Key research themes
1. How can ratio transformations be optimized to effectively control for size variation in morphometric data?
This research area investigates the mathematical and statistical properties of ratio transformations when adjusting morphometric measurements to control for overall size effects. The goal is to identify ratio formulations that successfully eliminate size correlations while preserving meaningful shape variation, avoiding common pitfalls such as residual size dependence, distributional distortions, and biases introduced by improper regression modeling.
2. What advancements improve ratio-type estimators in survey sampling for more precise population mean estimation?
Survey sampling employs ratio-based estimators to leverage auxiliary information, enhancing the accuracy of population mean estimation, particularly in stratified designs. This theme surveys developments in ratio and exponential ratio estimators adjusted via calibration, power transformations, and incorporation of auxiliary variable parameters. Emphasis is on reducing bias and mean square error (MSE), handling positive or negative correlations, and usage of stratified sampling calibration to optimally weight estimators.
3. How can the Taguchi method and signal-to-noise ratio analysis optimize process parameters in engineering applications?
This research area focuses on applying the Taguchi design of experiments (DOE) methodology combined with signal-to-noise (S/N) ratio analysis for robust optimization of multi-parameter industrial and manufacturing processes. The approach seeks reduction in process variability, enhanced product quality, and improved performance metrics by systematically evaluating input factors and their levels. It has been adopted broadly in machining, welding, manufacturing defect reduction, and thermal system design, showcasing its versatility in handling noisy industrial environments.


