Search

In insurance, proposing an accurate premium that is adjusted to the insured risk profile allows companies to better manage their portfolios and to be more competitive. Machine learning methods have recently been adopted for various improvements in insurance ratemaking, especially in the automobile industry. These models are specifically used to mine potential data information and to build a predictive model for a variable of interest using explanatory variables. In this paper, we aim to provide a pricing method for ratemaking individual healthcare insurance contracts using machine learning algorithms that are applied to a Tunisian healthcare insurance portfolio. We start with a simple Classification and Regression Tree, and we work toward more advanced methods that are Random Forest, Extreme gradient boosting, Support Vector Regression, and Artificial Neural network regression model. The predictive performance of these non-parametric methods is compared with the standard generalized linear model. Our results showed the applicability of machine learning in the healthcare insurance market and that the XGBoost algorithm outperforms the predictive capacity of the classical generalized linear model. [ABSTRACT FROM AUTHOR]

Sample multiplexing enables pooled analysis during single-cell RNA sequencing workflows, thereby increasing throughput and reducing batch effects. A challenge for all multiplexing techniques is to link sample-specific barcodes with cell-specific barcodes, then demultiplex sample identity post-sequencing. However, existing demultiplexing tools fail under many real-world conditions where barcode cross-contamination is an issue. We therefore developed deMULTIplex2, an algorithm inspired by a mechanistic model of barcode cross-contamination. deMULTIplex2 employs generalized linear models and expectation-maximization to probabilistically determine the sample identity of each cell. Benchmarking reveals superior performance across various experimental conditions, particularly on large or noisy datasets with unbalanced sample compositions.

Long time series of vegetation monitoring can be carried out by remote sensing data, the level of urban greening is objectively described, and the spatial characteristics of plant pollen are indirectly understood. Pollen is the main allergen in patients with seasonal allergic rhinitis. Meteorological factors affect the release and diffusion of pollen. Therefore, studying of the complex relationship between meteorological factors and allergic rhinitis is essential for effective prevention and treatment of the disease. In this study, we leverage remote sensing data for a comprehensive decade-long analysis of urban greening in Tianjin, which exhibits an annual increase in vegetative cover of 0.51 per annum, focusing on its impact on allergic rhinitis through changes in pollen distribution. Utilizing high-resolution imagery, we quantify changes in urban Fractional Vegetation Coverage (FVC) and its correlation with pollen types and allergic rhinitis cases. Our analysis reveals a significant correlation between FVC trends and pollen concentrations, with a surprising value of 0.71, highlighting the influence of urban greenery on allergenic pollen levels. We establish a robust connection between the seasonal patterns of pollen outbreaks and allergic rhinitis consultations, with a noticeable increase in consultations during high pollen seasons. our findings indicate a higher allergenic potential of herbaceous compared to woody vegetation. This nuanced understanding underscores the importance of pollen sensitivity, alongside concentration, in driving allergic rhinitis incidents. Utilizing a Generalized Linear Model, significant features influencing the number of visits for allergic rhinitis (P < 0.05) were identified. Both GLM and LSTM models were employed to forecast the visitation volumes for rhinitis during the spring and summer-autumn of 2022. Upon validation, it was found that the R² values between the simulated and actual values for both GLM and LSTM models surpassed the 95% confidence threshold. Moreover, the R² values for the summer-autumn seasons (GLM: 0.56, LSTM: 0.72) were higher than those for spring (GLM: 0.22, LSTM: 0.47). Comparing the errors between the simulated and actual values of GLM and LSTM models, LSTM exhibited higher simulation precision in both spring and summer-autumn seasons, demonstrating superior simulation performance. Overall, our study pioneers the integration of remote sensing with meteorological and health data for allergic rhinitis forecasting. This integrative approach provides valuable insights for public health planning, particularly in urban settings, and lays the groundwork for advanced, location-specific allergenic pollen forecasting and mitigation strategies. Highlights: The incidence of allergic rhinitis is primarily determined by pollen allergenicity, followed by concentration. Utilizing high-resolution imagery, we quantify changes in urban Fractional Vegetation Coverage (FVC) and its correlation with pollen types and allergic rhinitis cases. Weaving together remote sensing, meteorological, and health data, we employed Generalized Linear Models and LSTM models to dissect the determinants of allergic rhinitis and to construct a daily predictive model for the incidence of allergic rhinitis consultations. [ABSTRACT FROM AUTHOR]

ABSTRACT Regression analyses based on transformations of cumulative incidence functions are often adopted when modeling and testing for treatment effects in clinical trial settings involving competing and semi‐competing risks. Common frameworks include the Fine–Gray model and models based on direct binomial regression. Using large sample theory we derive the limiting values of treatment effect estimators based on such models when the data are generated according to multiplicative intensity‐based models, and show that the estimand is sensitive to several process features. The rejection rates of hypothesis tests based on cumulative incidence function regression models are also examined for null hypotheses of different types, based on which a robustness property is established. In such settings supportive secondary analyses of treatment effects are essential to ensure a full understanding of the nature of treatment effects. An application to a palliative study of individuals with breast cancer metastatic to bone is provided for illustration. [ABSTRACT FROM AUTHOR]

In many studies of human diseases, multiple omics datasets are measured. Typically, these omics datasets are studied one by one with the disease, thus the relationship between omics is overlooked. Modeling the joint part of multiple omics and its association to the outcome disease will provide insights into the complex molecular base of the disease. Several dimension reduction methods which jointly model multiple omics and two-stage approaches that model the omics and outcome in separate steps are available. Holistic one-stage models for both omics and outcome are lacking. In this article, we propose a novel one-stage method that jointly models an outcome variable with omics. We establish the model identifiability and develop EM algorithms to obtain maximum likelihood estimators of the parameters for normally and Bernoulli distributed outcomes. Test statistics are proposed to infer the association between the outcome and omics, and their asymptotic distributions are derived. Extensive simulation studies are conducted to evaluate the proposed model. The method is illustrated by modeling Down syndrome as outcome and methylation and glycomics as omics datasets. Here we show that our model provides more insight by jointly considering methylation and glycomics. [ABSTRACT FROM AUTHOR]

