2016/01/25 by Holger Dette, Dette, Holger, Kirsten Schorning +3
Decision Sciences · Mathematics · #Advanced Statistical Methods and Models #Advanced Statistical Process Monitoring #FOS: Computer and information sciences #Methodology (stat.ME) #Optimal Experimental Design Methods
paper · pdf · doi:10.48550/arxiv.1601.06722
openalex publication_date 2016/01/25 · openalex created_date 2022/10/07 · openalex updated_date 2026/07/28
We consider the problem of efficient statistical inference for comparing two\nregression curves estimated from two samples of dependent measurements. Based\non a representation of the best pair of linear unbiased estimators in\ncontinuous time models as a stochastic integral, an efficient pair of linear\nunbiased estimators with corresponding optimal designs for finite sample size\nis constructed. This pair minimises the width of the confidence band for the\ndifference between the estimated curves. We thus extend results readily\navailable in the literature to the case of correlated observations and provide\nan easily implementable and efficient solution. The advantages of using such\npairs of estimators with corresponding optimal designs for the comparison of\nregression models are illustrated via numerical examples.\n