was derived from two-dimensional speckle-tracking. Results In IR group level of 25-OH-D was deficient in 25 (61.2%), insufficient in 10 (25%) and sufficient in 6 (13.8%) patients and significantly lower compared to control group (46.8 ± 25.5 vs 61.5 ± 33.8, p &amp;lt; 0.001). Importantly, 25-OH-D was associated with global longitudinal strain (r= −0.21, &amp;lt;0.05). Values of GLS (-19.9 ± 2.8 vs -26.6 ± 2.9; p &amp;lt; 0.001) and IVCv (0.07 ± 0.02m/s vs 0.09 ± 0.03m/s; p &amp;lt; 0.05) were significantly lower and E/e (9.11 ± 2.24 vs 7.18 ± 1.65; p &amp;lt; 0.001) significantly higher in group of patients with IR. Conclusion The results showed that insulin resistence is asociated with subclinical LV diastolic and systolic dysfunction. Level of 25-OH-D was significantly lower in patients with insulin resistence suggests that vitamin D deficiency may have a certain contribution to the development of myocardial dysfunction in these patients. Fortunately insulin resistance and vitamin D deficiency are a modifiable risk factors; the reduction of insulin resistance and increase the level of 25-OH-D may reduce CV risk in this group of patients.

The relationship between vitamin D and insulin resistance before delivery in advanced maternal age

BackgroundWith the widely implementation of universal two-child policy, the number of pregnant women in advanced maternal age (AMA) will increase gradually. We aimed to assess the association of vitamin D levels and insulin resistance (IR) during the late pregnancy in AMA.MethodsA total of 80 pregnant women were consecutively enrolled in the cross-sectional study before delivery from the August 2016 to June 2017 at the department of gynecology and obstetrics in the hospital of ZhongDa, affiliated to Southeast University. At delivery, serum 25(OH) D and metabolism parameters including glucose and lipid levels were measured. IR was calculated by the method of homeostasis model assessment 2(HOMA2).ResultsPregnant women in AMA with vitamin D deficiency have higher fasting insulin (14.70(8.76–34.65) and 10.89(7.15–16.12), respectively, P = 0.031) and HOMA-IR indices (1.78(1.07–4.14) and 1.30(0.83–1.89), respectively, P = 0.024) than those with vitamin D non-deficiency. Serum 25(OH) D levels were inversely associated with HOMA-IR indices (r = − 0.25, P = 0.025). In multivariable analysis for adjusting confounder factors, vitamin D non-deficiency was also negatively correlated with HOMA-IR compared to vitamin D deficiency (β = − 1.289, P = 0.026).ConclusionsTaken together, our findings suggest that serum 25(OH) D levels were inversely associated with HOMA-IR in AMA. Furthermore, pregnant women in AMA with vitamin D deficiency might have higher HOMA-IR levels than those with vitamin D non-deficiency.Trial registrationChinese Clinical Trial Registry (No. ChiCTR-RRC-16008714). retrospectively registered.

Emergency measure of soft isolation controlling pollution diffusion response to sudden water pollution accidents.

The frequent occurrence of sudden water pollution accidents has become a major threat to water environment safety. Although most researches have focused on constructing a pollutant source identification model and risk assessment methods for dealing with sudden water pollution accidents, a real-time, effective emergency measure for controlling pollutant diffusion, isolating and removing the pollutant, aiming at sudden water pollution accidents, has not been emphasized. Therefore, in this paper, a novel emergency approach of soft isolation was investigated to control pollution diffusion and decrease damage as soon as the accident occurred. In stage 1, the feature of pollution diffusion regarding a sudden water accident was predicted through a water quality model using computational fluid dynamics (CFD). Then, a design scheme of soft isolation was constructed in stage 2 to isolate the polluted zone and attention was paid to optimizing the parameters of soft isolation. Ultimately, the mathematical model of complete purification was formulated in stage 3 to remove the pollution from the impacted zone. The results indicated that the emergency measure of soft isolation could have significant potential to control and isolate pollution occurring in a sudden water pollution accident in the future.