BACKGROUND: Hispanics are the largest growing ethnic minority group in the U.S. Despite significant progress in providing norms for this population, updated normative data are essential. OBJECTIVE: To present the methodology for a study generating normative neuropsychological test data for Spanish-speaking adults living in the U.S. using Bayesian inference as a novel approach. METHODS: The sample consisted of 253 healthy adults from eight U.S. regions, with individuals originating from a diverse array of Latin American countries. To participate, individuals must have met the following criteria: were between 18 and 80 years of age, had lived in the U.S. for at least 1 year, self-identified Spanish as their dominant language, had at least one year of formal education, were able to read and write in Spanish at the time of evaluation, scored≥23 on the Mini-Mental State Examination, <10 on the Patient Health Questionnaire– 9, and <10 on the Generalized Anxiety Disorder scale. Participants completed 12 neuropsychological tests. Reliability statistics and norms were calculated for all tests. CONCLUSION: This is the first normative study for Spanish-speaking adults in the U.S. that uses Bayesian linear or generalized linear regression models for generating norms in neuropsychology, implementing sociocultural measures as possible covariates. [ABSTRACT FROM AUTHOR]

Spike-and-slab prior distributions are used to impose variable selection in Bayesian regression-style problems with many possible predictors. These priors are a mixture of two zero-centered distributions with differing variances, resulting in different shrinkage levels on parameter estimates based on whether they are relevant to the outcome. The spike-and-slab lasso assigns mixtures of double exponential distributions as priors for the parameters. This framework was initially developed for linear models, later developed for generalized linear models, and shown to perform well in scenarios requiring sparse solutions. Standard formulations of generalized linear models cannot immediately accommodate categorical outcomes with > 2 categories, i.e. multinomial outcomes, and require modifications to model specification and parameter estimation. Such modifications are relatively straightforward in a Classical setting but require additional theoretical and computational considerations in Bayesian settings, which can depend on the choice of prior distributions for the parameters of interest. While previous developments of the spike-and-slab lasso focused on continuous, count, and/or binary outcomes, we generalize the spike-and-slab lasso to accommodate multinomial outcomes, developing both the theoretical basis for the model and an expectation-maximization algorithm to fit the model. To our knowledge, this is the first generalization of the spike-and-slab lasso to allow for multinomial outcomes. [ABSTRACT FROM AUTHOR]

In this paper, our goal is to enhance the interpretability of Generalized Linear Models by identifying the most relevant interactions between categorical predictors. Searching for interaction effects can quickly become a highly combinatorial, and thus computationally costly, problem when we have many categorical predictors or even a few of them but with many categories. Moreover, the estimation of coefficients requires large training samples with enough observations for each interaction between categories. To address these bottlenecks, we propose to find a reduced representation for each categorical predictor as a binary predictor, where categories are clustered based on a dissimilarity. We provide a collection of binarized representations for each categorical predictor, where the dissimilarity takes into account information from the main effects and the interactions. The choice of the binarized predictors representing the categorical predictors is made with a novel heuristic procedure that is guided by the accuracy of the so-called binarized model. We test our methodology on both real-world and simulated data, illustrating that, without damaging the out-of-sample accuracy, our approach trains sparse models including only the most relevant interactions between categorical predictors. [ABSTRACT FROM AUTHOR]

The e-commerce sector is in a constant state of growth and evolution, particularly within its subdomain of online food delivery. As such, ensuring customer satisfaction is critical for companies working in this field. One way to achieve this is by providing an accurate delivery time estimation. While companies can track couriers via GPS, they often lack real-time data on traffic and road conditions, complicating delivery time predictions. To address this, a range of statistical and machine learning techniques are employed, including neural networks and specialized expert systems, with different degrees of success. One issue with neural networks and machine learning models is their heavy dependence on vast, high-quality data. To mitigate this issue, we propose two Bayesian generalized linear models to predict the time of delivery. Utilizing a linear combination of predictor variables, we generate a practical range of outputs with the Hamiltonian Monte Carlo sampling method. These models offer a balance of generality and adaptability, allowing for tuning with expert knowledge. They were compared with the PSIS-LOO criteria and WAIC. The results show that both models accurately estimated delivery times from the dataset while maintaining numerical stability. A model with more predictor variables proved to be more accurate. [ABSTRACT FROM AUTHOR]

Calibrating parametric fragility curves via empirical damage data is one of the standard approaches to derive seismic structural vulnerability models. Fragilities based on empirical data require the characterization of the ground motion (GM) intensity at the building sites in the area affected by the earthquake producing the observed damages. This is commonly conducted via ShakeMap, that is, a map of the expected values of a Gaussian random field (GRF) of the logarithms of a GM intensity measure conditional to magnitude, location, and possibly a set of recordings of the earthquake. Once that intensity and damage data at the same sites are available, the typical approach calibrates a two‐parameter fragility model. However, ShakeMap estimates are affected by uncertainty deriving from that of the GM model used to characterize it. Furthermore, such an uncertainty can be reduced by building damage data, which provide information on the shaking intensity at the sites where damage is observed. It is shown herein that if this uncertainty is not addressed, also considering the shaking information provided by damage, the estimates of the fragility parameters obtained using a median ShakeMap only can be biased, and a recommended maximum likelihood estimation procedure – which exploits the expectation maximization algorithm – is provided. These arguments are illustrated via an application considering damage data from the 2009 L'Aquila earthquake in central Italy. [ABSTRACT FROM AUTHOR]

Abstract Thermal spray coating is a critical process in many industries, involving the application of coatings to surfaces to enhance their functionality. This paper proposes a framework for modelling and predicting critical target variables in thermal spray coating processes, based on the application of statistical design of experiments (DoE) and the modelling of the data using generalized linear models (GLMs) with a particular emphasis on gamma regression. Experimental data obtained from thermal spray coating trials are used to validate the presented approach, demonstrating that it is able to accurately model and predict critical target variables. As such, the framework has significant potential for the optimization of thermal spray coating processes, and can contribute to the development of more efficient and effective coating technologies in various industries.

• Biodiversity gaps may be filled when richness or occurrence models are transferable. • Transferability of richness models was poor in the Waterberg savanna vegetation. • Plant growth form richness models could potentially display better transferability. Modelling measures of biodiversity for understudied taxa or regions is one method to address taxonomic and geographic biases in biodiversity data. However, modelling biodiversity metrics, such as species richness, to unsampled areas is only useful if predictions are reliable. As a result, testing the transferability of richness models is necessary for assessing the potential for models to predict to unsampled areas. Here we test the transferability of plant richness models between two reserves to examine if the richness-environment relationship from one reserve can accurately estimate richness patterns in the other reserve, using the vascular plant species richness of the Waterberg region (savanna biome; northern South Africa) as a model system. Six richness response variables (total species, grass species, herb species, woody species, genus, and family richness) and a set of 16 predictor variables were analysed with three modelling approaches and two statistical techniques to build: (1) models comprising all available predictor variables, (2) models using a subset of predictor variables chosen based on model performance, and (3) models using a subset of predictor variables that reduce the difference in the environmental conditions between the two reserves. The models' performance in the training area varied considerably, but soil variables were consistently the most important predictors of plant richness. However, the transferability of all the models was consistently poor across all modelling approaches and both techniques, possibly reflecting the degree to which each reserve contains novel environments absent from the other reserve (despite being separated by only c. 60 km and sharing vegetation types). Due to the poor performance of these richness models, they are currently not useful for predicting richness to other areas in the vicinity of the reserves or in the broader region. However, in areas, like the Waterberg region, that have high plant diversity and are poorly sampled, there may be value in continued development of richness models to address biodiversity gaps, thereby providing better data to inform conservation decisions. [ABSTRACT FROM AUTHOR]

