Home  /  Products  /  Features  /  GMM and nonlinear regression

Nonlinear regression, GMM and other systems of equations

Generalized method of moments (GMM)

  • Linear and nonlinear models
  • Single- and multiple-equation models
  • One-step, two-step, and iterative estimators
  • Cross-sectional, time-series, and panel models
  • Easily specify panel-style instruments
  • Interactive and programmable versions
  • Robust, cluster–robust, bootstrap, jackknife, and HAC standard errors

Nonlinear least-squares regression

  • Fit an arbitrary nonlinear function
  • Enter the function directly or write a program
  • Built-in exponential, logistic, and Gompertz functions
  • Robust, cluster–robust, bootstrap, jackknife, and HAC standard errors
  • Bayesian estimation

Nonlinear seemingly unrelated regression

  • Fit a system of nonlinear equations
  • Enter the the system directly or write a program
  • Two-step or iterative feasible generalized nonlinear least squares
  • Robust, cluster–robust, bootstrap, and jackknife standard errors
  • Bayesian estimation

Demand system estimation New

  • Fit eight different demand system models
    • Cobb–Douglas
    • Linear expenditure system
    • Translog demand system
    • Generalized translog demand system
    • Almost ideal demand system (AIDS)
    • Generalized AIDS
    • Quadratic AIDS (QUAIDS)
    • Generalized QUAIDS
  • Compute expenditure and price elasticities
Watch Flexible demand systems.

Bayesian estimation

Postestimation Selector

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

Additional resources

See tests, predictions, and effects.

See New in Stata 18 to learn about what was added in Stata 18.