Application of Statistical Selection Procedures in Biotechnology

  • Ute Römisch
  • S. Gargova
Conference paper
Part of the Contributions to Statistics book series (CONTRIB.STAT.)


A short methodical summary about the two classes of statistical selection procedures is given, i.e. the indifference zone (and d-correct) procedures and the subset procedures. The biotechnological problem consisted in selecting the „best“ or at least a „good“ mutant with high enzyme activity from a set of eight mutants of the species Aspergillus niger with a large probability. Depending on suppositions about the variances of the enzyme activities, different selection rules are applied. Starting with the subset procedure of Gupta (1985) for the case of equal variances, the number of mutants is reduced. The following d-correct procedure of Bechhofer, Dunnett and Sobel (1954) calculates the necessary sample size n. Then the mutant whose sample has the largest mean will be selected as a „good“ one with a given precision of d and a probability of correct selection of (1-β). As long as the variances of the enzyme activities are assumed to be different, the selection procedure of Dudewicz and Dalai (1975) must be used.

Key words

biotechnology enzyme activity selection subset indifference zone procedure 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bechhofer, R.E. (1954). A single-sample multiple decision procedure for ranking means of normal populations with known variances. Ann. Math. Stat. 25, 16–39.CrossRefGoogle Scholar
  2. Bechhofer,R. E., Dunnett, C.W.and Sobel, M. (1954). A two-sample multiple decision procedure for ranking means of normal populations with a common unknown variance. Biometrika 41, 170–176.Google Scholar
  3. Chiu, W.K. (1974). The ranking of means of normal populations for a generalised selection goal. Biometrika 61, 579–584.CrossRefGoogle Scholar
  4. Dudewicz, EJ. and Dalal, S.R. (1975). Allocation of observations in ranking and selection with unequal variances. Sankhya Ser.B 37, 28–78.Google Scholar
  5. Gargova, S. and Tschiriska, J. (1984). Study of the effects of different mutagenic factors on Aspergillus niger. Sci. Rep of the HIFFI Vol XXXI/1, 255–262.Google Scholar
  6. Gupta, S.S. and Kim, W. (1984). A two-stage elimination type procedure for selecting the largest of several normal means with a common unknown variance, in: Design of Experiments: Ranking and selection. Ed. by T.J. Santner and A.C. Tamhane, M.Dekker Inc., New York.Google Scholar
  7. Gupta, S.S. and Panchapakesan, S. (1985). Subset selection procedures: review and assessment. Amer. J. Math. Managern. Sci. 5, 235–223.Google Scholar
  8. Horn, M. and Vollandt, R. (1995). Multiple Tests und Auswahlverfahren. Reihe Biometrie. G. Fischer Verl. Stuttgart.Google Scholar
  9. Hsu, J.C. (1980). Robust and nonparametric subset selection procedures. Commun. Statist.Theor. Meth. 9, 1439–1459.CrossRefGoogle Scholar
  10. Hsu, J.C. (1981). Simultaneous confidence intervals for all distances from the “best”. Ann. Statist. 9, 1026–1034.CrossRefGoogle Scholar
  11. Rasch, D., Herrendörfer, G., Bock, J., Victor, N. and Guiard, V. (1996). Verfahrensbibliothek-Versuchsplanung und-Auswertung, Bd.1, R. OldenbourgVerl., München.Google Scholar
  12. Sobel, M. (1967). ISfonparametric procedures for selecting the t populations with the largest α-quantile. Ann. Math. Statist. 38, 1804–1816.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Ute Römisch
    • 1
  • S. Gargova
    • 2
  1. 1.FB Lebensmittelwissenschaft und Biotechnologie, FG InformatikTechnische Universität BerlinBerlinGermany
  2. 2.Plovdiv Dep. of BiotechnologyHigher Institute of Food and Flavour IndustryPlovdivBulgaria

Personalised recommendations