In item response theory (IRT) modeling, the magnitude of the lower and upper asymptote parameters determines the degree to which the inflection point shifts above or below P = 0.50. The current study examines the one-parameter negative log-log model (NLLM), which is characterized by a downward shift in the inflection point, among other distinctive psychometric properties. After detailing the statistical foundations of the NLLM, we present a series of simulation studies to establish item and person parameter estimation accuracy and to demonstrate that this parsimonious model addresses the "slipping" effect (i.e., unexpectedly incorrect answers) via an inflection point < 0.50 rather than through computationally difficult estimation of the upper asymptote. We then provide further support for these simulation results through empirical data analysis. Finally, we discuss how the NLLM contributes to recent methodological literature on the utility of asymmetric IRT models. [ABSTRACT FROM AUTHOR]

Using data from 2000 through 2022, we analyze the predictive capability of the annual numbers of new home constructions and four available environmental, social, and governance (ESG) factors on the average annual price of homes sold in eight major U.S. cities. We contrast the predictive capability of a P-spline generalized additive model (GAM) against a strictly linear version of the commonly used generalized linear model (GLM). As the data for the annual price and predictor variables constitute non-stationary time series, we transform each time series appropriately to produce stationary series for use in the GAMs and GLMs in order to avoid spurious correlations in the analysis. While arithmetic returns or first differences are adequate transformations for the predictor variables, we utilize the series of innovations obtained from AR(q)-ARCH(1) fits for the average price response variable. Based on the GAM results, we find that the influence of ESG factors varies markedly by city and reflects geographic diversity. Notably, the presence of air conditioning emerges as a strong factor. Despite limitations on the length of available time series, this study represents a pivotal step toward integrating ESG considerations into predictive time series models for real estates. [ABSTRACT FROM AUTHOR]

Generalized fused Lasso (GFL) is a powerful method based on adjacent relationships or the network structure of data. It is used in a number of research areas, including clustering, discrete smoothing, and spatio-temporal analysis. When applying GFL, the specific optimization method used is an important issue. In generalized linear models, efficient algorithms based on the coordinate descent method have been developed for trend filtering under the binomial and Poisson distributions. However, to apply GFL to other distributions, such as the negative binomial distribution, which is used to deal with overdispersion in the Poisson distribution, or the gamma and inverse Gaussian distributions, which are used for positive continuous data, an algorithm for each individual distribution must be developed. To unify GFL for distributions in the exponential family, this paper proposes a coordinate descent algorithm for generalized linear models. To illustrate the method, a real data example of spatio-temporal analysis is provided. [ABSTRACT FROM AUTHOR]

Regression by composition is a new and flexible toolkit for building and understanding statistical models. Focusing here on regression models for a binary outcome conditional on a binary treatment and other covariates, we motivate the need for regression by composition. We do this first by exhibiting—using L'Abbé plots—the families of relationships between untreated and treated conditional outcome risks that emerge from generalized linear models for many different link functions. These are compared with the relationships (between untreated and treated risks) that arise from mechanistic sufficient component cause models, which are first principles causal models for binary outcomes. By considering mechanistic models that allow for non-monotone causal effects and by allowing sufficient causes to be associated, we expand upon similar discussions in the recent literature. We discuss conditions under which commonly used statistical models for binary data, such as logistic regression, arise from mechanistic models where the sufficient causes are associated in a particular way, as well as other situations in which the statistical models arising do not correspond to a generalized linear model but can be naturally expressed as a regression by composition model. [ABSTRACT FROM AUTHOR]

Generalized linear models (GLMs) are an integral tool in ecology. Like general linear models, GLMs assume linearity, which entails a linear relationship between independent and dependent variables. However, because this assumption acts on the link rather than the natural scale in GLMs, it is more easily overlooked. We reviewed recent ecological literature to quantify the use of linearity. We then used two case studies to confront the linearity assumption via two GLMs fit to empirical data. In the first case study we compared GLMs to generalized additive models (GAMs) fit to mammal relative abundance data. In the second case study we tested for linearity in occupancy models using passerine point‐count data. We reviewed 162 studies published in the last 5 years in five leading ecology journals and found less than 15% reported testing for linearity. These studies used transformations and GAMs more often than they reported a linearity test. In the first case study, GAMs strongly out‐performed GLMs as measured by AIC in modeling relative abundance, and GAMs helped uncover nonlinear responses of carnivore species to landscape development. In the second case study, 14% of species‐specific models failed a formal statistical test for linearity. We also found that differences between linear and nonlinear (i.e., those with a transformed independent variable) model predictions were similar for some species but not for others, with implications for inference and conservation decision‐making. Our review suggests that reporting tests for linearity are rare in recent studies employing GLMs. Our case studies show how formally comparing models that allow for nonlinear relationships between the dependent and independent variables has the potential to impact inference, generate new hypotheses, and alter conservation implications. We conclude by suggesting that ecological studies report tests for linearity and use formal methods to address linearity assumption violations in GLMs. [ABSTRACT FROM AUTHOR]

The assessment of regression models with discrete outcomes is challenging and has many fundamental issues. With discrete outcomes, standard regression model assessment tools such as Pearson and deviance residuals do not follow the conventional reference distribution (normal) under the true model, calling into question the legitimacy of model assessment based on these tools. To fill this gap, we construct a new type of residuals for regression models with general discrete outcomes, including ordinal and count outcomes. The proposed residuals are based on two layers of probability integral transformation. When at least one continuous covariate is available, the proposed residuals closely follow a uniform distribution (or a normal distribution after transformation) under the correctly specified model. One can construct visualizations such as QQ plots to check the overall fit of a model straightforwardly, and the shape of QQ plots can further help identify possible causes of misspecification such as overdispersion. We provide theoretical justification for the proposed residuals by establishing their asymptotic properties. Moreover, in order to assess the mean structure and identify potential covariates, we develop an ordered curve as a supplementary tool, which is based on the comparison between the partial sum of outcomes and of fitted means. Through simulation, we demonstrate empirically that the proposed tools outperform commonly used residuals for various model assessment tasks. We also illustrate the workflow of model assessment using the proposed tools in data analysis. for this article are available online. [ABSTRACT FROM AUTHOR]

