This work introduces a novel rank-based test for comparing yield quality distributions across multiple spatially distributed populations while accounting for spatial dependence. Traditional methods often fail to address the challenges posed by spatial correlation and heterogeneity, leading to unreliable conclusions. The proposed test integrates kernel smoothing with spatially weighted cumulative distribution function (CDF) estimation to ensure robustness against outliers and deviations from distributional assumptions. A test statistic is derived by aggregating squared differences between smoothed CDFs, and its asymptotic properties are established under the null hypothesis, demonstrating convergence to a weighted sum of chi-squared random variables. Practical implementation relies on resampling techniques such as permutation tests and spatial bootstrap methods to approximate the null distribution. The test is consistent under alternatives, making it an effective tool for analyzing spatially dependent data in fields such as environmental monitoring and agricultural research. Extensions to multivariate and spatio-temporal applications are suggested for future work.

翻译：暂无翻译