Semiparametric Modeling Approach Research Articles

Wildfire Loss Modeling: A Flexible Semiparametric Approach

Wildfires have emerged as one of the most devastating natural disasters worldwide, which, in addition to a loss of life, results in billions of dollars in annual losses. This study aims to identify factors that contribute to the frequency and severity of wildfire losses. We propose a semiparametric modeling approach to analyze wildfire property losses in the United States from 1995 to 2020. Our methodology incorporates flexible generalized additive models for location, scale, and shape (GAMLSS), which integrate climate, socioeconomic, and geographical variables into the modeling process. Through empirical analysis, we demonstrate the critical role of spatial effects in modeling wildfire-related property losses. Additionally, we identify key variables, including house index, state population, wildfire duration, and climate index, that significantly contribute to explaining the average property loss. These findings offer valuable insights for enhancing catastrophe risk management for insurance companies and government agencies. Furthermore, the proposed approach can be easily applied to diverse regions grappling with spatially varying catastrophe risks.

Flexible Bayesian semiparametric mixed-effects model for skewed longitudinal data

BackgroundIn clinical trials and epidemiological research, mixed-effects models are commonly used to examine population-level and subject-specific trajectories of biomarkers over time. Despite their increasing popularity and application, the specification of these models necessitates a great deal of care when analysing longitudinal data with non-linear patterns and asymmetry. Parametric (linear) mixed-effect models may not capture these complexities flexibly and adequately. Additionally, assuming a Gaussian distribution for random effects and/or model errors may be overly restrictive, as it lacks robustness against deviations from symmetry.MethodsThis paper presents a semiparametric mixed-effects model with flexible distributions for complex longitudinal data in the Bayesian paradigm. The non-linear time effect on the longitudinal response was modelled using a spline approach. The multivariate skew-t distribution, which is a more flexible distribution, is utilized to relax the normality assumptions associated with both random-effects and model errors.ResultsTo assess the effectiveness of the proposed methods in various model settings, simulation studies were conducted. We then applied these models on chronic kidney disease (CKD) data and assessed the relationship between covariates and estimated glomerular filtration rate (eGFR). First, we compared the proposed semiparametric partially linear mixed-effect (SPPLM) model with the fully parametric one (FPLM), and the results indicated that the SPPLM model outperformed the FPLM model. We then further compared four different SPPLM models, each assuming different distributions for the random effects and model errors. The model with a skew-t distribution exhibited a superior fit to the CKD data compared to the Gaussian model. The findings from the application revealed that hypertension, diabetes, and follow-up time had a substantial association with kidney function, specifically leading to a decrease in GFR estimates.ConclusionsThe application and simulation studies have demonstrated that our work has made a significant contribution towards a more robust and adaptable methodology for modeling intricate longitudinal data. We achieved this by proposing a semiparametric Bayesian modeling approach with a spline smoothing function and a skew-t distribution.

Multiresponse semiparametric regression model approach to standard growth charts design for assessing nutritional status of East Java toddlers

Multiresponse semiparametric regression model approach to standard growth charts design for assessing nutritional status of East Java toddlers

Generalised Additive Model Improves Estimates of Vibrio Species Abundance in Penaeus vannamei Boone, 1931 Biofloc Production System

Environmental factors influence the abundance of Vibrio species in shrimp culture systems. Prediction of the abundance of presumptive Vibrio species can help prevent the occurrence of bacterial diseases as this will provide insights about when and which environmental factors to manage. In this study, the parametric linear regression model (LRM) and negative binomial model (NBM), and semiparametric generalised additive model (GAM) were used to identify correlations and predict changes of Vibrio abundance with physicochemical and biological water parameters. Water parameters were recorded from three 300 m2 biofloc ponds stocked with Penaeus vannamei Boone, 1931, at 500 individuals.m-3 over four culture run periods. Each culture run lasted for 16 weeks. Imputed data were initially subjected to univariate analysis and Pearson’s correlation analysis. The abundance of presumptive Vibrio species was found to be highly correlated with alkalinity, pH, and phytoplankton density. GAM performed best among the three models based on Akaike’s information criterion (AIC), having the smallest value of 5,743.222 compared to 6,572.014 and 5,857.997 values for ordinary LRM and NBM, respectively. It also had the largest deviance explained statistic with 41.2 % of the deviance reduced by including the predictors compared with ordinary LRM and NBM with only 16.04 % and 14.5 % deviance reduced, respectively. GAM introduced flexibility that predicts the dependent variable better in terms of statistical significance than LRM and NBM. It is important to consider using a semiparametric modelling approach as a tool for aquaculture management.

