Journal of Korean Society of Occupational and Environmental Hygiene (한국산업보건학회지)

Korean Industrial Hygiene Association (한국산업보건학회)
권호 표지
DOI QR코드

DOI QR Code

A Comparison of Analysis Methods for Work Environment Measurement Databases Including Left-censored Data

불검출 자료를 포함한 작업환경측정 자료의 분석 방법 비교

  • Park, Ju-Hyun (Department of Statistics, Dongguk University) ;
  • Choi, Sangjun (Graduate School of Public Health and Healthcare Management, The Catholic University of Korea) ;
  • Koh, Dong-Hee (Department of Occupational and Environmental Medicine, International St.Mary's Hospital, Catholic Kwandong University) ;
  • Park, Donguk (Department of Environmental Health, Korea National Open University) ;
  • Sung, Yeji (Graduate School of Public Health and Healthcare Management, The Catholic University of Korea)
  • Received : 2022.02.02
  • Accepted : 2022.03.17
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Objectives: The purpose of this study is to suggest an optimal method by comparing the analysis methods of work environment measurement datasets including left-censored data where one or more measurements are below the limit of detection (LOD). Methods: A computer program was used to generate left-censored datasets for various combinations of censoring rate (1% to 90%) and sample size (30 to 300). For the analysis of the censored data, the simple substitution method (LOD/2), β-substitution method, maximum likelihood estimation (MLE) method, Bayesian method, and regression on order statistics (ROS)were all compared. Each method was used to estimate four parameters of the log-normal distribution: (1) geometric mean (GM), (2) geometric standard deviation (GSD), (3) 95th percentile (X95), and (4) arithmetic mean (AM) for the censored dataset. The performance of each method was evaluated using relative bias and relative root mean squared error (rMSE). Results: In the case of the largest sample size (n=300), when the censoring rate was less than 40%, the relative bias and rMSE were small for all five methods. When the censoring rate was large (70%, 90%), the simple substitution method was inappropriate because the relative bias was the largest, regardless of the sample size. When the sample size was small and the censoring rate was large, the Bayesian method, the β-substitution method, and the MLE method showed the smallest relative bias. Conclusions: The accuracy and precision of all methods tended to increase as the sample size was larger and the censoring rate was smaller. The simple substitution method was inappropriate when the censoring rate was high, and the β-substitution method, MLE method, and Bayesian method can be widely applied.

Keywords

References

  1. Byeon S, Yi K, Yu G, Phee Y. Regulatory compliance for the working environment measurement system in Korea. J Korean Soc Occup Environ Hyg 2009;19(3):233-239
  2. Choi S. Assessment on work environment monitoring program in Korea. J Korean Soc Occup Environ Hyg 2008;18(4):282-292
  3. Choi S, Kang D, Park D, Lee H, Choi B. Developing asbestos job exposure matrix using occupation and industry specific exposure data (1984-2008) in Republic of Korea. Saf Health Work 2017;8(1):105-115 (https://doi:10.1016/j.shaw.2016.09.002)
  4. Chung DA, Yang RR, Verma DK, Luo J. Retrospective exposure assessment for occupational disease of an individual worker using an exposure database and trend analysis. J Occup Environ Hyg 2015;12(12):855-65 (https://doi.org/10.1080/15459624.2015.1072630)
  5. Cohn TA, DeLong LL, Gilroy EJ, Hirsch RM, Wells DK. Estimating constituent loads. Water Resources Research 1989;25(5):937-942 (https://doi.org/10.1029/WR025i005p00937)
  6. Finkelstein MM, Verma DK. Exposure estimation in the presence of nondetectable values: Another look. AIHAJ 2001;62(2):195-198 (https://doi.org/10.1080/15298660108984622)
  7. Ganser GH, Hewett P. An accurate substitution method for analyzing censored data. J Occup Environ Hyg 2010;7(4):233-244 (https://doi.org/10.1080/15459621003609713)
  8. Glass DC, Gray CN. Estimating mean exposures from censored data: Exposure to benzene in the Australian petroleum industry. Ann Occup Hyg 2001;45(4):275-282 (https://doi.org/10.1093/annhyg/45.4.275)
  9. Helsel DR. Statistics for censored environmental data using minitab and R, Second Edition. Hoboken, New Jersey: John Wiley & Sons; 2012
  10. Hewett P, Ganser GH. A comparison of several methods for analyzing censored data. Ann Occup Hyg. 2007;51(7):611-632 (https://doi.org/10.1093/annhyg/mem045)
  11. Hornung RW, Reed LD. Estimation of average concentration in the presence of nondetectable values. Appl Occup Environ Hyg. 1990;5(1):46-51 (https://doi.org/10.1080/1047322X.1990.10389587)
  12. Huynh T, Ramachandran G, Banerjee S, Monteiro J, Stenzel M, Sandler DP, Engel LS, Kwok RK, Blair A, Stewart PA. Comparison of methods for analyzing left-censored occupational exposure data. Ann Occup Hyg 2014;58(9):1126-1142 (https://doi.org/10.1093/annhyg/meu067)
  13. Huynh T, Quick H, Ramachandran G, Banerjee S, Stenzel M, Sandler DP, Engel LS, Kwok RK, Blair A, Stewart PA. A comparison of the β-substitution Method and a Bayesian method for analyzing left-censored data. Ann Occup Hyg 2016;60(1):56-73 (https://doi.org/10.1093/annhyg/mev049)
  14. Koh DH, Jeon HK, Lee SG, Ryu HW. The relationship between low-level benzene exposure and blood cell counts in Korean workers. Occup Environ Med 2015;72(6):421-427 (https://doi:10.1136/oemed2014-102227)
  15. Koh DH, Park JH, Lee SG, Kim HC, Choi S, Jung H, Park DU. Combining lead exposure measurements and experts' judgment through a Bayesian framework. Ann Work ExpoHealth 2017;61(9):1054-1075 (https://doi: 10.1093/annweh/wxx072)
  16. Koh DH, Park JH, Lee SG, Kim HC, Choi S, Jung H, Park JO, Park DU. Estimation of lead exposure prevalence in Korean population through combining multiple experts' judgment based on objective data sources. Ann Work Expo Health 2018;62(2):210-220 (https://doi: 10.1093/annweh/wxx106)
  17. Koh DH, Park JH, Lee SG, Kim HC, Jung H, Kim I, Choi S, Park D. Estimation of lead exposure intensity by industry using nationwide exposure databases in Korea. Saf Health Work 2021;12(4):439-444 (https://doi: 10.1016/j.shaw.2021.07.008)
  18. Millard SP. EnvStats: an R package for environmental statistics. New York: Springer; 2013. ISBN 978- 1-4614-8455-4, URL:https://www.springer.com.
  19. Mulhausen J, Damiano J. A Strategy for assessing and managing occupational exposures, Second Edition. Fairfax Va: AIHA; 1998.
  20. Perkins JL, Cutter GN, Cleveland MS. Estimating the mean, variance, and confidence limits from censored (
  21. R Core Team. R: A language and environment for statistical computing. R Foundation forStatistical Computing, Vienna, Austria. 2021. URL https://www.R-project.org/.
  22. Tekindal MA, Erdogan BD, Yavuz Y. Evaluating left-censored data through substitution, parametric, semi-parametric, and nonparametric methods: a simulation study. Interdiscip Sci 2017;9(2):153-172 (https://DOI 10.1007/s12539-015-0132-9)