Comparative Study of Different Penalty Functions and Algorithms in Survey Calibration

  • Gareth DaviesEmail author
  • Jonathan Gillard
  • Anatoly Zhigljavsky
Part of the Springer Optimization and Its Applications book series (SOIA, volume 107)


The technique of calibration in survey sampling is a widely used technique in the field of official statistics. The main element of the calibration process is an optimization procedure, for which a variety of penalty functions can be used. In this chapter, we consider three of the classical penalty functions that are implemented in many of the standard calibration software packages. We present two algorithms used by many of these software packages, and explore the properties of the calibrated weights and the corresponding estimates when using these two algorithms with the classical calibration penalty functions.


Survey calibration Optimization g-Weights 



Work of the first author was supported by the Engineering and Physical Sciences Research Council, project number 1638853 “Examination of approaches to calibration and weighting for non-response in cross-sectional and longitudinal surveys.” The work of the third author was supported by the Russian Science Foundation, project No. 15-11-30022 “Global optimization, supercomputing computations, and application”.


  1. 1.
    Bankier, M., Rathwell, S., Majkowski, M., et al.: Two step generalized least squares estimation in the 1991 Canadian census. In: Proceedings of the Workshop on Uses of Auxiliary Information in Surveys (1992)Google Scholar
  2. 2.
    Bardsley, P., Chambers, R.: Multipurpose estimation from unbalanced samples. Appl. Stat. 33 (3), 290–299 (1984)CrossRefzbMATHGoogle Scholar
  3. 3.
    Bocci, J., Beaumont, C.: Another look at ridge calibration. Metron 66 (1), 5–20 (2008)zbMATHGoogle Scholar
  4. 4.
    Brewer, K.: Cosmetic calibration with unequal probability sampling. Surv. Methodol. 25 (2), 205–212 (1999)Google Scholar
  5. 5.
    Brodie, P., Cotterell, B.: Reducing or eliminating the effects of extreme calibration weights in social surveys. In: Proceedings, 3rd European Conference on Quality in Survey Statistics, Cardiff (2006)Google Scholar
  6. 6.
    Chambers, R.: Robust case-weighting for multipurpose establishment surveys. J. Off. Stat. 12 (1), 3–32 (1996)MathSciNetGoogle Scholar
  7. 7.
    Chauvet, G., Deville, J., El Haj Tirari, M., Le Guennec, J.: Evaluation de trois logiciels de calage: g-CALIB 2.0, CALMAR 2 et BASCULA 4.0. Tech. rep., Statistics Belgium (2005)Google Scholar
  8. 8.
    Davies, G., Gillard, J., Zhigljavsky, A.: Calibration in survey sampling as an optimization problem. In: Optimization, Control, and Applications in the Information Age, pp. 67–89. Springer, Cham (2015)Google Scholar
  9. 9.
    Deville, J.C., Särndal, C.E.: Calibration estimators in survey sampling. J. Am. Stat. Assoc. 87 (418), 376–382 (1992)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Deville, J.C., Särndal, C.E., Sautory, O.: Generalized raking procedures in survey sampling. J. Am. Stat. Assoc. 88 (423), 1013–1020 (1993)CrossRefzbMATHGoogle Scholar
  11. 11.
    Estevao, V.: Calculation of g-weights under calibration and bound constraints. Tech. rep., Statistics Canada (1994)Google Scholar
  12. 12.
    Estevao, V., Hidiroglou, M., Särndal, C.: Methodological principles for a generalized estimation system at statistics Canada. J. Off. Stat. 11 (2), 181–204 (1995)Google Scholar
  13. 13.
    Fuller, W., Loughin, M., Baker, H.: Regression weighting in the presence of nonresponse with application to the 1987–1988 national food consumption survey. Surv. Methodol. 20, 75–85 (1994)Google Scholar
  14. 14.
    Han, S.P.: A successive projection method. Math. Program. 40 (1), 1–14 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Horvitz, D.G., Thompson, D.J.: A generalization of sampling without replacement from a finite universe. J. Am. Stat. Assoc. 47 (260), 663–685 (1952)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Huang, E., Fuller, W.: Nonnegative regression estimation for sample survey data. In: Proceedings of the Social Statistics Section, vol. 21, pp. 300–305. American Statistical Association, Washington, D.C. (1978)Google Scholar
  17. 17.
    Kalton, G., Flores-Cervantes, I.: Weighting methods. J. Off. Stat. 19 (2), 81–98 (2003)Google Scholar
  18. 18.
