This study presents a novel statistical and computational approach using nonparametric regression, which capitalizes on correlation structure to deal with the high-dimensional data often found in pharmacogenomics, for instance, in Crohn’s inflammatory bowel disease. The empirical correlation between the test statistics, investigated via simulation, can be used as an estimate of noise. The theoretical distribution of −log₁₀(p-value) is used to support the estimation of that optimal bandwidth for the model, which adequately controls type I error rates while maintaining reasonable power. Two proposed approaches, involving normal and Laplace-LD kernels, were evaluated by conducting a case-control study using real data from a genome-wide association study on Crohn’s disease. The study successfully identified single nucleotide polymorphisms on the NOD2 gene associated with the disease. The proposed method reduces the computational burden by approximately 33% with reasonable power, allowing for a more efficient and accurate analysis of genetic variants influencing drug responses. The study contributes to the advancement of statistical methodology for analyzing complex genetic data and is of practical advantage for the development of personalized medicine.

This study investigates influenza trends in Thailand from 2003 to 2023, employing statistical models for robust analysis. Yearly cumulative influenza patient data, categorized by age groups, are examined using a Poisson Generalised Linear Model (GLM) with a log-link function. The influence of age subgroups, particularly 5-14 and 0-4 years, on disease spread is identified. Additionally, a cubic B-spline regression model is applied to predict cumulative yearly influenza cases, with optimal tuning parameters determined. Results reveal that the year 2019, coinciding with the COVID-19 pandemic, experienced the highest influenza patient count, suggesting a potential relationship between the two diseases. The study utilises the R programming language for thorough statistical analysis, contributing valuable insights into influenza dynamics in Thailand.

The present study forecasts the gold fund's closing price by using Box-Jenkins, Lasso and artificial neural networks over a period of 11 years from May 2010 to February 2021. The evaluation of model accuracy is conducted using Root Mean Square Error (RMSE). The findings indicate that NNAR emerges as the most fitting model for forecasting the gold funds closing price. These results hold significance of investors, economists, market regulators and policymakers, offering insight into the effectiveness of gold price forecasting to take better investment decisions and devise risk management strategies.