A semiparametric mixture model approach for regression analysis of partly interval-censored data with a cured subgroup.

Failure time data with a cured subgroup are frequently confronted in various scientific fields and many methods have been proposed for their analysis under right or interval censoring. However, a cure model approach does not seem to exist in the analysis of partly interval-censored data, which consist of both exactly observed and interval-censored observations on the failure time of interest. In this article, we propose a two-component mixture cure model approach for analyzing such type of data. We employ a logistic model to describe the cured probability and a proportional hazards model to model the latent failure time distribution for uncured subjects. We consider maximum likelihood estimation and develop a new expectation-maximization algorithm for its implementation. The asymptotic properties of the resulting estimators are established and the finite sample performance of the proposed method is examined through simulation studies. An application to a set of real data on childhood mortality in Nigeria is provided.

A semiparametric modeling approach for analyzing clinical biomarkers restricted to limits of detection

Before biomarkers can be used in clinical trials or patients' management, the laboratory assays that measure their levels have to go through development and analytical validation. One of the most critical performance metrics for validation of any assay is related to the minimum amount of values that can be detected and any value below this limit is referred to as below the limit of detection (LOD). Most of the existing approaches that model such biomarkers, restricted by LOD, are parametric in nature. These parametric models, however, heavily depend on the distributional assumptions, and can result in loss of precision under the model or the distributional misspecifications. Using an example from a prostate cancer clinical trial, we show how a critical relationship between serum androgen biomarker and a prognostic factor of overall survival is completely missed by the widely used parametric Tobit model. Motivated by this example, we implement a semiparametric approach, through a pseudo-value technique, that effectively captures the important relationship between the LOD restricted serum androgen and the prognostic factor. Our simulations show that the pseudo-value based semiparametric model outperforms a commonly used parametric model for modeling below LOD biomarkers by having lower mean square errors of estimation.

Maternal depression trajectories from 3 months to 11 years postpartum and offspring body composition in early adolescence.

To investigate the effect of maternal depressive symptom trajectories, from 3 months to 11 years postpartum, on the offspring's body composition at 11 years of age. Data from the Pelotas 2004 Birth Cohort, from the perinatal interview and from the 3-, 12-, 24- and 48-month and 6- and 11-year follow-ups. Community-based sample from the city of Pelotas, located in southern Brazil with approximately 350 000 inhabitants. The maternal depression symptom trajectories were identified through a semi-parametric group-based modelling approach, using the Edinburgh Postnatal Depression Scale (EPDS), with data from 3 months to 11 years postpartum. A total of 3467 (81·9 % of the total cohort). Five trajectory groups of EPDS scores were identified ('Low', 'Moderate low', 'Increasing', 'Decreasing' and 'Chronic high'). A total of 170 women (4·9 %) from the sample belonged to the 'Chronic high' group, having scored ≥13 EPDS points at every follow-up. Mean BMI in the 'Low' trajectory group was 0·77 (z-score 1·4), compared with 0·56 (z-score 1·4) in the 'Chronic high' group. Children from mothers in the 'Chronic high' group had lower fat mass (FM) (-1·34 ± 0·64 kg), FM% (-2·02 ± 0·85 percentage points) and FM index (-0·57 ± 0·27 kg/m2), compared with children from mothers in the 'Low' trajectory group. Adjusted analyses showed that sustained or transitory maternal depressive symptoms during childhood had no effect on the offspring's body composition indices at 11 years of age. Children raised by chronically depressed mothers have body composition indices at 11 years of age that are similar to those of children whose mothers have never been depressed.

A SEMIPARAMETRIC MODELING APPROACH USING BAYESIAN ADDITIVE REGRESSION TREES WITH AN APPLICATION TO EVALUATE HETEROGENEOUS TREATMENT EFFECTS.

