Whether your data require simple weighted adjustment because of differential sampling rates or you have data from a complex multistage survey, Stata’s survey features can provide you with correct standard errors and confidence intervals for your inferences. All you need to do is specify the relevant characteristics of your sampling design, including sampling weights (including weights at multiple stages), clustering (at one, two, or more stages), stratification, and poststratificaion. After that, most of Stata’s estimation commands can adjust their estimates to correct for your sampling design.
Survey regression models
- Descriptive statistics
- Linear regression models
- Structural equation models
- Survival-data regression models
- Binary-response regression models
- Discrete-response regression models
- Fractional-response regression models
- Poisson regression models
- Instrumental-variables regression models
- Regression models with selection
- Multilevel mixed-effects models
- Finite mixture models
- Item response theory
Watch Multilevel models for survey data in Stata
Variance and standard-error estimates
- Taylor-series linearization (Huber/White/sandwich)
- Balanced and repeated replications (BRR)
- Survey jackknife
- Bootstrap (with bootstrap replicate weights)
- Successive difference replication (SDR)
Sampling designs
- Sampling (probability) weights
- Stratification
- Clustering
- Multistage designs
- Weights at each sampling stage
- Finite population correction in all stages
- Support for strata with one sampling unit
- Watch Basic introduction to the analysis of complex survey data.
- Watch Specifying the design of your survey data
- Watch Specifying the poststratification of survey data
Features
- Poststratification
- Weight calibration via the raking-ratio method
- Weight calibration via the generalized regression (GREG) method
- Design effects
- Misspecification effects
- Effects for linear combinations
- Coefficient of variation
- Estimate linear/nonlinear combinations of parameters
- Hypotheses tests for survey data
- Estimation with linear constraints
- Goodness of fit for logistic and probit estimators
Maximum pseudolikelihood estimation
- User-defined likelihoods
- Survey characteristics automatically handled
Summary statistics
- Population and subpopulation means
- Population and subpopulation standard deviations
- Population and subpopulation proportions
- Population and subpopulation ratios
- Population and subpopulation totals
- Provide full covariance estimates across subpopulations
Summary tables
- Two-way contingency tables with tests of independence
- One-way tables
- Table describing the sampling design of survey data
Reference