Identifying Extremely Large Observations

  • Ganapati P. PatilEmail author
  • Sharad D. Gore
  • Charles Taillie*
Part of the Environmental and Ecological Statistics book series (ENES, volume 4)


It is not necessary that all environmental problems of site characterization, cleanup evaluation, and compliance monitoring aim only at estimating the average value. Many of these problems also have an interest in extremely high contamination levels. A common experience is that compositing sample averages out the individual sample values and hence does not incur any loss of information on the population mean. However, compositing poses a serious problem if the interest is in extreme values. There is very limited literature on detection of large individual sample values. Casey et al (1985) give a method to predict the maximum sample value using composite sample measurements. Gore and Patil (1993) develop a statistical method to identify the largest individual sample value without exhaustively obtaining all individual sample values.


Composite Sample Individual Sample Sample Maximum Component Sample Surface Soil Sample 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Boswell, M. T. and Patil, G.P. (1990). Composite sampling using spatial autocorrelation for Palmerton hazardous waste site: A preliminary report. In Proceedings of the Workshop on Superfund Hazardous Waste: Statistical Issues in Characterizing a Site: Protocols, Tools, and Research Needs, H. Lacayo, R. J. Nadeau, G. P. Patil, and L. Zaragoza, eds. USEPA Statistical Policy Branch, Washington DC. pp. 20–42.Google Scholar
  2. Carson, J. Jr. (2001). Analysis of composite sampling data using the principle of maximum entropy. Environ. Ecol. Stat. 8:201–211.CrossRefMathSciNetGoogle Scholar
  3. Casey, D. B., Nemetz, P. N., and Uyeno, D. (1985). Efficient search procedures for extreme pollutant values. Environ. Monit. Assess. 5:165–176.CrossRefGoogle Scholar
  4. Gore, S. D., Patil, G. P., Sinha, A. K., and Taillie, C. (1993). Certain Multivariate Considerations in Ranked Set Sampling and Composite Sampling Designs. In Multivariate Environmental Statistics, G. P. Patil and C. R. Rao, eds. Elsevier, New York, NY. pp. 121–148.Google Scholar
  5. Texas Eastern Gas Pipeline Company (1989a). Results of the Phase II surface soil and sediment sampling activities at the Armagh site, Pennsylvania, Vol. I. Roy F. Weston, West Chester, PA 19380.Google Scholar
  6. Texas Eastern Gas Pipeline Company (1989b). Results of the Phase II surface soil and sediment, sampling activities at the Armagh site, Pennsylvania, Vol. II: Appendices. Roy F. Weston, West Chester, PA 19380.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Ganapati P. Patil
    • 1
    Email author
  • Sharad D. Gore
    • 2
  • Charles Taillie*
    • 3
  1. 1.Center for Statistical Ecology and Environmental StatisticsPennsylvania State UniversityUniversity ParkUSA
  2. 2.Department of StatisticsUniversity of PunePuneIndia
  3. 3.Center for Statistical Ecology and Environmental StatisticsPenn State UniversityUniversity ParkUSA

Personalised recommendations