Semiparametric Approach Research Articles

Semiparametric Model-Assisted Approach to Probabilistic Sampling of Finite Populations With High Right-Skew and Kurtosis

Semiparametric Model-Assisted Approach to Probabilistic Sampling of Finite Populations With High Right-Skew and Kurtosis

Bayesian Empirical Likelihood Regression for Semiparametric Estimation of Optimal Dynamic Treatment Regimes.

We propose a semiparametric approach to Bayesian modeling of dynamic treatment regimes that is built on a Bayesian likelihood-based regression estimation framework. Methods based on this framework exhibit a probabilistic coherence property that leads to accurate estimation of the optimal dynamic treatment regime. Unlike most Bayesian estimation methods, our proposed method avoids strong distributional assumptions for the intermediate and final outcomes by utilizing empirical likelihoods. Our proposed method allows for either linear, or more flexible forms of mean functions for the stagewise outcomes. A variational Bayes approximation is used for computation to avoid common pitfalls associated with Markov Chain Monte Carlo approaches coupled with empirical likelihood. Through simulations and analysis of the STAR*D sequential randomized trial data, our proposed method demonstrates superior accuracy over Q-learning and parametric Bayesian likelihood-based regression estimation, particularly when the parametric assumptions of regression error distributions may be potentially violated.

High-Dimensional Dynamic Panel with Correlated Random Effects: A Semiparametric Hierarchical Empirical Bayes Approach

High-Dimensional Dynamic Panel with Correlated Random Effects: A Semiparametric Hierarchical Empirical Bayes Approach

Semiparametric approaches for the inference of univariate and multivariate extremes

Semiparametric approaches for the inference of univariate and multivariate extremes

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.

The “effect modifier” of US interest rate in the economic policy uncertainties and economic conditions of fifty (50) US states: A semi-parametric smooth varying-coefficient approach

In this study, we investigate the relationship between economic policy uncertainty [EPU] and the economic conditions of the 50 US states, as well as the role of interest rates. We use a semi-parametric smooth varying coefficient model (SVCM) to examine how interest rate affects the nexus of EPU-economic conditions. Our findings suggest a negative relationship between EPU and economic conditions and that when the interest rate is around 3 %, the negative impact of EPU on economic conditions decreases in more than 60 % of US states. Furthermore, we find that the rate of change in the interest rate between 2 % and 3 % helps mitigate the negative effects of EPU and improves economic conditions in several states. Our results remain consistent across different interest rate periods, regardless of whether the uncertainty is of internal or external origin.

Physicians and the Production of Health: Returns to Health Care during the Mortality Transition

Abstract This paper investigates the returns to health care provision during the mortality transition. We construct a new panel data set covering German municipalities from 1928 to 1936. The endogeneity of health care supply is addressed by using the expulsion of Jewish physicians from statutory health insurance as exogenous variation in regional physician supply. Increases in the supply of physicians reduce infant mortality and mortality from common childhood diseases. Using a semiparametric control function approach, we find diminishing marginal returns to health care provision. The results are consistent with historical trends in infant mortality over the 20th century.

Exploring the spatial relationship between urban built environment and green travel: An improved semi-parametric GWR approach

Public transit and non-motorized travel offer numerous environmental, social and public health benefits. Existing literature focuses on the correlation between the built environment and green travel in metropolitan centers, with limited studies on suburban new towns, essential for comprehensive urban expansion and sustainable development. This paper examines the effect of the built environment on public transit and non-motorized travel by using point of interest data and household economic data from Jiading District, Shanghai. An innovative framework is introduced, based on the geographically weighted regression model, which captures spatial heterogeneity while balancing the inequality and directionality of different areas in the transportation network. The results demonstrate that the proposed improved semi-parametric geographically weighted regression outperforms the traditional geographically weighted regression model in evaluation capabilities. A distinct spatial heterogeneity in travel patterns is identified between central and peripheral areas. The densely populated central zones exhibit a preference for intra-district travel, often opting for non-motorized modes due to their convenience and health benefits while peripheral areas serve as crucial connectors, facilitating long-distance travel within the metropolitan area through public transit and multimodal transportation. Regional transportation infrastructure construction and socioeconomic factors also affect the choice of green travel. The findings could provide theoretical references and policy implications to the development of green transportation and urban sustainability.

Integrating external summary information in the presence of prior probability shift: an application to assessing essential hypertension.

