A0359
Title: Unpaired regression for a discrete response via Poisson quantiles matching
Authors: Hyungjun Lim - Korea University (Korea, South) [presenting]
Arlene Kyoung Hee Kim - Korea University (Korea, South)
Abstract: Analyzing the data collected from different sources requires unpaired data analysis to account for the absence of correspondence between the response variable $Y$ and explanatory variables $X$. Several attempts have been made to analyze continuous $Y$, but the response variable of interest may follow a discrete distribution, which previous methodologies have overlooked. To address these limitations, Poisson quantile matching estimation (PQME) is proposed, the first unpaired data analysis method designed to examine the discrete response variable $Y$ and the unpaired continuous explanatory variable $X$. Using their order statistics, the PQME method matches the linear combination of explanatory variables to $\ln(Y)$. An effective algorithm and simulation results are presented, along with the convergence results. The practical application of PQME is illustrated by locating the ideal site for a new facility using real data.
