Comparison of Bayesian quantile and frequency-oriented regressions in studying the trend of discharge changes in several hydrometric stations of Gorganroud basin in Iran.

Climate change causes fluctuations in temperature and precipitation. As a result, it affects the discharge of rivers, the most important consequence of which is the tendency toward extreme events such as torrential rains and widespread droughts. River discharge is one of the most important climatic and hydrological parameters. Investigating the changes in this parameter is one of the main prerequisites in the management and proper use of water resources and rivers. Most trend detection studies are based on analyzing changes in the mean or middle of the data. They do not provide information on how changes occur in different data ranges. Therefore, to investigate parameter changes in a different range of the data series, various regression models were proposed. Frequentist quantile regression and Bayesian quantile regression models were used to estimate their trend and trend slope in different quantiles of discharge in different seasons of the year for Arazkouseh, Tamar, and Galikesh stations of Gorganroud basin in northern Iran with the statistical period of 1346–1396 (1966–2016). The results show that in most seasons of the year, high discharge rates for all 3 stations have decreased with a steep slope, and only in summer, Tamar and Galikesh stations have had an increasing trend, but low discharge rates have not changed significantly. Spatially, the discharge values at Arazkouseh station have a decreasing trend with a higher slope rate, and in terms of time, the most decreasing trend has been in spring. Comparing the models also shows that the Bayesian quantile regression model provides more accurate and reliable results than the frequency-oriented quantile regression model. In general, quantile regression models are useful for predicting and estimating extreme high and low discharge changes for better management to reduce flood and drought damage.

Modeling Length of Hospital Stay for Patients With COVID-19 in West Sumatra Using Quantile Regression Approach

This study aims to construct the model for the length of hospital stay for patients with COVID-19 using quantile regression and Bayesian quantile approaches. The quantile regression models the relationship at any point of the conditional distribution of the dependent variable on several independent variables. The Bayesian quantile regression combines the concept of quantile analysis into the Bayesian approach. In the Bayesian approach, the Asymmetric Laplace Distribution (ALD) distribution is used to form the likelihood function as the basis for formulating the posterior distribution. All 688 patients with COVID-19 treated in M. Djamil Hospital and Universitas Andalas Hospital in Padang City between March-July 2020 were used in this study. This study found that the Bayesian quantile regression method results in a smaller 95% confidence interval and higher value than the quantile regression method. It is concluded that the Bayesian quantile regression method tends to yield a better model than the quantile method. Based on the Bayesian quantile regression method, it investigates that the length of hospital stay for patients with COVID-19 in West Sumatra is significantly influenced by Age, Diagnoses status, and Discharge status.

Effects of faith-based attributes on hotel prices: the case of halal services

Purpose For more than 40 years, researchers have examined an exhaustive set of attributes as price determinants in tourism and hospitality. In extending this rich research stream, this study aims to propose and empirically assess a new set of hotel attributes, namely, faith-based attributes that allow tourists to continue following the activities and rituals guided by their religions while on vacation. Design/methodology/approach Using the Bayesian quantile regression for the first time in the field of hotel pricing, the hedonic pricing models examine both internal and external faith-based attributes, namely, halal services, which cater to the needs of Muslim tourists, in a sample of 805 hotels across the top three non-Muslim country destinations (Singapore, Thailand and Japan). Findings By exploring the effects of faith-based (halal) attributes available in hotels located in the biggest cities of the above-mentioned destinations, this study provides evidence for the significant role of faith-based (halal) attributes in determining hospitality prices. Practical implications This study’s findings offer a resource for several implications for tourism and hospitality scholars, practitioners and policymakers, especially within the field of Muslim/halal tourism, to develop action plans and strategies. Originality/value This study is the first to introduce a novel set of faith-based hospitality attributes and empirically assess their impact on hospitality price formation. Additionally, it contributes to the hedonic pricing method by being the first to use the Bayesian quantile regression.

Gestational Exposure to Toxicants and Autistic Behaviors using Bayesian Quantile Regression

Autism Spectrum Disorder, which is characterized by impaired social communication and stereotypic behaviors, affects 1-2% of children. While prenatal exposure to toxicants has been associated with autistic behaviors, most studies have focused on shifts in mean behavior scores. We used Bayesian quantile regression to assess the associations between log2-transformed toxicant concentrations and autistic behaviors across the distribution of behaviors. We used data from the Maternal-Infant Research on Environmental Chemicals study, a pan-Canadian cohort (2008-2011). We measured metal, pesticide, polychlorinated biphenyl, phthalate, bisphenol-A, and triclosan concentrations in blood or urine samples collected during the first trimester of pregnancy. Autistic behaviors were assessed in 478 3-4-year-old children using the Social Responsiveness Scale (SRS), where higher scores denote more autistic-like behaviors. Lead, cadmium, and most phthalate metabolites were associated with mild increases in SRS scores at the 90th percentile of the SRS distribution. Manganese and some pesticides were associated with mild decreases in SRS scores at the 90th percentile of the SRS distribution. We identified several monotonic trends where associations increased in magnitude from the bottom to the top of the SRS distribution. These results suggest that Quantile regression can reveal nuanced relationships and should thus be more widely used by epidemiologists.

Anomaly Detection in Health Insurance Claims Using Bayesian Quantile Regression

Research has shown that current health expenditure in most countries, especially in sub-Saharan Africa, is inadequate and unsustainable. Yet, fraud, abuse, and waste in health insurance claims by service providers and subscribers threaten the delivery of quality healthcare. It is therefore imperative to analyze health insurance claim data to identify potentially suspicious claims. Typically, anomaly detection can be posited as a classification problem that requires the use of statistical methods such as mixture models and machine learning approaches to classify data points as either normal or anomalous. Additionally, health insurance claim data are mostly associated with problems of sparsity, heteroscedasticity, multicollinearity, and the presence of missing values. The analyses of such data are best addressed by adopting more robust statistical techniques. In this paper, we utilized the Bayesian quantile regression model to establish the relations between claim outcome of interest and subject-level features and further classify claims as either normal or anomalous. An estimated model component is assumed to inherently capture the behaviors of the response variable. A Bayesian mixture model, assuming a normal mixture of two components, is used to label claims as either normal or anomalous. The model was applied to health insurance data captured on 115 people suffering from various cardiovascular diseases across different states in the USA. Results show that 25 out of 115 claims (21.7%) were potentially suspicious. The overall accuracy of the fitted model was assessed to be 92%. Through the methodological approach and empirical application, we demonstrated that the Bayesian quantile regression is a viable model for anomaly detection.