|
|
|
||||
|
|
|||||
The examples below use Stata 9.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 350 cluster sampling with unequal probabilities: probability proportional to size sampling
This example uses the hospslct data set.
svyset drawing [pw=wstar]
pweight: wstar
VCE: linearized
Strata 1: <one>
SU 1: drawing
FPC 1: <zero>
svy: total lifethrt dxdead
(running total on estimation sample)
Survey: Total estimation
Number of strata = 1 Number of obs = 50
Number of PSUs = 5 Population size = 50056
Design df = 4
--------------------------------------------------------------
| Linearized
| Total Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
lifethrt | 6006.72 1001.12 3227.165 8786.275
dxdead | 2002.24 1226.117 -1402.005 5406.485
--------------------------------------------------------------
svy: mean lifethrt dxdead
(running mean on estimation sample)
Survey: Mean estimation
Number of strata = 1 Number of obs = 50
Number of PSUs = 5 Population size = 50056
Design df = 4
--------------------------------------------------------------
| Linearized
| Mean Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
lifethrt | .12 .02 .0644711 .1755289
dxdead | .04 .0244949 -.0280087 .1080087
--------------------------------------------------------------
svy: ratio dxdead/lifethrt
(running ratio on estimation sample)
Survey: Ratio estimation
Number of strata = 1 Number of obs = 50
Number of PSUs = 5 Population size = 50056
Design df = 4
_ratio_1: dxdead/lifethrt
--------------------------------------------------------------
| Linearized
| Ratio Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
_ratio_1 | .3333333 .2324056 -.311928 .9785946
--------------------------------------------------------------
Page 351 cluster sampling with unequal probabilities: probability proportional to size sampling
gen tl = .
(50 missing values generated)
replace tl = 785 if hospno == 2
(10 real changes made)
replace tl = 3404 if hospno == 5
(30 real changes made)
replace tl = 778 if hospno == 9
(10 real changes made)
gen w2star = (admiss/50)*(7087/tl)
svyset drawing [pw=w2star]
pweight: w2star
VCE: linearized
Strata 1: <one>
SU 1: drawing
FPC 1: <zero>
svy: total lifethrt dxdead
(running total on estimation sample)
Survey: Total estimation
Number of strata = 1 Number of obs = 50
Number of PSUs = 5 Population size = 51345
Design df = 4
--------------------------------------------------------------
| Linearized
| Total Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
lifethrt | 6259.176 1277.322 2712.762 9805.591
dxdead | 1760.471 1079.043 -1235.433 4756.376
--------------------------------------------------------------
svy: mean lifethrt dxdead
(running mean on estimation sample)
Survey: Mean estimation
Number of strata = 1 Number of obs = 50
Number of PSUs = 5 Population size = 51345
Design df = 4
--------------------------------------------------------------
| Linearized
| Mean Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
lifethrt | .1219043 .0214156 .0624452 .1813634
dxdead | .0342871 .0230032 -.02958 .0981542
--------------------------------------------------------------
svy: ratio dxdead/lifethrt
(running ratio on estimation sample)
Survey: Ratio estimation
Number of strata = 1 Number of obs = 50
Number of PSUs = 5 Population size = 51345
Design df = 4
_ratio_1: dxdead/lifethrt
--------------------------------------------------------------
| Linearized
| Ratio Std. Err. [95% Conf. Interval]
-------------+------------------------------------------------
_ratio_1 | .2812625 .2114835 -.3059098 .8684347
--------------------------------------------------------------
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