Bayesian Additive Regression Trees (BART) is a flexible machine learning algorithm capable of capturing nonlinearities between an outcome and covariates and interactions among covariates. We extend BART to a semiparametric regression framework in which the conditional expectation of an outcome is a function of treatment, its effect modifiers, and confounders. The confounders are allowed to have unspecified functional form, while treatment and effect modifiers that are directly related to the research question are given a linear form. The result is a Bayesian semiparametric linear regression model where the posterior distribution of the parameters of the linear part can be interpreted as in parametric Bayesian regression. This is useful in situations where a subset of the variables are of substantive interest and the others are nuisance variables that we would like to control for. An example of this occurs in causal modeling with the structural mean model (SMM). Under certain causal assumptions, our method can be used as a Bayesian SMM. Our methods are demonstrated with simulation studies and an application to dataset involving adults with HIV/Hepatitis C coinfection who newly initiate antiretroviral therapy. The methods are available in an R package called semibart.

Bayesian Semiparametric Double Autoregressive Modeling

This paper proposes a Bayesian semiparametric modeling approach for the return distribution in double autoregressive models. Monte Carlo investigation of finite sample properties and an empirical application are presented. The results indicate that the semiparametric model developed in this paper is valuable and competitive.

Gender inequality in literacy status and its effects on households economic well-being in Burkina Faso: a semi-parametric bivariate sample selection modelling approach

This paper models the gender inequality in literacy status, and its effects on economic well-being in Burkina Faso, using data from the 2014 survey on household living conditions and a semi-parametric bivariate sample selection modelling approach. This approach compared to the classic Heckman two-step estimation procedure is methodologically innovative because it deals simultaneously with non-random sample selection using conventional systems of two equations, non-linear covariates' effects using spline approach, and the non-normal bivariate distribution using copula functions. The results show that although the observed gender inequality in literacy status does not translate into inequality in non-food wellness, it does however for food-wellness as females-headed households have 38.9% less per-capita food consumption spending than their males' counterparts. Combining both food and non-food consumption spending, total economic well-being also seems to exhibit significant gender inequality as female headed households now have relatively 26.7% less combined per-capita consumption spending.

Gender inequality in literacy status and its effects on households economic well-being in Burkina Faso: a semi-parametric bivariate sample selection modelling approach

Gender inequality in literacy status and its effects on households economic well-being in Burkina Faso: a semi-parametric bivariate sample selection modelling approach

Developmental trajectories of adaptive behavior in autism spectrum disorder: a high‐risk sibling cohort

Children with autism spectrum disorder (ASD) often experience impairments in adaptive behavior. Developmental trajectories of adaptive behavior in ASD were examined in children from high-risk (siblings of children diagnosed with ASD, n=403) and low-risk (no family history of ASD, n=163) families. Children were assessed prospectively at 12, 18, 24, and 36months of age using the Vineland Adaptive Behavior Scales and underwent a blind independent diagnostic assessment for ASD at 36months of age. The semi-parametric group-based modeling approach using standard scores on the Adaptive Behavior Composite revealed three distinct developmental trajectories: (a) Group 1 (21.2% of sample) showed average performance at 12months and a declining trajectory; (b) Group 2 (52.8% of the sample) showed average performance at 12months with a slightly declining trajectory; and (c) Group 3 (26.0% of the sample) showed a higher level of adaptive behavior at 12months and a stable trajectory. The Mullen Scales of Early Learning Early Learning Composite and the Autism Observation Scale for Infants total score at 6 and 12months predicted trajectory membership. The results emphasize heterogeneous development associated with ASD and the need for interventions tailored to individual presentations.

The Impact of Missing Risk Factor Data on Semiparametric Group-Based Trajectory Models

To investigate how missing data (Missing Completely at Random [MCAR] vs. Missing Not at Random [MNAR]) on risk factors can impact trajectory solutions (i.e., latent class probabilities) and coefficient estimates capturing the relationship between covariates and trajectory group solutions using a semiparametric group-based trajectory modeling (GBTM) approach. To address this issue, we conducted a systematic investigation using Monte Carlo simulation. Data were generated from a population with known growth parameters and risk factors. Observations for risk factors were then systematically deleted in a way that reflects key missing data assumptions (MCAR and MNAR). Models were then estimated to test the sensitivity of the estimates to each missing data scenario. Two key findings emerged: (1) trajectory solutions were largely unaffected by missing data on risk factors; and, (2) there was some degree of bias in estimating relationships between risk factors and trajectory group membership when data were missing on those risk factors. GBTM may be useful for testing etiological explanations of long-term patterns of offending. Missing data on risk factors poses a threat to this approach, however.