Early menarche is associated with insulin resistance in advanced maternal age before delivery

Purpose: With the wide implementation of the universal two-child policy in China, the number of pregnant women in advanced maternal age (AMA) will increase gradually. We aimed to assess the association between age at menarche (AAM) and insulin resistance (IR) before delivery in AMA. Methods: A total of 80 pregnant women in AMA were consecutively enrolled before delivery in Zhongda hospital. Pregnant women were stratified into early menarche group and late menarche group according to the age of regular menstruation (about 13 years). At delivery, serum glucose and lipid levels were measured. IR was calculated by the method of homeostasis model assessment 2(HOMA2). Results: The fasting blood insulin (17.68(9.72–36.71) and 10.35(7.76–15.10), respectively; p = .006) and HOMA-IR (2.08(1.18–4.37) and 1.24(0.89–1.78), respectively; p = .005) were higher in early menarche group than in late menarche group. AAM was inversely associated with HOMA-IR in AMA (r= −0.27, p = .014). In the multivariable analysis, AAM in late menarche group was negatively related to the level of HOMA-IR compared to those in early menarche group (β= −2.275, p≤.0001). Conclusions: Taken together, our findings suggest that AAM was inversely associated with HOMA-IR in AMA. Furthermore, pregnant women in AMA with early menarche might have higher HOMA-IR levels than those with late menarche. Clinical trial registration: Chinese Clinical Trial Registry (No. ChiCTR-RRC-16008714), retrospectively registered

Risk Models for Breast Cancer and Their Validation.

Strategies to prevent cancer and diagnose it early when it is most treatable are needed to reduce the public health burden from rising disease incidence. Risk assessment is playing an increasingly important role in targeting individuals in need of such interventions. For breast cancer many individual risk factors have been well understood for a long time, but the development of a fully comprehensive risk model has not been straightforward, in part because there have been limited data where joint effects of an extensive set of risk factors may be estimated with precision. In this article we first review the approach taken to develop the IBIS (Tyrer–Cuzick) model, and describe recent updates. We then review and develop methods to assess calibration of models such as this one, where the risk of disease allowing for competing mortality over a long follow-up time or lifetime is estimated. The breast cancer risk model model and calibration assessment methods are demonstrated using a cohort of 132,139 women attending mammography screening in the State of Washington, USA.

A model and data hybrid-driven short-term voltage stability real-time monitoring method

This paper proposes a model and data hybrid-driven short-term voltage stability assessment method. First, a double-generator-one-load (DGOL) simplified model for short-term voltage stability analysis is introduced, and the mechanism of the occurrence of short-term voltage instability is analysed based on a DGOL model. Then, a model and data hybrid-driven online application algorithm is proposed, which includes a pre-fault analysis module and a real-time monitoring module. At last, a two-dimensional index is proposed to evaluate the short-term voltage stability margin. Simulation work is first conducted based on the DGOL system to illustrate the advantage of the proposed simplified model, and on the EPRI 36-bus system to demonstrate the effectiveness of online application algorithm.

Model-Based Conditional Weighted Residuals Analysis for Structural Model Assessment