Our study aims to address the methodological challenges frequently encountered in RNA-Seq data analysis within cancer studies. Specifically, it enhances the identification of key genes involved in axillary lymph node metastasis (ALNM) in breast cancer. We employ Generalized Linear Models with Quasi-Likelihood (GLMQLs) to manage the inherently discrete and overdispersed nature of RNA-Seq data, marking a significant improvement over conventional methods such as the t-test, which assumes a normal distribution and equal variances across samples. We utilize the Trimmed Mean of M-values (TMMs) method for normalization to address library-specific compositional differences effectively. Our study focuses on a distinct cohort of 104 untreated patients from the TCGA Breast Invasive Carcinoma (BRCA) dataset to maintain an untainted genetic profile, thereby providing more accurate insights into the genetic underpinnings of lymph node metastasis. This strategic selection paves the way for developing early intervention strategies and targeted therapies. Our analysis is exclusively dedicated to protein-coding genes, enriched by the Magnitude Altitude Scoring (MAS) system, which rigorously identifies key genes that could serve as predictors in developing an ALNM predictive model. Our novel approach has pinpointed several genes significantly linked to ALNM in breast cancer, offering vital insights into the molecular dynamics of cancer development and metastasis. These genes, including ERBB2, CCNA1, FOXC2, LEFTY2, VTN, ACKR3, and PTGS2, are involved in key processes like apoptosis, epithelial–mesenchymal transition, angiogenesis, response to hypoxia, and KRAS signaling pathways, which are crucial for tumor virulence and the spread of metastases. Moreover, the approach has also emphasized the importance of the small proline-rich protein family (SPRR), including SPRR2B, SPRR2E, and SPRR2D, recognized for their significant involvement in cancer-related pathways and their potential as therapeutic targets. Important transcripts such as H3C10, H1-2, PADI4, and others have been highlighted as critical in modulating the chromatin structure and gene expression, fundamental for the progression and spread of cancer. [ABSTRACT FROM AUTHOR]

We consider network autoregressive models for count data with a non‐random neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference for such models. We consider both cases of fixed and increasing network dimension and we show that quasi‐likelihood inference provides consistent and asymptotically normally distributed estimators. The article is complemented by simulation results and a data example. [ABSTRACT FROM AUTHOR]

In biomedical research, the simultaneous inference of multiple binary endpoints may be of interest. In such cases, an appropriate multiplicity adjustment is required that controls the family‐wise error rate, which represents the probability of making incorrect test decisions. In this paper, we investigate two approaches that perform single‐step p$p$‐value adjustments that also take into account the possible correlation between endpoints. A rather novel and flexible approach known as multiple marginal models is considered, which is based on stacking of the parameter estimates of the marginal models and deriving their joint asymptotic distribution. We also investigate a nonparametric vector‐based resampling approach, and we compare both approaches with the Bonferroni method by examining the family‐wise error rate and power for different parameter settings, including low proportions and small sample sizes. The results show that the resampling‐based approach consistently outperforms the other methods in terms of power, while still controlling the family‐wise error rate. The multiple marginal models approach, on the other hand, shows a more conservative behavior. However, it offers more versatility in application, allowing for more complex models or straightforward computation of simultaneous confidence intervals. The practical application of the methods is demonstrated using a toxicological dataset from the National Toxicology Program. [ABSTRACT FROM AUTHOR]

Thermal spray coating is a critical process in many industries, involving the application of coatings to surfaces to enhance their functionality. This paper proposes a framework for modelling and predicting critical target variables in thermal spray coating processes, based on the application of statistical design of experiments (DoE) and the modelling of the data using generalized linear models (GLMs) with a particular emphasis on gamma regression. Experimental data obtained from thermal spray coating trials are used to validate the presented approach, demonstrating that it is able to accurately model and predict critical target variables. As such, the framework has significant potential for the optimization of thermal spray coating processes, and can contribute to the development of more efficient and effective coating technologies in various industries. [ABSTRACT FROM AUTHOR]

The literature has witnessed an upsurge of interest in model selection in diverse fields and optimization applications. Despite the substantial progress, model selection remains a significant challenge when covariates are highly correlated, particularly within economic and financial datasets that exhibit cross‐sectional and serial dependency. In this paper, we introduce a novel methodology named factor augmented regularized model selection with weak factors (WeakFARM) for generalized linear models in the presence of correlated covariates with weak latent factor structure. By identifying weak latent factors and idiosyncratic components and employing them as predictors, WeakFARM converts the challenge from model selection with highly correlated covariates to that with weakly correlated ones. Furthermore, we develop a variable screening method based on the proposed WeakFARM method. Comprehensive theoretical guarantees including estimation consistency, model selection consistency and sure screening property are also provided. We demonstrate the effectiveness of our approach by extensive simulation studies and a real data application in economic forecasting. [ABSTRACT FROM AUTHOR]

In supervised learning, feature selection methods identify the most relevant predictors to include in a model. For linear models, the inclusion or exclusion of each variable may be represented as a vector of bits playing the role of the genetic material that defines the model. Genetic algorithms reproduce the strategies of natural selection on a population of models to identify the best. We derive the distribution of the importance scores for parallel genetic algorithms under the null hypothesis that none of the features has predictive power. They, hence, provide an objective threshold for feature selection that does not require the visual inspection of a bubble plot. We also introduce the eradication strategy, akin to forward stepwise selection, where the genes of useful variables are sequentially forced into the models. The method is illustrated on real data, and simulation studies are run to describe its performance. [ABSTRACT FROM AUTHOR]

The temporal trends in species' descriptions of new amphibian species in the period 1758–2017 were studied to understand whether the increase in the number of active taxonomists could have influenced the increase in the number of species discovered over the years, and whether there was any differential attention during the various periods towards especially one of three main orders of amphibians (Anura, Caudata or Gymnophiona). These aspects were studied using a suite of statistical methods. We highlighted that the temporal effect was not statistically homogeneous among the amphibian taxa, with a very strong effect of the years (1758–2017) on the species description numbers for only the order Anura. We also showed that there was a significant positive correlation between the number of active taxonomists (that increased remarkably in recent decades) and the yearly number of discovered amphibian species. Moreover, we showed that the rise of new descriptions by year was significantly quicker in the Neotropical region. In future years, it would be interesting to place the observed patterns within the specific history of the countries situated within the various biogeographic regions, including such aspects as the legacy of the 'colonial time', the post-colonization effect, the 'cold war', and the modern times. Further suggestions on possible research about correlation to biogeographic variables, type of rarity, threat category, and eco-behavioral traits of the species have been added. [ABSTRACT FROM AUTHOR]