    Kish, L.: Weighting for unequal pi. J. Off. Stat. 8 (2), 183 (1992)Google Scholar
  19. 19.
    Kott, P.S.: Using calibration weighting to adjust for nonresponse and coverage errors. Surv. Methodol. 32 (2), 133–142 (2006)Google Scholar
  20. 20.
    Le Guennec, J., Sautory, O.: La macro CALMAR2: redressement d’un échantillon par calage sur marges. Tech. rep., INSEE (2005)Google Scholar
  21. 21.
    Lumley, T.: Package ‘survey’. R package version 3.30-3 (2015)Google Scholar
  22. 22.
    Lundström, S., Särndal, C.E.: Calibration as a standard method for treatment of nonresponse. J. Off. Stat. 15, 305–327 (1999)Google Scholar
  23. 23.
    Mathar, R., Žilinskas, A.: A class of test functions for global optimization. J. Glob. Optim. 5 (2), 195–199 (1994)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Nieuwenbroek, N., Boonstra, H.: Bascula 4.0 Reference Manual. Statistics Netherlands, The Hague/Heerlen (2002)Google Scholar
  25. 25.
    Office for National Statistics. Social Survey Division: Labour Force Survey Five-Quarter Longitudinal Dataset, April 2012–June 2013. UK Data Service. SN: 7379. (2015)
  26. 26.
    Rao, J., Singh, A.: Range restricted weight calibration for survey data using ridge regression. Pak. J. Stat. 25 (4), 371–384 (2009)MathSciNetGoogle Scholar
  27. 27.
    Särndal, C.: The calibration approach in survey theory and practice. Surv. Methodol. 33 (2), 99–119 (2007)Google Scholar
  28. 28.
    Särndal, C.E., Swensson, B., Wretman, J.: Model Assisted Survey Sampling. Springer, New York (2003)zbMATHGoogle Scholar
  29. 29.
    Sautory, O.: Redressements d’échantillons d’enquêtes auprès des ménages par calage sur marges. Tech. rep., INSEE (1991)Google Scholar
  30. 30.
    Sautory, O.: La macro CALMAR. Redressement d’un échantillon par calage sur marges. Tech. rep., INSEE (1993)Google Scholar
  31. 31.
    Sautory, O.: CALMAR2: a new version of the CALMAR calibration adjustment program. In: Proceedings of Statistics Canada Symposium (2003)Google Scholar
  32. 32.
    Singh, A., Mohl, C.: Understanding calibration estimators in survey sampling. Surv. Methodol. 22 (2), 107–116 (1996)Google Scholar
  33. 33.
    Tate, P.F.: Utilising longitudinally linked data from the British labour force survey. Surv. Methodol. 25, 99–104 (1999)Google Scholar
  34. 34.
    Théberge, A.: Calibration and restricted weights. Surv. Methodol. 26 (1), 99–108 (2000)Google Scholar
  35. 35.
    Tillé, Y., Matei, A.: Package ‘sampling’. R package version 2.6 (2015)Google Scholar
  36. 36.
    Torn, A., Žilinskas, A.: Global Optimization. Springer, New York (1989)CrossRefzbMATHGoogle Scholar
  37. 37.
    Vanderhoeft, C.: Generalised calibration at Statistics Belgium: SPSS module g-CALIB-S and current practices. Tech. rep., Statistics Belgium (2001)Google Scholar
  38. 38.
    Ypma, T.J.: Historical development of the Newton-Raphson method. SIAM Rev. 37 (4), 531–551 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  39. 39.
    Zardetto, D.: Package ‘ReGenesees’. R package version 1.7 (2015)Google Scholar
  40. 40.
    Zhigljavsky, A., Žilinskas, A.: Stochastic Global Optimization. Springer, Berlin (2008)zbMATHGoogle Scholar
  41. 41.
    Žilinskas, A.: A review of statistical models for global optimization. J. Glob. Optim. 2 (2), 145–153 (1992)MathSciNetCrossRefzbMATHGoogle Scholar
  42. 42.
    Žilinskas, A.: On similarities between two models of global optimization: statistical models and radial basis functions. J. Glob. Optim. 48 (1), 173–182 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  43. 43.
    Žilinskas, A.: A statistical model-based algorithm for ‘black-box’ multi-objective optimisation. Int. J. Syst. Sci. 45 (1), 82–93 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  44. 44.
    Žilinskas, A., Žilinskas, J.: Branch and bound algorithm for multidimensional scaling with city-block metric. J. Glob. Optim. 43 (2), 357–372 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  45. 45.
    Žilinskas, A., Žilinskas, J.: P-algorithm based on a simplicial statistical model of multimodal functions. Top 18 (2), 396–412 (2010)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Gareth Davies
    • 1
    Email author
  • Jonathan Gillard
    • 1
  • Anatoly Zhigljavsky
    • 1
  1. 1.Cardiff School of MathematicsCardiff UniversityCardiffUK

Personalised recommendations