 |
      |
||||
|
Help the Stat Consulting Group by
giving a gift
| |||||
|
Loading
|
|||||
Stata FAQ
How do I analyze survey data with a stratified random sampling design?
The examples below use Stata 9. If you are using Stata versions 7 or 8, please see this page.NOTE: If you want to see the design effect or the misspecification effect, use estat effects after the command.
This example is taken from Levy and Lemeshow's Sampling of Populations.
page 136 stratified random sampling
use http://www.ats.ucla.edu/stat/books/sop/hospsamp.dta, clear
svyset [pweight=weighta], strata(oblevel) fpc(tothosp)
pweight: weighta
VCE: linearized
Strata 1: oblevel
SU 1: <observations>
FPC 1: tothosp
svy: total births
(running total on estimation sample)
Survey: Total estimation
Number of strata = 3 Number of obs = 15
Number of PSUs = 15 Population size = 158
Design df = 12
--------------------------------------------------------------
| Linearized
| Total Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
births | 183982.9 34014.33 109872 258093.8
--------------------------------------------------------------
svy: total births, over(oblevel)
(running total on estimation sample)
Survey: Total estimation
Number of strata = 3 Number of obs = 15
Number of PSUs = 15 Population size = 158
Design df = 12
1: oblevel = 1
2: oblevel = 2
3: oblevel = 3
--------------------------------------------------------------
| Linearized
Over | Total Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
births |
1 | 14931 2669.857 9113.882 20748.12
2 | 117116.9 33067.66 45068.68 189165.2
3 | 51934.98 7508.399 35575.58 68294.37
--------------------------------------------------------------
This example is taken from Lehtonen and Pahkinen's Practical Methods for Design and Analysis of Complex Surveys.
page 74 Table 3.3 Estimates from an optimally allocated stratified simple random sample (n = 8); the Province'91 population.
NOTE: In this data set, the fpc changes with the strata. This is different from all of the previous examples.
input id str clu wt ue91 lab91 fpc 1 1 1 1.75 4123 33786 7 2 1 2 1.75 666 6016 7 3 1 4 1.75 760 5919 7 4 1 6 1.75 457 3022 7 5 2 21 6.25 61 573 25 6 2 25 6.25 262 1737 25 7 2 26 6.25 331 2543 25 8 2 27 6.25 98 545 25 end
svyset clu [pweight=wt], fpc(fpc) strata(str)
pweight: wt
VCE: linearized
Strata 1: str
SU 1: clu
FPC 1: fpc
svy: total ue91
(running total on estimation sample)
Survey: Total estimation
Number of strata = 2 Number of obs = 8
Number of PSUs = 8 Population size = 32
Design df = 6
--------------------------------------------------------------
| Linearized
| Total Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
ue91 | 15210.5 4279.452 4739.059 25681.94
--------------------------------------------------------------
estat effects
----------------------------------------------------------
| Linearized
| Total Std. Err. Deff Deft
-------------+--------------------------------------------
ue91 | 15210.5 4279.452 .20649 .393532
----------------------------------------------------------
Note: Weights must represent population totals for deff to be correct when using an FPC; however, deft is
invariant to the scale of weights.
svy: ratio ue91 lab91
(running ratio on estimation sample)
Survey: Ratio estimation
Number of strata = 2 Number of obs = 8
Number of PSUs = 8 Population size = 32
Design df = 6
_ratio_1: ue91/lab91
--------------------------------------------------------------
| Linearized
| Ratio Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
_ratio_1 | .1277788 .0031736 .1200134 .1355442
--------------------------------------------------------------
estat effects
_ratio_1: ue91/lab91
----------------------------------------------------------
| Linearized
| Ratio Std. Err. Deff Deft
-------------+--------------------------------------------
_ratio_1 | .1277788 .0031736 .380341 .534093
----------------------------------------------------------
Note: Weights must represent population totals for deff to be correct when using an FPC; however, deft is
invariant to the scale of weights.
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services
The content of this web site should not be construed as an endorsement of any particular web site, book, or software product by the University of California