The Causes and Courses of Nonviolent and Violent Delinquency among South Korean Adolescents

ABSTRACTThis study combines and compares data from the Korean Youth Panel Survey and the Korean Children and Youth Panel Survey to examine the effects parenting, peers, school, social structure, and personality exert on nonviolent and violent delinquency among 5,462 male and 5,103 female adolescents in South Korea. Overall, parental effects were found to be more important than peer effects, but their influence diminishes relative to that of peer effects with age. The semiparametric group-based modeling approach identifies distinct groups of stable nondelinquents, stable moderates, moderate escalators, de-escalators, and desistors (but not chronic offenders). Lastly, this study does not provide support for a public discourse that infers juvenile delinquency has increased in frequency and severity.

A semiparametric model for wearable sensor-based physical activity monitoring data with informative device wear.

Wearable sensors provide an exceptional opportunity in collecting real-time behavioral data in free living conditions. However, wearable sensor data from observational studies often suffer from information bias, since participants' willingness to wear the monitoring devices may be associated with the underlying behavior of interest. The aim of this study was to introduce a semiparametric statistical approach for modeling wearable sensor-based physical activity monitoring data with informative device wear. Our simulation study indicated that estimates from the generalized estimating equations showed ignorable bias when device wear patterns were independent of the participants physical activity process, but incrementally more biased when the patterns of device non-wear times were increasingly associated with the physical activity process. The estimates from the proposed semiparametric modeling approach were unbiased both when the device wear patterns were (i) independent or (ii) dependent to the underlying physical activity process. We demonstrate an application of this method using data from the 2003-2004 National Health and Nutrition Examination Survey ($N=4518$), to examine gender differences in physical activity measured using accelerometers. The semiparametric model can be implemented using our R package acc, free software developed for reading, processing, simulating, visualizing, and analyzing accelerometer data, publicly available at the Comprehensive R Archive Network.

Mining Massive Amounts of Genomic Data: A Semiparametric Topic Modeling Approach

ABSTRACTCharacterizing the functional relevance of transcription factors (TFs) in different biological contexts is pivotal in systems biology. Given the massive amount of genomic data, computational identification of TFs is emerging as a useful approach to bridge functional genomics with disease risk loci. In this article, we use large-scale gene expression and chromatin immunoprecipitation (ChIP) data corpuses to conduct high-throughput TF-biological context association analysis. This work makes two contributions: (i) From a methodological perspective, we propose a unified topic modeling framework for exploring and analyzing large and complex genomic datasets. Under this framework, we develop new statistical optimization algorithms and semiparametric theoretical analysis, which are also applicable to a variety of large-scale data analyses. (ii) From an experimental perspective, our method generates an informative list of tumor-related TFs and their possible effected tumor types. Our data-driven analysis of 38 TFs in 68 tumor biological contexts identifies functional signatures of epigenetic regulators, such as SUZ12 and SET-DB1, and nuclear receptors, in many tumor types. In particular, the TF signature of SUZ12 is present in a broad range of tumor types, many of which have not been reported before. In summary, our work established a robust method to identify the association between TFs and biological contexts. Given the limited amount of genome-wide binding profiles of TFs and the massive number of expression profiles, our work provides a useful tool to deconvolute the gene regulatory network for tumors and other biological contexts. Supplementary materials for this article are available online.

Educational Attainment, and the Joint Outcomes of Employment and Consumption in Burkina Faso: A Semi-Parametric Bivariate Modeling Approach

With UN member states formally adopting the Education 2030 Agenda through the Incheon Declaration, comes the need to evaluate the effect of education on the joint outcomes of employment and consumption for each member state, so as to get a clear picture of its value as an effective policy leverage for sustainable development in the country. To this end, this paper looks at the effects of educational attainment on the two key aspects of consumer behavior (labor force participation, and consumption spending) in Burkina Faso, using a Semi-parametric Bivariate modeling approach, and data from the National Survey on Household Living Conditions. The results show that not only is the semi-parametric modeling approach methodologically innovative because it deals with the simultaneity of labor force participation and consumption spending using conventional systems of two equations, with non-linear covariates' effects using spline approach, and non-normal bivariate distribution using copula functions; it also performs better than the classic Heckman two-step estimator based on the AIC and BIC criterion. Most importantly, it is found that a typical head of household's education level plays a positive and significant role in his/her likely participation in the labor market, and also Simultaneously contributes to higher household's per-capita food consumption and non-food consumption spending in burkina faso. Moreover, the positive and significant correlation coefficients between labor force participation and consumption spending on food and non-food items, suggest that the assumption of joint occurrence of the two processes is important. This assumption leads to a more accurate account of the effects of education and that of the other covariates in the system. Overall, the results do support the importance of education as an effective policy leverage for fighting against food insecurity and poverty in burkina faso, although care must be taken to reduce the disparities between rural and urban areas.

