The examples below use Stata 8. If you are using Stata version 9, please see this page.
This example is taken from Lehtonen and Pahkinen’s Practical Methods for Design and Analysis of Complex Surveys.
page 46 Table 2.6 Estimates from a systematic sample drawn from the Province’91 population using implicit stratification.
NOTE: The standard error of the total is different from that shown in the text (the text shows 11802). However, we get the 13627 in each of the statistical packages in which we have tried to recreate this example.
input id str clu wt ue91 lab91 1 1 1 4 4123 33786 2 1 5 4 721 4930 3 2 9 4 194 2069 4 2 13 4 129 927 5 2 17 4 239 2144 6 2 21 4 61 573 7 2 25 4 262 1737 8 2 29 4 166 1615 end gen fpc = 32 svyset [pweight=wt], psu(clu) strata(str) fpc(fpc) svytotal ue91 Survey total estimation pweight: wt Number of obs = 8 Strata: str Number of strata = 2 PSU: clu Number of PSUs = 8 FPC: fpc Population size = 32 ------------------------------------------------------------------------------ Total | Estimate Std. Err. [95% Conf. Interval] Deff ---------+-------------------------------------------------------------------- ue91 | 23580 13191.99 -8699.644 55859.64 .9479457 ------------------------------------------------------------------------------ Finite population correction (FPC) assumes simple random sampling without replacement of PSUs within each stratum with no subsampling within PSUs. Weights must represent population totals for deff to be correct when using an FPC. Note: deft is invariant to the scale of weights. svyratio ue91 lab91 Survey ratio estimation pweight: wt Number of obs = 8 Strata: str Number of strata = 2 PSU: clu Number of PSUs = 8 FPC: fpc Population size = 32 ------------------------------------------------------------------------------ Ratio | Estimate Std. Err. [95% Conf. Interval] Deff ------------------+----------------------------------------------------------- ue91/lab91 | .1233754 .0036606 .1144183 .1323325 1.560909 ------------------------------------------------------------------------------ Finite population correction (FPC) assumes simple random sampling without replacement of PSUs within each stratum with no subsampling within PSUs. Weights must represent population totals for deff to be correct when using an FPC. Note: deft is invariant to the scale of weights.