Nonlinear mixed effects models are widely used to describe longitudinal data to improve the efficiency of drug development process or increase the understanding of the studied disease. In such settings, the appropriateness of the modeling assumptions is critical in order to draw correct conclusions and must be carefully assessed for any substantial violations. Here, we propose a new method for structure model assessment, based on assessment of bias in conditional weighted residuals (CWRES). We illustrate this method by assessing prediction bias in two integrated models for glucose homeostasis, the integrated glucose-insulin (IGI) model, and the integrated minimal model (IMM). One dataset was simulated from each model then analyzed with the two models. CWRES outputted from each model fitting were modeled to capture systematic trends in CWRES as well as the magnitude of structural model misspecifications in terms of difference in objective function values (ΔOFVBias). The estimates of CWRES bias were used to calculate the corresponding bias in conditional predictions by the inversion of first-order conditional estimation method’s covariance equation. Time, glucose, and insulin concentration predictions were the investigated independent variables. The new method identified correctly the bias in glucose sub-model of the integrated minimal model (IMM), when this bias occurred, and calculated the absolute and proportional magnitude of the resulting bias. CWRES bias versus the independent variables agreed well with the true trends of misspecification. This method is fast easily automated diagnostic tool for model development/evaluation process, and it is already implemented as part of the Perl-speaks-NONMEM software.

A novel water quality mechanism modeling and eutrophication risk assessment method of lakes and reservoirs

Water quality mechanism modeling and eutrophication analysis are important technical means for water pollution prevention and control of lake and reservoirs. However, the existing classical water quality mechanism models usually contain unknown parameters with empirical values range, which brings difficulty of predicting water quality changes of specific lakes and reservoirs to meet the accuracy requirements. Furthermore, the most existing water quality prediction methods output single-valued predictions of water quality indicators. These prediction results possess contingencies and uncertainties. Eutrophication analysis based on these results will bring errors, even become completely wrong. Therefore, combining the evolution mechanism of water quality, this paper proposes a fruit fly optimization algorithm (FFOA)-based water quality mechanism modeling method and studies a eutrophication risk assessment method of lakes and reservoirs based on the mechanism model. First, combining observed water quality data, unknown parameters of a water quality mechanism model are estimated by using FFOA. Then, Monte Carlo simulation is employed to predict the evolution of water quality, and the probability distribution functions (PDFs) of water quality indicators at predicted time indexes are obtained to achieve water quality prediction. Finally, to quantitatively assess the eutrophication status, a comprehensive eutrophication status index (CESI) is constructed. The PDF of CESI and the probabilities of being in different eutrophication levels are calculated to achieve water eutrophication risk assessment. The simulation results show that the proposed method can effectively estimate the unknown parameters of the water quality mechanism model, predict water quality evolution and assess the eutrophication risk with better accuracy and rationality by comparing the existing methods.

Association of copeptin, a surrogate marker for arginine vasopressin secretion, with insulin resistance: Influence of adolescence and psychological stress

In middle-aged and elderly individuals, circulating copeptin concentrations, a surrogate marker for arginine vasopressin (AVP) secretion, associates with insulin resistance (IR). Whether this association is present in adolescents and young adults is unclear. Because psychological stress associates with higher circulating copeptin concentrations and IR, it has been speculated that increased AVP secretion could be a link between psychological stress and IR. We measured plasma copeptin concentrations in 351 14–16-year-old adolescents and 617 20–28-year-old young adults from the Danish site of the European Youth Heart Study, a population-based cardiovascular risk factor study in adolescents and young adults. IR was determined by the homeostatic model assessment method. Among the young adults, we used symptoms of depression, evaluated by means of the Major Depression Inventory (MDI) scale, as a measure of psychological stress. We applied linear regressions to examine associations, expressed as unstandardized regression coefficients (B) with 95% confidence intervals (CIs), between variables of interest, stratified by age group and adjusting for age, sex and Tanner stages. Copeptin and IR were log-transformed. Among the young adults, copeptin associated with IR (B (95%CI) = 0.19 (0.11 to 0.27), P < 0.001). This association was not found among the adolescents (B=-0.01 (-0.12 to 0.09), P = 0.78). MDI score associated with IR (B = 0.010 (0.004 to 0.016), P < 0.001) and copeptin (B=0.010 (0.004 to 0.015); P<0.002) in the young adults. Adjusted for copeptin, the strength of the association between MDI score and IR somewhat diminished (to B=0.008). In conclusion, adolescence and psychological stress appear to influence the association between copeptin and IR.

