当前位置: X-MOL 学术Environmetrics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Robust functional multivariate analysis of variance with environmental applications
Environmetrics ( IF 1.7 ) Pub Date : 2020-05-31 , DOI: 10.1002/env.2641
Zhuo Qu 1 , Wenlin Dai 2 , Marc G. Genton 1
Affiliation  

We propose median polish for functional multivariate analysis of variance (FMANOVA) with the implementation of depth for multivariate functional data. As an alternative to classical mean estimation, functional median polish estimates the functional grand effect and factor effects based on functional medians in one‐way and two‐way additive FMANOVA models. Median polish estimates in FMANOVA are visually unbiased, independently of the choice of multivariate functional depth. The corresponding mean‐based and rank‐based tests are generalized to evaluate whether the functional medians in various levels of the factors are the same. Simulation studies illustrate the robustness of our functional median polish in various scenarios, compared with the results from classical FMANOVA fitted by means. The results are evaluated both marginally and jointly. Three environmental data sets are considered to illustrate that our median polish is robust against outliers in practical implementations. Functional boxplots and heat maps are two ways of visualizing the functional factors, depending on whether the functional data are curves or images, respectively.

中文翻译:

对环境应用进行方差分析的鲁棒函数多元分析

我们建议使用中值波兰语进行方差函数多元分析(FMANOVA),并针对多元函数数据进行深度实现。作为经典均值估计的替代方法,函数中位数抛光基于单向和双向加法FMANOVA模型中的函数中位数来估计函数宏效应和因子效应。FMANOVA中的波兰语中值估计在视觉上无偏见,与多元功能深度的选择无关。概括了相应的基于均值和基于秩的检验,以评估各个级别因素的功能中位数是否相同。仿真研究表明,与经典FMANOVA拟合方法得出的结果相比,我们的功能性中值抛光剂在各种情况下的鲁棒性。对结果进行边际评估和联合评估。考虑了三个环境数据集,以说明我们的中值抛光在实际实现中对异常值具有鲁棒性。功能盒图和热图是可视化功能因子的两种方式,分别取决于功能数据是曲线还是图像。
更新日期:2020-05-31
down
wechat
bug