Panel Data Models

The panel data models in LIMDEP and NLOGIT include fixed and random effects, random parameters and latent class models for almost all nonlinear models supported by the package. There are also numerous special estimators for the linear model, such as Arellano and Bond's GMM estimator for dynamic panels and Hausman and Taylor's estimator for random effects models. No panel data operation anywhere in the program requires that the data set be balanced. Most estimators place no limit on the number of groups in the panel - the data set is already 'in the program' so it must already fit in memory. Many tools in addition to the estimation programs are also provided. For example, you can bootstrap sample groups in your panel data set, a feature we have not seen anywhere else.

Conditional Logit, Ordered Probit, Loglinear Models, Limited Dependent Variables and More

Nearly all of the models in LIMDEP and NLOGIT may be analyzed with special tools for panel data.  A partial list of the panel data models supported in LIMDEP and NLOGIT includes:

  • Linear regression model, OLS, GLS, IV
  • Probit, logit, Gompertz, complementary log log binary choice
  • Tobit, truncated regression, categorical data
  • Survival models: exponential, Weibull, lognormal, loglogistic
  • Loglinear models: Weibull, gamma, exponential, inverse Gauss
  • Stochastic frontier
  • Bivariate probit, partial observability
  • Ordered probit, ordered logit, ordered Gompertz, ordered complementary log log
  • Sample selection
  • Poisson, negative binomial, zero inflated Poisson
  • Censoring and truncation models for limited dependent variables
  • Conditional logit (multinomial logit - discrete choice)

The full range of treatments to exploit longitudinal data are supported for all models included in the program. Many different forms are provided for ordinal data, including ordered probit and logit, sample selection, bivariate models and panel data treatments such as fixed and random effects. LIMDEP and NLOGIT support all forms of models for count dependent variables, including Poisson, several forms of negative binomial, gamma, and so on as well as two part models including hurdle and zero inflation.