Inhalation cancer risk estimation of source-specific personal exposure for particulate matter-bound polycyclic aromatic hydrocarbons based on positive matrix factorization.

In previous studies, inhalation cancer risk was estimated using conventional risk assessment method, which was normally based on compound-specific analysis, and cannot provide substantial data for source-specific particulate matter concentrations and pollution control. In the present study, we applied an integrated risk analysis method, which was a synthetic combination of source apportionment receptor model and risk assessment method, to estimate cancer risks associated to individual PAHs coming from specific sources. Personal exposure particulate matter samples referring to an elderly panel were collected in a community of Tianjin, Northern China, in 2009, and 12 PAH compounds were measured using GC-MS. Positive matrix factorization (PMF) was used to extract the potential sources and quantify the source contributions to the PAH mixture. Then, the lung cancer risk of each modeled source was estimated by summing up the cancer risks of all measured PAH species according to the extracted source profile. The final results indicated that the overall cancer risk was 1.12 × 10-5, with the largest contribution from gasoline vehicle emission (44.1%). Unlike other risk estimation studies, this study was successful in combining risk analysis and source apportionment approaches, which allow estimating the potential risk of all source types and provided suitable information to select prior control strategies and mitigate the main air pollution sources that contributing to health risks.

Beta-cell function and insulin resistance among First-Degree relatives of persons with type 2 diabetes in a Northwestern Nigerian Population

Background and Aims: Pancreatic beta-cell deficit and insulin resistance (IR) form two major factors in the etiopathogenesis of type 2 diabetes. The aim of this study is to assess beta-cell function and IR among first-degree relatives (FDRs) of persons with type 2 diabetes in a Northwestern Nigerian population. Other objectives include assessing the relationships among HOMA-%B, HOMA-IR, plasma glucose levels, and some obesity indices and to determine whether beta cell function, IR, and some obesity indices are independent determinants of glucose intolerance in the studied population. Materials and Methods: A total of 200 individuals and 200 controls were recruited through cluster sampling from their respective communities after due consent. The relevant biodata was documented and appropriate examinations including anthropometric measurements were carried out. Oral glucose tolerance test was carried out and fasting plasma insulin levels were also measured. IR and beta-cell function were calculated using homeostasis model assessment (HOMA) method. Results: Mean HOMA-IR was higher while HOMA-% B lower among FDRs compared to controls. Significant independent determinants of glucose intolerance with odds ratio (OR) and confidence interval (CI) included age (OR = 1.9, CI 1.9–2.0, P = 0.002), body mass index (OR = 1.9, CI 1.8–2.0, P = 0.032), waist circumference (OR = 2.0, CI 1.9–2.0, P = 0.043), waist-to-hip ratio (OR = 1.1, CI 1.0–15.7, P = 0.022), HOMA-IR (OR = 3.0, CI 2.3–3.3, P

Model za evaluaciju sistema upravljanja komunalnim otpadom, primena LCA - deo II: Verifikacija modela

The aim of this study was to use the life cycle assessment (LCA) instrument to assess the different municipal solid waste (MSW) management scenarios for the South Bačka region. LCA has proven to be a very effective instrument for identifying strategies that minimize negative environmental impacts. A comparative analysis is very important for decision makers and planners in the waste sector. This paper presents the application of the LCA model described in the Part I of this study. This model combined life cycle inventory model (IWM2) and life cycle impact assessment method (Impact2002+) to compare and evaluate the municipal solid waste system with the purpose of identifying environmental benefits and disadvantages, as well as the economic cost of defined scenarios of waste management systems that could be implemented. The model was applied to a regional municipal waste management system in South Bačka (The Republic of Serbia). Four scenarios of waste management are defined. The scenarios include the combination of different treatments of waste (biological and thermal), and a sanitary landfill. The results show clear differences between the scenarios in the selected indicators and quantify the relative advantages and disadvantages of different waste management scenarios. The model is a useful tool to support decision-makers to choose the technology of solid municipal waste treatment. Also, the participants in the planning of solid waste management will enable a better understanding of the importance of LCA method. Finally, it will help the improvement of the strategic planning process in the field of environmental protection, without which it is impossible to achieve the concept of sustainable development in the AP Vojvodina.

