help svy estimation also see: svy
svy postestimation
-------------------------------------------------------------------------------
Title
[SVY] svy estimation -- Estimation commands for survey data
Description
Survey data analysis in Stata is essentially the same as standard data
analysis. The standard syntax applies; you just need to also remember
the following:
o Use svyset to identify the survey design characteristics.
o Prefix the estimation commands with svy:.
For example,
. webuse nhanes2f
. svyset psuid [pweight=finalwgt], strata(stratid)
. svy: regress zinc age c.age#c.age weight female black orace
rural
The following estimation commands support the svy prefix.
command description
-------------------------------------------------------------------------
Descriptive statistics
mean Estimate means
proportion Estimate proportions
ratio Estimate ratios
total Estimate totals
Linear regression models
cnsreg Constrained linear regression
glm Generalized linear models
intreg Interval regression
nl Nonlinear least-squares estimation
regress Linear regression
tobit Tobit regression
treatreg Treatment-effects regression
truncreg Truncated regression
Survival-data regression models
stcox Cox proportional hazards model
streg Parametric survival models
Binary-response regression models
biprobit Bivariate probit regression
cloglog Complementary log-log regression
hetprob Heteroskedastic probit regression
logistic Logistic regression, reporting odds ratios
logit Logistic regression, reporting coefficients
probit Probit regression
scobit Skewed logistic regression
Discrete-response regression models
clogit Conditional (fixed-effects) logistic regression
mlogit Multinomial (polytomous) logistic regression
mprobit Multinomial probit regression
ologit Ordered logistic regression
oprobit Ordered probit regression
slogit Stereotype logistic regression
Poisson regression models
gnbreg Generalized negative binomial regression
nbreg Negative binomial regression
poisson Poisson regression
zinb Zero-inflated negative binomial regression
zip Zero-inflated Poisson regression
ztnb Zero-truncated negative binomial regression
ztp Zero-truncated Poisson regression
Instrumental-variables regression models
ivprobit Probit model with endogenous regressors
ivregress Single-equation instrumental-variables regression
ivtobit Tobit model with endogenous regressors
Regression models with selection
heckman Heckman selection model
heckprob Probit model with sample selection
-------------------------------------------------------------------------
Menu
Statistics > Survey data analysis > ...
Dialog boxes for all statistical estimators that support svy can be found
on the above menu path. In addition, you can access survey data
estimation from standard dialog boxes on the SE/Robust or SE/Cluster tab.
Examples
Descriptive statistics
. webuse nmihs
. svyset [pweight=finwgt], strata(stratan)
. svy: mean birthwgt
Regression models
. webuse nhanes2d
. svyset
. svy: logistic highbp height weight age age2 female
. svy, subpop(female): logistic highbp height weight age age2
Cox proportional hazards model
. webuse nhefs
. svyset psu2 [pw=swgt2], strata(strata2)
. stset age_lung_cancer [pw=swgt2], fail(lung_cancer)
. svy: stcox former_smoker smoker male urban1 rural
Multiple baseline hazards
. stphplot, strata(revised_race) adjust(former_smoker smoker male urban1
rural) zero legend(col(1))
. svy: stcox former_smoker smoker male urban1 rural, strata(revised_race)
Also see
Manual: [SVY] svy estimation
Help: [SVY] svy, [SVY] svy postestimation, [SVY] svyset