Charcoal rot disease of soybean is a major threat to soybean harvests in the United States. This disease, caused by the fungal pathogen Macrophomina phaseolina (MP), cannot be economically treated in agronomic field conditions, and breeding of resistant cultivars has been largely unsuccessful due to multiple gene resistance. For difficult-to-treat phytopathogens, nascent research has emphasized the potential utility of endophyte modulation of disease symptoms. Most research into biocontrol of MP in soybeans has focused on in vitro or limited greenhouse/pot experiments, which may not emulate field conditions. Here, using a paired framework of diseased and asymptomatic soybeans exposed to MP in a production field setting, coupled with model-based community analyses, we identify several fungal endophytic taxa that apparently modulate disease pathogenicity. We use a multilevel analytical framework to provide evidence of taxa that respond to the disease state by querying plants across years and plant compartments. Additional work is needed to test the mechanisms by which these identified taxa may modulate MP, but this work provides the strongest evidence to date that endophytes may modulate charcoal rot disease levels in production field conditions. We posit that breeding for improved colonization of disease-modulating endophytes is a promising option to manage charcoal rot in soybean. [Figure: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

Abstract Background Epidemiological studies in refugee settings are often challenged by the denominator problem, i.e. lack of population at risk data. We develop an empirical approach to address this problem by assessing relationships between occupancy data in refugee centres, number of refugee patients in walk-in clinics, and diseases of the digestive system. Methods Individual-level patient data from a primary care surveillance system (PriCarenet) was matched with occupancy data retrieved from immigration authorities. The three relationships were analysed using regression models, considering age, sex, and type of centre. Then predictions for the respective data category not available in each of the relationships were made. Twenty-one German on-site health care facilities in state-level registration and reception centres participated in the study, covering the time period from November 2017 to July 2021. Results 445 observations (“centre-months”) for patient data from electronic health records (EHR, 230 mean walk-in clinics visiting refugee patients per month and centre; standard deviation sd: 202) of a total of 47.617 refugee patients were available, 215 for occupancy data (OCC, mean occupancy of 348 residents, sd: 287), 147 for both (matched), leaving 270 observations without occupancy (EHR-unmatched) and 40 without patient data (OCC-unmatched). The incidence of diseases of the digestive system, using patients as denominators in the different sub-data sets were 9.2% (sd: 5.9) in EHR, 8.8% (sd: 5.1) when matched, 9.6% (sd: 6.4) in EHR- and 12% (sd 2.9) in OCC-unmatched. Using the available or predicted occupancy as denominator yielded average incidence estimates (per centre and month) of 4.7% (sd: 3.2) in matched data, 4.8% (sd: 3.3) in EHR- and 7.4% (sd: 2.7) in OCC-unmatched. Conclusions By modelling the ratio between patient and occupancy numbers in refugee centres depending on sex and age, as well as on the total number of patients or occupancy, the denominator problem in health monitoring systems could be mitigated. The approach helped to estimate the missing component of the denominator, and to compare disease frequency across time and refugee centres more accurately using an empirically grounded prediction of disease frequency based on demographic and centre typology. This avoided over-estimation of disease frequency as opposed to the use of patients as denominators.

Innovation within a company, sector, or territorial context can arise from identifying specific problems or needs. Performance analysis provides valuable insights, potentially highlighting areas where innovation may be necessary. This paper outlines a methodology designed to identify latent innovation needs at regional, sectoral, and dimensional levels. This methodology is based on critical issues emerging from comparing economic, environmental, and social sustainability indicators of farms. An iterative approach is used for this purpose. Mixed matching algorithms are employed to form the comparison groups, while G-computation is used to calculate the differences. Logistic regression is adopted to calculate the propensity scores, and several generalized linear models are used to estimate the impact of regional localization. Hypothesis tests are then conducted to confirm the statistical significance of the impacts, from which criticality levels are derived. This methodology is applied to data collected by the Italian Farm Accountancy Data Network, which includes over 64,000 observations from two consecutive three-year periods (2016-2018 and 2019-2021). The results highlight the existence of widespread critical issues in Italian agriculture. These problems primarily concern the efficient use of water, whose costs, relative to revenue, exceed, on average, around 40 %, and greenhouse horticulture, which shows an increased criticality level in terms of sustainability of over 50 %. From a regional perspective, Puglia in Southern Italy exhibits the most evident critical issues, with an average criticality level of 30 % that has increased over time. The emerging criticalities are analyzed in relation to the interventions introduced by the 2023-2027 Common Agricultural Policy to verify their coherence and identify possible innovative actions that can be implemented.

Introduction: Our study undertakes a detailed exploration of gene expression dynamics within human lung organ tissue equivalents (OTEs) in response to Influenza A virus (IAV), Human metapneumovirus (MPV), and Parainfluenza virus type 3 (PIV3) infections. Through the analysis of RNA-Seq data from 19,671 genes, we aim to identify differentially expressed genes under various infection conditions, elucidating the complexities of virus-host interactions. Methods: We employ Generalized Linear Models (GLMs) with Quasi-Likelihood (QL) F-tests (GLMQL) and introduce the novel Magnitude-Altitude Score (MAS) and Relaxed Magnitude-Altitude Score (RMAS) algorithms to navigate the intricate landscape of RNA-Seq data. This approach facilitates the precise identification of potential biomarkers, highlighting the host's reliance on innate immune mechanisms. Our comprehensive methodological framework includes RNA extraction, library preparation, sequencing, and Gene Ontology (GO) enrichment analysis to interpret the biological significance of our findings. Results: The differential expression analysis unveils significant changes in gene expression triggered by IAV, MPV, and PIV3 infections. The MAS and RMAS algorithms enable focused identification of biomarkers, revealing a consistent activation of interferon-stimulated genes (e.g., IFIT1, IFIT2, IFIT3, OAS1) across all viruses. Our GO analysis provides deep insights into the host's defense mechanisms and viral strategies exploiting host cellular functions. Notably, changes in cellular structures, such as cilium assembly and mitochondrial ribosome assembly, indicate a strategic shift in cellular priorities. The precision of our methodology is validated by a 92% mean accuracy in classifying respiratory virus infections using multinomial logistic regression, demonstrating the superior efficacy of our approach over traditional methods. Discussion: This study highlights the intricate interplay between viral infections and host gene expression, underscoring the need for targeted therapeutic interventions. The stability and reliability of the MAS/RMAS ranking method, even under stringent statistical corrections, and the critical importance of adequate sample size for biomarker reliability are significant findings. Our comprehensive analysis not only advances our understanding of the host's response to viral infections but also sets a new benchmark for the identification of biomarkers, paving the way for the development of effective diagnostic and therapeutic strategies. [ABSTRACT FROM AUTHOR]

