I am trying to understand linear and GREG survey sample weighting adjustments through some examples. Page 85 of this paper by Calton and Flores-Cervantes shows the adjusted weights using the different weighting methods. The algorithms for Cell weighting and Raking are shown but not for the other methods. Can anybody show me how it was done for linear weighting adjustment and give me some clue on how to proceed about the other methods? I would prefer a step-by-step calculation but I appreciate too how this can be done through R.


It seems the link can't load the PDF directly so I linked to the abstract page instead. The full text can be downloaded from the sidebar link.

Below is a screenshot of Table 1 in page 84 that shows the initially weighted sample and population joint distributions for two auxiliary variables.

enter image description here

Below is a screenshot of Table 2 that shows the weighting adjustments from the different methods.

enter image description here

  • $\begingroup$ The article fails to load. $\endgroup$ – SmallChess Sep 18 '16 at 4:33
  • $\begingroup$ Hopefully the edit fixed it @StudentT. $\endgroup$ – hpesoj626 Sep 18 '16 at 4:57

There is R code and output in the tests directory of the R survey package.

| cite | improve this answer | |
  • $\begingroup$ Thank you for taking your time out to answer this question @ThomasLumley! Greatly appreciated. $\endgroup$ – hpesoj626 Nov 6 '16 at 11:30

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.