Comparison of Algorithms for Two-way Stratification Design

  • Published : 2004.04.01


Kim et al. (2002) developed public use SAS-based software for two-way stratification design, which is called SOCSLP We describe the details of a new approach implemented using SOCSLP and key differences between the approach and the sampling schemes of Sitter and Skinner (1994) and Winkler (2001). In addition, a numerical example is given to compare those methods with respect to the probabilities of selecting sample arrays.


  1. The Journal of the American Statistical Association v.55 Design and estimation in two-way stratification Bryant,E.C.;Hartley,H.O.;Jessen,R.J.
  2. The Journal of the American Statistical Association v.80 Application of transportation theory to statistical problems Causey,B.D.;Cox,L.H.;Ernst,L.R.
  3. The Journal of the American Statistical Association v.45 Controlled selection - a technique in probability sampling Goodman,R.;Kish,L.
  4. Probability Sampling of Hospitals and Patients(2nd ed.) Hess,I.;Ridel,D.C.;Fitzpatrick,T.B.
  5. The Journal of the American Statistical Association v.65 Probability sampling with marginal constraints Jessen,R.J.
  6. Proceedings of the Survey Research Methods Section Kim,Sun-Woong;Heeringa,S.G.;Solenberger P.W.
  7. User's guide: mathematical programming, Version 8. SAS/OR
  8. Survey Methodology v.20 no.1 Multi-way stratification by linear programming Sitter,R.R.;Skinner,C.J.
  9. Biometrika v.77 Optimal controlled sampling design Rao,J.N.K;Nigam,A.K.
  10. International Statistical Review v.60 Optimal controlled sampling: a unified approach Rao,J.N.K.;Nigam,A.K.
  11. U.S. Bureau of the Census, Statistical Division Report RRS2001/01 Multi-way survey stratification and sampling Winkler,E.W.