Recent years have witnessed a rise in the popularity of information integration without sharing of raw data. By leveraging and incorporating summary information from external sources, internal studies can achieve enhanced estimation efficiency and prediction accuracy. However, a noteworthy challenge in utilizing summary-level information is accommodating the inherent heterogeneity across diverse data sources. In this study, we delve into the issue of prior probability shift between two cohorts, wherein the difference of two data distributions depends on the outcome. We introduce a novel semi-parametric constrained optimization-based approach to integrate information within this framework, which has not been extensively explored in existing literature. Our proposed method tackles the prior probability shift by introducing the outcome-dependent selection function and effectively addresses the estimation uncertainty associated with summary information from the external source. Our approach facilitates valid inference even in the absence of a known variance-covariance estimate from the external source. Through extensive simulation studies, we observe the superiority of our method over existing ones, showcasing minimal estimation bias and reduced variance for both binary and continuous outcomes. We further demonstrate the utility of our method through its application in investigating risk factors related to essential hypertension, where the reduced estimation variability is observed after integrating summary information from an external data.

Semi-parametric approach for modelling overdispersed count data with application to Industry 4.0

The paper deals with a test for the goodness-of-fit of a model for count data, in the framework of Generalized Linear Models. The motivating example concerns the study on the effectiveness of policy incentives for the adoption of 4.0 technologies by Small and Medium Enterprises. According to the literature, openness to Industry 4.0 should be measured in terms of the number of 4.0 technologies adopted, represented by a count variable. To investigate the effectiveness of public policy interventions to encourage the adoption of 4.0 technologies, we propose the application of a model for count data with a permutation ANOVA to test the goodness-of-fit and for the model selection. When the distribution of the response is neither Poisson nor Negative Binomial, and in the quite common situation in which the response variance is much greater than the mean, the classic Poisson regression and Negative Binomial regression are not valid. The proposed testing method is based on the combination of permutation tests on the significance of the regression coefficient estimates. The power behaviour of the proposed semi-parametric solution is investigated through a comparative Monte Carlo simulation study. The performance of such a method is compared to those of the two main parametric competitors. The application of the permutation test to an interesting case study is presented. The dataset is original, and related to a sample survey carried out in Italy, about the adoption of Industry 4.0 technologies by Italian enterprises.

A Semiparametric Bayesian Approach to Heterogeneous Spatial Autoregressive Models.

Many semiparametric spatial autoregressive (SSAR) models have been used to analyze spatial data in a variety of applications; however, it is a common phenomenon that heteroscedasticity often occurs in spatial data analysis. Therefore, when considering SSAR models in this paper, it is allowed that the variance parameters of the models can depend on the explanatory variable, and these are called heterogeneous semiparametric spatial autoregressive models. In order to estimate the model parameters, a Bayesian estimation method is proposed for heterogeneous SSAR models based on B-spline approximations of the nonparametric function. Then, we develop an efficient Markov chain Monte Carlo sampling algorithm on the basis of the Gibbs sampler and Metropolis-Hastings algorithm that can be used to generate posterior samples from posterior distributions and perform posterior inference. Finally, some simulation studies and real data analysis of Boston housing data have demonstrated the excellent performance of the proposed Bayesian method.

The impact of diversification on the profitability and risk of Chinese banks: evidence from a semiparametric approach

AbstractThis paper analyzes the effects of banking diversification and focus strategies on the profitability and risk of Chinese banks in the post-crisis years (2008–2019). For this purpose, semiparametric estimates are used. The main results indicate that Chinese banks do not gain much benefit in terms of profitability and risk from following income or asset diversification strategies, although the former are more beneficial than the latter. These results have important implications for the design of specific diversification strategies for different types of banks. Results suggest that state-owned banks could benefit from a greater degree of diversification to obtain more profits and simultaneously decrease their risk levels, while national shareholding commercial banks and city commercial banks should evaluate these strategies with more caution as the benefits from them are less obvious.

An examination of health care efficiency in Canada: a two-stage semi-parametric approach.

Using data envelopment analysis, we examine the efficiency of Canada's universal health care system by considering a set of labour (physicians) and capital (beds) inputs, which produce a level of care (measured in terms of health quality and quantity) in a given region. Data from 2013-2015 were collected from the Canadian Institute for Health Information regarding inputs and from the Canadian Community Health Survey and Statistics Canada regarding our output variables, health utility (quality) and life expectancy (quantity). We posit that variation in efficiency scores across Canada is the result of regional heterogeneity regarding socioeconomic and demographic disparities. Regressing efficiency scores on such covariates suggests that regional unemployment and an older population are quite impactful and associated with less efficient health care production. Moreover, regional variation indicates the Atlantic provinces (Newfoundland, Prince Edward Island, Nova Scotia, New Brunswick) are quite inefficient, have poorer economic prospects, and tend to have an older population than the rest of Canada. Oaxaca-Blinder decompositions suggest that the latter two factors explain about one-third of this efficiency gap. Based on our two-stage semi-parametric analysis, we recommend Canada adjust their transfer payments to reflect these disparities, thereby potentially reducing inequality in regional efficiency.