Background: Epidemiological studies in refugee settings are often challenged by the denominator problem, i.e. lack of population at risk data. We develop an empirical approach to address this problem by assessing relationships between occupancy data in refugee centres, number of refugee patients in walk-in clinics, and diseases of the digestive system. Methods: Individual-level patient data from a primary care surveillance system (PriCarenet) was matched with occupancy data retrieved from immigration authorities. The three relationships were analysed using regression models, considering age, sex, and type of centre. Then predictions for the respective data category not available in each of the relationships were made. Twenty-one German on-site health care facilities in state-level registration and reception centres participated in the study, covering the time period from November 2017 to July 2021. Results: 445 observations ("centre-months") for patient data from electronic health records (EHR, 230 mean walk-in clinics visiting refugee patients per month and centre; standard deviation sd: 202) of a total of 47.617 refugee patients were available, 215 for occupancy data (OCC, mean occupancy of 348 residents, sd: 287), 147 for both (matched), leaving 270 observations without occupancy (EHR-unmatched) and 40 without patient data (OCC-unmatched). The incidence of diseases of the digestive system, using patients as denominators in the different sub-data sets were 9.2% (sd: 5.9) in EHR, 8.8% (sd: 5.1) when matched, 9.6% (sd: 6.4) in EHR- and 12% (sd 2.9) in OCC-unmatched. Using the available or predicted occupancy as denominator yielded average incidence estimates (per centre and month) of 4.7% (sd: 3.2) in matched data, 4.8% (sd: 3.3) in EHR- and 7.4% (sd: 2.7) in OCC-unmatched. Conclusions: By modelling the ratio between patient and occupancy numbers in refugee centres depending on sex and age, as well as on the total number of patients or occupancy, the denominator problem in health monitoring systems could be mitigated. The approach helped to estimate the missing component of the denominator, and to compare disease frequency across time and refugee centres more accurately using an empirically grounded prediction of disease frequency based on demographic and centre typology. This avoided over-estimation of disease frequency as opposed to the use of patients as denominators. [ABSTRACT FROM AUTHOR]

Radiation therapy (RT) is a frontline approach to treating cancer. While the target of radiation dose delivery is the tumor, there is an inevitable spill of dose to nearby normal organs causing complications. This phenomenon is known as radiotherapy toxicity. To predict the outcome of the toxicity, statistical models can be built based on dosimetric variables received by the normal organ at risk (OAR), known as Normal Tissue Complication Probability (NTCP) models. To tackle the challenge of the high dimensionality of dosimetric variables and limited clinical sample sizes, statistical models with variable selection techniques are viable choices. However, existing variable selection techniques are data-driven and do not integrate medical domain knowledge into the model formulation. We propose a knowledge-constrained generalized linear model (KC-GLM). KC-GLM includes a new mathematical formulation to translate three pieces of domain knowledge into non-negativity, monotonicity, and adjacent similarity constraints on the model coefficients. We further propose an equivalent transformation of the KC-GLM formulation, which makes it possible to solve the model coefficients using existing optimization solvers. Furthermore, we compare KC-GLM and several well-known variable selection techniques via a simulation study and on two real datasets of prostate cancer and lung cancer, respectively. These experiments show that KC-GLM selects variables with better interpretability, avoids producing counter-intuitive and misleading results, and has better prediction accuracy. [ABSTRACT FROM AUTHOR]

Context. Analysis of data uncertainties in modeling and forecasting of actuarial processes is very important issue because it allows actuaries to efficiently construct mathematical models and minimize insurance risks considering different situations. Objective. The goal of the following research is to develop an approach that allows for predicting future insurance payments with prior minimization of possible statistical data uncertainty. Method. The proposed method allows for the implementation of algorithms for estimating the parameters of generalized linear models with the preliminary application to data of the optimal Kalman filter. The results demonstrated better forecast results and more adequate model structures. This approach was applied successfully to the simulation procedure of insurance data. For generating insurance dataset the next features of clients were used: age; sex; body mass index (applying normal distribution); number of children (between 0 and 5); smoker status; region (north, east, south, west, center); charges. For creating the last feature normal distribution with known variance and a logarithmic function, exponential distribution with the identity link function and Pareto distribution with a known scale parameter and a negative linear function were used. Results. The proposed approach was implemented in the form of information processing system for solving the problem of predicting insurance payments based on insurance data and with taking into account the noise of the data. Conclusions. The conducted experiments confirmed that the proposed approach allows for more adequate model constructing and accurate forecasting of insurance payments, which is important point in the analysis of actuarial risks. The prospects for further research may include the use of this approach proposed in other fields of insurance related to availability of actuarial risk. A specialized intellectual decision support system should be designed and implemented to solve the problem by using actual insurance data from real world in online mode as well as modern information technologies and intellectual data analysis. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a machine learning setting which allows multiple participants collaboratively to train a model under the orchestration of a server without disclosing their local data. Vertical federated learning (VFL) is a special structure in FL. It handles the situation where participants have the same ID space but different feature spaces. In order to guarantee the security and privacy of the local data of each participant, homomorphic encryption (HE) is often used to transmit intermediate parameters or data during the training process. In most VFL frameworks, a trusted third-party server is necessary because the plaintexts of the parameters need to be revealed for the computation. However, it is hard to find such a credible entity in the real world. Existing methods for solving this problem are either communication-intensive or unsuitable for multi-party scenarios. By combining secret sharing (SS) and HE, we propose a novel VFL framework without any trusted third parties called EFMVFL. It allows intermediate parameters to be transmitted among multiple parties without revealing the plaintexts. EFMVFL is applicable to generalized linear models (GLMs) and supports flexible expansion to multiple participants. Extensive experiments under Logistic Regression and Poisson Regression show that our framework is outstanding in communication (reduced by 3.2×– 6.8×) and efficiency (accelerated by 1.6×– 3.1×). [ABSTRACT FROM AUTHOR]

In an insurance context, Long-Term Care (LTC) products cover the risk of permanent loss of autonomy, which is defined by the impossibility or difficulty of performing alone all or part of the activities of daily living (ADL). From an actuarial point of view, knowledge of risk depends on knowledge of the underlying biometric laws, including the mortality of autonomous insureds and the mortality of disabled insureds. Due to the relatively short history of LTC products and the age limit imposed at underwriting, insurers lack information at advanced ages. This represents a challenge for actuaries, making it difficult to estimate those biometric laws. In this paper, we propose to complete the missing information at advanced ages on the mortality of autonomous and disabled insured populations using information on the global mortality of the portfolio. In fact, the three previous mortality laws are linked since the portfolio is composed only of autonomous and disabled policyholders. We model the two mortality laws (deaths in autonomy and deaths in LTC) in a Poisson Generalized Linear Model framework, additionally using the P-Splines smoothing method. A constraint is then included to link the mortality laws of the two groups and the global mortality of the portfolio. This new method allows for estimating and extrapolating both mortality laws simultaneously in a consistent manner. [ABSTRACT FROM AUTHOR]