Decipherment of potential zones for groundwater occurrence: a study in Khatra Block, Bankura District, West Bengal, using geospatial techniques

Groundwater is considered as one of the most valuable natural resources as it supports human civilization. Freshwater is considered as an important natural resource which occurs partially on the surface and dominantly beneath the surface. The resource is declining drastically owing to the rapid increase in population and its management in an improper way. The occurrence of groundwater in hard rock terrain still behaves as enigmatic. Various terrain parameters control the movement and storage of groundwater. Accordingly geoscientists are using various techniques to explore the potential zone amongst which multi-criteria evaluation (MCE) technique seems to be more precise. Application of remote sensing and geographic information system (GIS) has come out as very effective tools in deciphering groundwater potential zone by modeling terrain features specially in hard rock arid regions. The present study is aimed to find out groundwater potential zones in Khatra Block of Bankura District, West Bengal, India characterized by hard granitic terrain and semi-arid climatic condition. In the present study various thematic maps viz., geomorphology, geology, lineament density, drainage density and slope have been prepared. For these, IRS Resources at LISS-4 with 5.8 m spatial resolution digital data, CARTOSAT-1 digital elevation model, CartoDEM with 2.5 m spatial resolution, along with other data sets such as Survey of India toposheets (73J/13, 73I/16, 73I/12), GSI Map have been used. Digitized vector maps relating to chosen parameters, were converted to raster data using 30 m × 30 m grid cell size. Different theme weight and class rank have been assigned to these raster maps. Each theme weight has been multiplied by its respective class rank and all the raster thematic layers have been summed up in a linear combination equation in Arc GIS Raster Calculator module. Similarly, the weighted layers have been statistically modeled to get the areal extent of groundwater prospects. This integrated approach, helped in classifying the groundwater availability in the study area into five categories, viz. very good, good, moderate, poor and very poor. Finally, it can be stated that the modeling assessment method proposed in this study forms an effective tool for delineating groundwater potential zones for proper development and management of groundwater resources in hard rock terrains.

Bayesian Item Response Analysis of Method-of-Payment Habits in Banking Surveys

Customers have a wide variety of choices in selecting a method of payment in modern society due to advancements in technology. In this paper, we investigate the method of payment habits of banking customers using item response models. We consider three binary item response models used in the literature within the Bayesian framework. These models capture the heterogeneity and complexity of customer perception on methods of payment in different capacities, with different features. For this reason, model assessment methods need to be developed for better inferential purposes. We introduce an assessment criterion based on predictive simulations and illustrate the approach using graphical summary measures. The approach is further highlighted using survey data based on consumer payment choices that was conducted for the Federal Reserve Bank of Boston.

Chemmodlab: a cheminformatics modeling laboratory\xa0R package for fitting and assessing machine learning models

The goal of chemmodlab is to streamline the fitting and assessment pipeline for many machine learning models in R, making it easy for researchers to compare the utility of these models. While focused on implementing methods for model fitting and assessment that have been accepted by experts in the cheminformatics field, all of the methods in chemmodlab have broad utility for the machine learning community. chemmodlab contains several assessment utilities, including a plotting function that constructs accumulation curves and a function that computes many performance measures. The most novel feature of chemmodlab is the ease with which statistically significant performance differences for many machine learning models is presented by means of the multiple comparisons similarity plot. Differences are assessed using repeated k-fold cross validation, where blocking increases precision and multiplicity adjustments are applied. chemmodlab is freely available on CRAN at https://cran.r-project.org/web/packages/chemmodlab/index.html.