Analysing HCV incidence trends in people who inject drugs using serial behavioural and seroprevalence data: A modelling study

IntroductionThe introduction of new direct-acting antivirals for hepatitis C virus (HCV) infection, has enabled the formulation of a HCV elimination strategy led by the World Health Organisation (WHO). Guidelines for elimination of HCV target a reduction in incidence, but this is difficult to measure and needs estimating. MethodsSerial cross-sectional bio-behavioural sero-surveys provide information on an individual's infection status and duration of exposure and how these change over time. These data can be used to estimate the rate of first infection through appropriate statistical models. This study utilised updated HCV seroprevalence information from the Unlinked Anonymous Monitoring survey, an annual survey of England, Wales and Northern Ireland monitoring the prevalence of blood borne viruses in people who inject drugs. Flexible parametric and semiparametric approaches, including fractional polynomials and splines, for estimating incidence rates by exposure time and survey year were implemented and compared. ResultsIncidence rates were shown to peak in those recently initiating injecting drug use at approximately 0.20 infections per person-year followed by a rapid reduction in the subsequent few years of injecting to approximately 0.05 infections per person-year. There was evidence of a rise in incidence rates for recent initiates between 2011 and 2020 from 0.17 infections per person-year (95 % CI, 0.16–0.19) to 0.26 infections per person-year (0.23–0.30). In those injecting for longer durations, incidence rates were stable over time. ConclusionsFractional polynomials provided an adequate fit with relatively few parameters, but splines may be preferable to ensure flexibility, in particular, to detect short-term changes in the rate of first infection over time that may be a result of treatment effects. Although chronic HCV prevalence has declined with treatment scale up over 2016–2020, there is no evidence yet of a corresponding fall in the rate of first infection. Seroprevalence and risk behaviour data can be used to estimate and monitor HCV incidence, providing insight into progress towards WHO defined elimination of HCV.

Flat rent price prediction in Berlin with web scraping

Internet data pose a challenge to the traditional system of official statistics, which relies on more conventional sources such as surveys and registers, not readily adaptable to rapid changes. Expanding this system to include internet data is currently at an experimental stage, exploring these sources’ potentials and benefits. This paper describes a project conducted within the ESSnet Trusted Smart Statistics – Web Intelligence Network framework. It investigates the use of online apartment listings to analyze the rental market. We used web scraping to extract information from two online real estate portals for flats in the city of Berlin. Using this data, we developed a model to predict rental prices per square meter based on the accommodation’s features and location within the city. We detected offers which appear in both portals by means of statistical matching and removed duplicate offers. Missing values were treated by multiple imputation. The prediction model is a semi-parametric approach where the postal districts are used to describe the location effect. Comparisons with microcensus results and the local rent index reveal significant differences between the market of online flat offers and the stock of existing flat contracts. Interested readers will find the commented programming code in the internet supplement.

Advancing Solar Energetic Particle Event Prediction through Survival Analysis and Cloud Computing. I. Kaplan–Meier Estimation and Cox Proportional Hazards Modeling

Solar energetic particles (SEPs) pose significant challenges to technology, astronaut health, and space missions. This initial paper in our two-part series undertakes a comprehensive analysis of the time to detection for SEPs, applying advanced statistical techniques and cloud-computing resources to deepen our understanding of SEP event probabilities over time. We employ a range of models encompassing nonparametric, semiparametric, and parametric approaches, such as the Kaplan–Meier estimator and Cox Proportional Hazards models. These are complemented by various distribution models—including exponential, Weibull, lognormal, and log-logistic distributions—to effectively tackle the challenges associated with “censored data,” a common issue in survival analysis. Employing Amazon Web Services and Python’s “lifelines” and “scikit-survival” libraries, we efficiently preprocess and analyze large data sets. This methodical approach not only enhances our current analysis, but also sets a robust statistical foundation for the development of predictive models, which will be the focus of the subsequent paper. In identifying the key determinants that affect the timing of SEP detection, we establish the vital features that will inform the machine-learning (ML) techniques explored in the second paper. There, we will utilize advanced ML models—such as survival trees and random survival forests—to evolve SEP event prediction capabilities. This research is committed to advancing space weather, strengthening the safety of space-borne technology, and safeguarding astronaut health.