Gender Inequality in Literacy Status, and its Effects on Households Economic Well-Being in Burkina Faso: A Semiparametric Bi-Variate Sample Selection Modeling Approach

This paper models the gender inequality in literacy status, and its effects on households economic well-being in Burkina Faso using A semi-parametric bi-variate sample selection modeling approach. This approach compared to the classic Heckman two-step estimator is methodologically innovative because it deals simultaneously with non-random sample selection using conventional systems of two equations, non-linear covariates' effects using spline approach, and the non-normal bivariate distribution using copula functions. Using data from the National Survey on Households Living Conditions in Burkina Faso, the graphical results by the Lorenz curves combined with the numerical Atkinson and Gini coefficients suggest that inequality in overall per-capita consumption spending (Economic well-being) among households headed by literates is higher than that of their illiterate counterparts for 2009 and 2014. However, independently of the head of household's literacy status, the level of inequality in total economic well-being decreased from 2009 to 2014. The analysis of poverty by literacy status using the poverty indices of Watts, Sen, Foster (alpha=1) suggests that poverty among households headed by literates is lower than that of their illiterates counterparts for both years. Without distinction of literacy status however, overall poverty decreased nationally between 2009 and 2014. The semi-parametric bivariate results do support the existence of gender inequality in literacy status, with women heads of households having relatively less chances of having a literate status than their men counterparts. The results also show that although this gender inequality in literacy status does not translate into inequalities in non-food wellness, it does however for food-wellness with female headed households having 38.9% less per-capita food consumption spending than their men counterparts. Combining both food and non-food consumption spending, total economic well-being seems to also exhibit gender inequality as female headed households now have relatively 26.7% less combined per-capita consumption spending.

Joint partially linear model for longitudinal data with informative drop-outs.

In biomedical research, a steep rise or decline in longitudinal biomarkers may indicate latent disease progression, which may subsequently cause patients to drop out of the study. Ignoring the informative drop-out can cause bias in estimation of the longitudinal model. In such cases, a full parametric specification may be insufficient to capture the complicated pattern of the longitudinal biomarkers. For these types of longitudinal data with the issue of informative drop-outs, we develop a joint partially linear model, with an aim to find the trajectory of the longitudinal biomarker. Specifically, an arbitrary function of time along with linear fixed and random covariate effects is proposed in the model for the biomarker, while a flexible semiparametric transformation model is used to describe the drop-out mechanism. Advantages of this semiparametric joint modeling approach are the following: 1) it provides an easier interpretation, compared to standard nonparametric regression models, and 2) it is a natural way to control for common (observable and unobservable) prognostic factors that may affect both the longitudinal trajectory and the drop-out process. We describe a sieve maximum likelihood estimation procedure using the EM algorithm, where the Akaike information criterion (AIC) and Bayesian information criterion (BIC) are considered to select the number of knots. We show that the proposed estimators achieve desirable asymptotic properties through empirical process theory. The proposed methods are evaluated by simulation studies and applied to prostate cancer data.

Semiparametric modeling: Correcting low-dimensional model error in parametric models

In this paper, a semiparametric modeling approach is introduced as a paradigm for addressing model error arising from unresolved physical phenomena. Our approach compensates for model error by learning an auxiliary dynamical model for the unknown parameters. Practically, the proposed approach consists of the following steps. Given a physics-based model and a noisy data set of historical observations, a Bayesian filtering algorithm is used to extract a time-series of the parameter values. Subsequently, the diffusion forecast algorithm is applied to the retrieved time-series in order to construct the auxiliary model for the time evolving parameters. The semiparametric forecasting algorithm consists of integrating the existing physics-based model with an ensemble of parameters sampled from the probability density function of the diffusion forecast. To specify initial conditions for the diffusion forecast, a Bayesian semiparametric filtering method that extends the Kalman-based filtering framework is introduced. In difficult test examples, which introduce chaotically and stochastically evolving hidden parameters into the Lorenz-96 model, we show that our approach can effectively compensate for model error, with forecasting skill comparable to that of the perfect model.