|
|
|
| Study on the Distributions of Interlaboratory Comparisons Data of Oil Atomic Emission Spectrometer |
| LIU Yun-tao1,2,TIAN Hong-xiang1,Dong Qing-shan2 |
1.College of Naval Architecture and Power,Naval University of Engineering, Wuhan, Hubei 430033, China
2.Department of Equipment,Naval 91959 Army, Sanya, Hainan 572016, China |
|
|
|
|
Abstract It’s found that part of the data didn’t fit normal distribution in the process of interlaboratory comparisons of oil atomic emission spectroscopies,so that,methods which are based on normal distribution hypothesis,such as Z-test and h-test,couldn’t be used to the data.Based on polluted distribution class model in statistics and the principle of maximum likelihood estimation,the distribution model which based on normal distribution hypothesis were mended.It’s assumed that the non-normal distribution data should fit polluted distributions contained 2 or more normal distributions.And the normal distribution,whose coefficient is the biggest in the polluted distribution,should be considered as the estimated distribution of population.Chi-square test results showed that,of the 4 non-normal distribution elements,there are 3 elements fitted polluted distribution,and the other one didn’t.
|
|
|
|
|
|
|
|
［1］Yan X P, Zhao C H, Lu Z Y, et al. A Study of Information Technology Used in Oil Monitoring［J］.Tribology International,2005,38:879-886.
［2］刘瑜,田洪祥,陈锦玲.油料发射光谱仪检测性能的实验室间比对［J］.计量学报,2010,31(2):183-188.
［3］Lin Z C, Inn K G W, Filliben J J. An alternative statistical approach for interlaboratory comparison data evaluation［J］. Journal of Radioanalytical and Nuclear Chemistry,2001,248(1):163-173.
［4］代彩红,林延东,于家琳,黄勃.紫外辐射照度计国内量值比对与一致性分析［J］.计量学报,2010,31(4):303-307.
［5］Zhou Q, Shen Z Y, Li S N, et al. Robust and traditional statistical methods in the establishment ofimmunoglobulin E target values in externalquality assessment program［J］.Clinica Chimica Acta,2008,387:66–70.
［6］Corporation S M． Spectroil M Operation & Maintenance Manual (version2.2)［M］． USA:Spectroil M Corporation,2006．
［7］刘瑜.油料发射光谱仪检测性能研究［D］.武汉:海军工程大学,2008.
［8］MaCurdya T E, Ryub K. E quivalence results in chi-square tests［J］. Economics Letters,2003,80:329. |
|
|
|
2012, Vol. 33 