To tackle massive data, subsampling is a practical approach to select the more informative data points. However, when responses are expensive to measure, developing efficient subsampling schemes is challenging, and an optimal sampling approach under measurement constraints was developed to meet this challenge. This method uses the inverses of optimal sampling probabilities to reweight the objective function, which assigns smaller weights to the more important data points. Thus, the estimation efficiency of the resulting estimator can be improved. In this paper, we propose an unweighted estimating procedure based on optimal subsamples to obtain a more efficient estimator. We obtain the unconditional asymptotic distribution of the estimator via martingale techniques without conditioning on the pilot estimate, which has been less investigated in the existing subsampling literature. Both asymptotic results and numerical results show that the unweighted estimator is more efficient in parameter estimation. [ABSTRACT FROM AUTHOR]

A simple and efficient adaptive Markov Chain Monte Carlo (MCMC) method, called the Metropolized Adaptive Subspace (MAdaSub) algorithm, is proposed for sampling from high-dimensional posterior model distributions in Bayesian variable selection. The MAdaSub algorithm is based on an independent Metropolis-Hastings sampler, where the individual proposal probabilities of the explanatory variables are updated after each iteration using a form of Bayesian adaptive learning, in a way that they finally converge to the respective covariates' posterior inclusion probabilities. We prove the ergodicity of the algorithm and present a parallel version of MAdaSub with an adaptation scheme for the proposal probabilities based on the combination of information from multiple chains. The effectiveness of the algorithm is demonstrated via various simulated and real data examples, including a high-dimensional problem with more than 20,000 covariates. [ABSTRACT FROM AUTHOR]

Abstract Generalized linear models (GLMs) are an integral tool in ecology. Like general linear models, GLMs assume linearity, which entails a linear relationship between independent and dependent variables. However, because this assumption acts on the link rather than the natural scale in GLMs, it is more easily overlooked. We reviewed recent ecological literature to quantify the use of linearity. We then used two case studies to confront the linearity assumption via two GLMs fit to empirical data. In the first case study we compared GLMs to generalized additive models (GAMs) fit to mammal relative abundance data. In the second case study we tested for linearity in occupancy models using passerine point‐count data. We reviewed 162 studies published in the last 5 years in five leading ecology journals and found less than 15% reported testing for linearity. These studies used transformations and GAMs more often than they reported a linearity test. In the first case study, GAMs strongly out‐performed GLMs as measured by AIC in modeling relative abundance, and GAMs helped uncover nonlinear responses of carnivore species to landscape development. In the second case study, 14% of species‐specific models failed a formal statistical test for linearity. We also found that differences between linear and nonlinear (i.e., those with a transformed independent variable) model predictions were similar for some species but not for others, with implications for inference and conservation decision‐making. Our review suggests that reporting tests for linearity are rare in recent studies employing GLMs. Our case studies show how formally comparing models that allow for nonlinear relationships between the dependent and independent variables has the potential to impact inference, generate new hypotheses, and alter conservation implications. We conclude by suggesting that ecological studies report tests for linearity and use formal methods to address linearity assumption violations in GLMs.

Abstract Sample multiplexing enables pooled analysis during single-cell RNA sequencing workflows, thereby increasing throughput and reducing batch effects. A challenge for all multiplexing techniques is to link sample-specific barcodes with cell-specific barcodes, then demultiplex sample identity post-sequencing. However, existing demultiplexing tools fail under many real-world conditions where barcode cross-contamination is an issue. We therefore developed deMULTIplex2, an algorithm inspired by a mechanistic model of barcode cross-contamination. deMULTIplex2 employs generalized linear models and expectation–maximization to probabilistically determine the sample identity of each cell. Benchmarking reveals superior performance across various experimental conditions, particularly on large or noisy datasets with unbalanced sample compositions.

The discrete Weibull model can be adapted to capture different levels of dispersion in the count data. This paper takes into account the direct relationship between explanatory variables and the median of discrete Weibull response variable. Additionally, it provides the Bayesian estimate of the discrete Weibull regression model using the random walk Metropolis algorithm. The prior distributions of the coefficient predictors were carried out based on the uniform non-informative, normal and Laplace distributions. The performance of the Bayes estimators was also compared with the maximum likelihood estimator in terms of the mean square error and the coverage probability through the Monte Carlo simulation study. Meanwhile, a real data set was analyzed to show how the proposed model and the methods work in practice.

Abstract Background The Maximum Likelihood Estimator (MLE) for parameters of the gamma distribution is commonly used to estimate models of right-skewed variables such as costs, hospital length of stay, and appointment wait times in Economics and Healthcare research. The common specification for this estimator assumes the variance is proportional to the square of the mean, which underlies estimation and specification tests. We present a specification in which the variance is directly proportional to the mean. Methods We used simulation experiments to investigate finite sample results, and we used United States Department of Veterans Affairs (VA) healthcare cost data as an empirical example comparing the fit and predictive ability of the models. Results Simulation showed the MLE based on a correctly specified alternative has less parameter bias, lower standard errors, and less skewness in distribution than a misspecified standard model. The application to VA healthcare cost data showed the alternative specification can have better R square, smaller root mean squared error, and smaller mean residuals within deciles of predicted values. Conclusions The alternative gamma specification can be a useful alternative to the standard specification for estimating models of right-skewed continuous variables.

Before visual information from the retina reaches primary visual cortex (V1), it is dynamically filtered by the lateral geniculate nucleus (LGN) of the thalamus, the first location within the visual hierarchy at which nonretinal structures can significantly influence visual processing. To explore the form and dynamics of geniculate filtering we used data from monosynpatically connected pairs of retinal ganglion cells (RGCs) and LGN relay cells in the cat that, under anesthetized conditions, were stimulated with binary white noise and/or drifting sine-wave gratings to train models of increasing complexity to predict which RGC spikes were relayed to cortex, what we call "relay status." In addition, we analyze and compare a smaller dataset recorded in the awake state to assess how anesthesia might influence our results. Consistent with previous work, we find that the preceding retinal interspike interval (ISI) is the primary determinate of relay status with only modest contributions from longer patterns of retinal spikes. Including the prior activity of the LGN cell further improved model predictions, primarily by indicating epochs of geniculate burst activity in recordings made under anesthesia, and by allowing the model to capture gain control-like behavior within the awake LGN. Using the same modeling framework, we further demonstrate that the form of geniculate filtering changes according to the level of activity within the early visual circuit under certain stimulus conditions. This finding suggests a candidate mechanism by which a stimulus specific form of gain control may operate within the LGN.