A nonparametric proportional risk model to assess a treatment effect in time-to-event data.

Time-to-event analysis often relies on prior parametric assumptions, or, if a semiparametric approach is chosen, Cox's model. This is inherently tied to the assumption of proportional hazards, with the analysis potentially invalidated if this assumption is not fulfilled. In addition, most interpretations focus on the hazard ratio, that is often misinterpreted as the relative risk (RR), the ratio of the cumulative distribution functions. In this paper, we introduce an alternative to current methodology for assessing a treatment effect in a two-group situation, not relying on the proportional hazards assumption but assuming proportional risks. Precisely, we propose a new nonparametric model to directly estimate the RR of two groups to experience an event under the assumption that the risk ratio is constant over time. In addition to this relative measure, our model allows for calculating the number needed to treat as an absolute measure, providing the possibility of an easy and holistic interpretation of the data. We demonstrate the validity of the approach by means of a simulation study and present an application to data from a large randomized controlled trial investigating the effect of dapagliflozin on all-causemortality.

Influence of long-term observed trends on the performance of seasonal hydroclimate forecasts

Skillful forecasts of hydroclimate variables are essential for operational water management, agricultural planning, and food supply. Several studies have attempted to improve the skill of raw forecasts either by post-processing or by incorporating sea surface conditions into raw forecasts. However, to the best of our knowledge, limited to no study has investigated temporal trend, which is present in observed records but is absent from retrospective forecasts (also known as, hindcasts). The current study understands that a temporal trend can be yielded in raw meteorological forecasts by i) updating surface boundary forcings and ii) applying statistical models for either post-processing meteorological forecasts or issuing streamflow forecasting using weather forecasts as predictors. To analytically derive the relationship between temporal trend and forecast performance, this study applies three statistical approaches for post-processing season-ahead hindcasts of the Indian monsoon obtained from three general circulation models (GCM). The findings show that raw hindcasts of the Indian monsoons typically ignore the temporal trend present in the observed records. Furthermore, analytical derivations confirm that the absence of a trend in GCM hindcasts significantly influences post-processing performance. Moreover, a semi-parametric approach could not overcome the limitations of a parametric linear model in yielding a temporal trend in the hindcasts. Potential reasons for the absence of a trend in the hindcast is also discussed.

Semiparametric evaluation of first‐passage distribution for step‐stress accelerated degradation tests

AbstractIn reliability engineering, different types of accelerated degradation tests have been used to obtain reliability information for evaluating highly reliable or expensive products. The step‐stress accelerated degradation test (SSADT) is one of the useful experimental schemes that can be used to save the resources of an experiment. Motivated by the SSADT data for operational amplifiers collected in Xi'an Microelectronic Technology Institute, in which the underlying degradation mechanism of the operational amplifiers is unknown, we propose a semiparametric approach for SSADT data analysis that does not require strict distributional assumptions. Specifically, the empirical saddlepoint approximation method is proposed to estimate the items' lifetime (first‐passage time) distribution at both stress levels included and not included in the SSADT experiment. Monte Carlo simulation studies are used to evaluate the performance and illustrate the advantages of the proposed approach. Finally, the proposed semiparametric approach is applied to analyze the motivating data set.

Modeling of the daily dynamics in bike rental system using weather and calendar conditions: A semi-parametric approach

This study proposes a more robust methodological approach to modeling the effect of weather and calendar variables on the number of bike rentals. We employ penalized splines quasi-Poisson regression (a semi-parametric model), which involves some form of regularization, like those used in lasso, ridge, and other types of parametric regularization models. We demonstrate that this modeling approach reveals hidden relationships that a pure parametric model fails to identify.The findings show that visibility, windspeed, season, working day, and year all significantly impact bike rentals. Increased rentals are associated with increased visibility and lower wind speed. Rentals are negatively affected by the spring and winter seasons, while working days and the year show positive trends except in a few cases. The analysis of rentals by registered and casual users reveals similar patterns, though the magnitudes of the effects differ. These findings highlight the importance of considering weather and calendar variables when managing and promoting bike-sharing services. The study has implications for bike-sharing system operators and policymakers, suggesting strategies such as improving visibility and wind protection, seasonally tailoring promotional campaigns, targeting non-working days for casual users, and adapting to changing user demands. The study adds to our understanding of the factors that influence bike rentals and provides suggestions for improving the utilization and accessibility of bike-sharing systems.