中文摘要：

由于以往采用稳健统计分析方法对能力验证数据处理中遇到了诸多问题，如提供信息少，无法恰当描述实验室数据之间的相关性，当测试对象为多组分或多元素时，只能逐一分析单个项目，缺乏整体性，导致当比对内容与对象不断增加时不再适用．为解决此类问题，文章将非负矩阵分解（NMF）引入到能力验证数据处理中，并以CNALT162和CNAST0387为例对其测定的数据进行处理．研究表明，该方法可以多层次、多角度对数据进行分析；可将实验室按测试结果及相似性进行分类，便于对检测过程存在问题的查找和分析，也有利于检测实验室对自身测试水平的认识和评价．

英文摘要：

The method based on the traditional robust statistical analysis to validation data processing tes- ting has so many problems in the past. Such as,less information,can＇t properly describe correlation of the liboratory data;only a single project was analyzed when test object is multivariate, lack of overall judg- ment,and can＇t adapt the content and objects increasing trend. To solve such problems,a non-negative ma- trix faetorization （NMF） to the proficiency testing data processing was introduced, and the two examples were researched. The result indicates that this method can analyze data with multi-level and multi-angle. The experiment will be classified by means of test results and the similarity,it is not only easy to find and analyze the problem of the detection process, but also conducive to the understanding and evaluation of tes- ting laboratories of their own test level.