Various creative multi-response optimisation approaches have been developed in the literature. Most of these researches are based on the normality assumption of the response distribution. However, this assumption does not necessarily hold in some real cases, such as non-normal multiple responses. Also, the reproducibility of optimisation results does not hold in some practical applications due to the variability of predicted responses associated with model uncertainty. In this paper, a novel approach is proposed to address the issues for non-normal multi-response optimisation. The proposed method not only identifies significant effects for each response by incorporating factorial effect principles into the framework of the Bayesian generalised linear models (GLMs) but also takes into account the model uncertainty and the variability of predicted responses by using the Bayesian sampling technique and Pareto optimal strategy. Furthermore, the optimal parameter settings are found by using grey incidence analysis (GIA). Besides, two examples are used to illustrate the effectiveness of the proposed method. The results show that the proposed method not only effectively identify significant factors but also find more satisfactory parameter settings when the reliability and reproducibility of optimisation results are considered simultaneously. [ABSTRACT FROM AUTHOR]

There are now many options for doubly robust estimation; however, there is a concerning trend in the applied literature to believe that the combination of a propensity score and an adjusted outcome model automatically results in a doubly robust estimator and/or to misuse more complex established doubly robust estimators. A simple alternative, canonical link generalized linear models (GLM) fit via inverse probability of treatment (propensity score) weighted maximum likelihood estimation followed by standardization (the g$$ g $$‐formula) for the average causal effect, is a doubly robust estimation method. Our aim is for the reader not just to be able to use this method, which we refer to as IPTW GLM, for doubly robust estimation, but to fully understand why it has the doubly robust property. For this reason, we define clearly, and in multiple ways, all concepts needed to understand the method and why it is doubly robust. In addition, we want to make very clear that the mere combination of propensity score weighting and an adjusted outcome model does not generally result in a doubly robust estimator. Finally, we hope to dispel the misconception that one can adjust for residual confounding remaining after propensity score weighting by adjusting in the outcome model for what remains 'unbalanced' even when using doubly robust estimators. We provide R code for our simulations and real open‐source data examples that can be followed step‐by‐step to use and hopefully understand the IPTW GLM method. We also compare to a much better‐known but still simple doubly robust estimator. [ABSTRACT FROM AUTHOR]

The local linear approximation algorithm is an effective algorithm for computing a global solution of the folded concave penalization problem. However, the effectiveness of this method is highly dependent on a reasonably good initial estimator. It will lose efficacy when the correlation among predictors is high. In this paper, we propose a new local linear approximation ridge algorithm designed to deal with highly correlated predictors. The ridge estimator is chosen as an initial estimator, the local linear approximation ridge algorithm is stable and effective. Simulation studies and a real data analysis show that the proposed algorithm has better performance than the local linear approximation algorithm in the presence of highly correlated predictors. [ABSTRACT FROM AUTHOR]

A model-based biclustering method for multivariate discrete longitudinal data is proposed. We consider a finite mixture of generalized linear models to cluster units and, within each mixture component, we adopt a flexible and parsimonious parameterization of the component-specific canonical parameter to define subsets of variables (segments) sharing common dynamics over time. We develop an Expectation-Maximization-type algorithm for maximum likelihood estimation of model parameters. The performance of the proposed model is evaluated on a large scale simulation study, where we consider different choices for the sample the size, the number of measurement occasions, the number of components and segments. The proposal is applied to Italian crime data (font ISTAT) with the aim to detect areas sharing common longitudinal trajectories for specific subsets of crime types. The identification of such biclusters may potentially be helpful for policymakers to make decisions on safety. [ABSTRACT FROM AUTHOR]

One of the challenges in the healthcare sector is making accurate forecasts across insurance years for claims reserve. Healthcare claims present huge variability and heterogeneity influenced by random decisions of the courts and intrinsic characteristics of the damaged parties, which makes traditional methods for estimating reserves inadequate. We propose a new methodology to estimate claim reserves in the healthcare insurance system based on generalized linear models using the Overdispersed Poisson distribution function. In this context, we developed a method to estimate the parameters of the quasi-likelihood function using a Gauss–Newton algorithm optimized through a genetic algorithm. The genetic algorithm plays a crucial role in glimpsing the position of the global minimum to ensure a correct convergence of the Gauss–Newton method, where the choice of the initial guess is fundamental. This methodology is applied as a case study to the healthcare system of the Tuscany region. The results were validated by comparing them with state-of-the-art measurement of the confidence intervals of the Overdispersed Poisson distribution parameters with better outcomes. Hence, local healthcare authorities could use the proposed and improved methodology to allocate resources dedicated to healthcare and global management. [ABSTRACT FROM AUTHOR]

Difference-in-differences is undoubtedly one of the most widely used methods for evaluating the causal effect of an intervention in observational (i.e., nonrandomized) settings. The approach is typically used when pre- and postexposure outcome measurements are available, and one can reasonably assume that the association of the unobserved confounder with the outcome has the same absolute magnitude in the two exposure arms and is constant over time; a so-called parallel trends assumption. The parallel trends assumption may not be credible in many practical settings, for example, if the outcome is binary, a count, or polytomous, as well as when an uncontrolled confounder exhibits nonadditive effects on the distribution of the outcome, even if such effects are constant over time. We introduce an alternative approach that replaces the parallel trends assumption with an odds ratio equi-confounding assumption under which an association between treatment and the potential outcome under no treatment is identified with a well-specified generalized linear model relating the pre-exposure outcome and the exposure. Because the proposed method identifies any causal effect that is conceivably identified in the absence of confounding bias, including nonlinear effects such as quantile treatment effects, the approach is aptly called universal difference-in-differences. We describe and illustrate both fully parametric and more robust semiparametric universal difference-in-differences estimators in a real-world application concerning the causal effects of a Zika virus outbreak on birth rate in Brazil. A supplementary digital video is available at: http://links.lww.com/EDE/C90 [ABSTRACT FROM AUTHOR]

In the assessment of car insurance claims, the claim rate for car insurance presents a highly skewed probability distribution, which is typically modeled using Tweedie distribution. The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset, when the data is provided by multiple parties, training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge. To address this issue, this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos. The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data. After determining which entities are shared, the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters. The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model. Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data from both parties without exchanging data. The assessment results of the scheme approach those of the Tweedie regression model learned from centralized data, and outperform the Tweedie regression model learned independently by a single party. [ABSTRACT FROM AUTHOR]