Take full advantage of the extra information that panel data provide, while simultaneously handling the peculiarities of panel data. Study the time-invariant features within each panel, the relationships across panels, and how outcomes of interest change over time. Fit linear models or nonlinear models for binary, count, ordinal, censored, or survival outcomes with fixed-effects, random-effects, or population-averaged estimators. Fit dynamic models or models with endogeneity. And much more.


LINEAR FIXED- AND RANDOM-EFFECTS MODELS

  • Linear model with panel-level effects and i.i.d. errors
  • Linear model with panel-level effects and AR(1) errors
  • GLS and ML estimators
  • Difference in differences (DID) estimation
  • Heterogeneous DID estimation
  • Robust and cluster–robust standard errors
  • Multiway clustering
  • HC2 with degrees-of-freedom adjustment
  • Wildbootstrap confidence intervals and inference
  • Multiple imputation
  • Bayesian estimation

 

RANDOM-EFFECTS REGRESSION FOR BINARY, ORDINAL, CATEGORICAL, AND COUNT-DEPENDENT VARIABLES

  • Probit
  • Logistic regression
  • Complementary log-log regression
  • Ordered logistic regression
  • Ordered probit regression
  • Multinomial logistic regression
  • Interval regression
  • Tobit
  • Poisson regression (Gaussian or gamma random-effects)
  • Negative binomial regression
  • Robust standard errors with (*) regressions
  • Bayesian estimation

CONDITIONAL FIXED-EFFECTS REGRESSION FOR BINARY, CATEGORICAL, AND COUNT-DEPENDENT VARIABLES

  • Multinomial logistic regression
  • Logit regression
  • Poisson regression
  • Negative binomial regression

 

TWO-STAGE LEAST-SQUARES PANEL-DATA ESTIMATORS

  • Between-2SLS estimator
  • Within-2SLS estimator
  • Balestra–Varadharajan–Krishnakumar G2SLS estimator
  • Baltagi EC2SLS estimator
  • All with balanced or exogenously balanced panels
  • Robust and cluster–robust standard errors
    • Multiway clustering
    • HC2 with degrees-of-freedom adjustment
    • Wildbootstrap confidence intervals and inference

 

RANDOM-EFFECTS REGRESSION WITH SAMPLE SELECTION

 

RANDOM-EFFECTS EXTENDED REGRESSION MODELS

  • Combine endogeneity, Heckman-style selection, and treatment effects
  • Linear regression
  • Interval regression, including tobit
  • Probit regression
  • Ordered probit regression
  • Exogenous or endogenous treatment assignment
    • Binary treatment–untreated/treated
    • Ordinal treatment levels–0 doses, 1 dose, 2 doses, etc.
  • Endogenous selection using probit or tobit
  • All standard postestimation commands available, including predict and margins

 

REGRESSORS CORRELATED WITH INDIVIDUAL-LEVEL EFFECTS

  • Hausman–Taylor instrumental-variables estimators
  • Amemiya–MaCurdy instrumental-variables estimators
  • Robust and cluster–robust standard errors
    • Multiway clustering
    • HC2 with degrees-of-freedom adjustment
    • Wildbootstrap confidence intervals and inference

 

Panel-corrected standard errors (PCSE) for linear cross-sectional models

 

Swamy’s random-coefficients regression

 

STOCHASTIC FRONTIER MODELS

  • Time-invariant model
  • Time-varying decay model
  • Battese–Coelli parameterization of time effects
  • Estimates of technical efficiency and inefficiency

SPECIFICATION TESTS

  • Hausman specification test
  • Breusch and Pagan Lagrange multiplier test for random effects

PANEL-DATA UNIT-ROOT TESTS

  • Im–Pesaran–Shin
  • Levin–Lin–Chu
  • Hadri
  • Breitung
  • Fisher-type (combining p-values)
  • Harris–Tzavalis

© Copyright 1996–2023 StataCorp LLC. All rights reserved.

SUMMARY STATISTICS AND TABULATIONS

  • Statistics within and between panels
  • Pattern of panel participation

PANEL-DATA LINE PLOTS

  • Graphs by panel
  • Overlaid panels

GEE ESTIMATION OF GENERALIZED LINEAR MODELS (GLMS)

  • Six distribution families
  • Nine links
  • Seven correlation structures
  • Specific models include:
    • Probit model with panel-correlation structure
    • Poisson model with panel-correlation structure

LINEAR DYNAMIC PANEL-DATA ESTIMATORS

  • Arellano–Bond estimator
  • Arellano–Bover/Blundell–Bond system
  • Opening, closing, and embedded gaps
  • Serially correlated disturbances
  • Complete control over instrument list
  • Predetermined variables
  • Tests for autocorrelation and of overidentifying restrictions

RANDOM-EFFECTS PARAMETRIC SURVIVAL MODELS

  • Weibull, exponential, lognormal, loglogistic, or gamma models
  • Robust and cluster–robust standard errors
    • Multiway clustering
    • HC2 with degrees-of-freedom adjustment
    • Wildbootstrap confidence intervals and inference
  • Bayesian estimation

 

MULTILEVEL MIXED-EFFECTS MODELS

 

POPULATION-AVERAGED REGRESSION

  • Complementary log-log regression
  • Generalized estimating equations
  • Logit regression
  • Negative binomial regression
  • Poisson regression
  • Probit regression
  • Linear models regression

STATIONARITY TESTS

  • Panel-data unit-root tests
  • Cointegration tests for nonstationary process
    • Kao, Pedroni, or Westerlund tests
    • Include panel-specific means or panel-specific time trends

 

POSTESTIMATION SELECTOR

  • View and run all postestimation features for your command
  • Automatically updated as estimation commands are run

 

FACTOR VARIABLES

  • Automatically create indicators based on categorical variables
  • Form interactions among discrete and continuous variables
  • Include polynomial terms
  • Perform contrasts of categories/levels
Watch Introduction to Factor Variables in Stata tutorials

MARGINAL ANALYSIS

  • Estimated marginal means
  • Marginal and partial effects
  • Average marginal and partial effects
  • Least-squares means
  • Predictive margins
  • Adjusted predictions, means, and effects
  • Works with multiple outcomes simultaneously
  • Contrasts of margins
  • Pairwise comparisons of margins
  • Profile plots
  • Graphs of margins and marginal effects
Watch Introduction to margins in Stata tutorials
Watch Profile plots and interaction plots in Stata tutorials