Capabilities
LIMDEP and NLOGIT are integrated statistical analysis software programs. They contain a large array of tools for data analysis, data management and model building from simple linear regression to maximum likelihood estimation of nonlinear systems of equations, with many extensions and variations. Nearly all techniques used in modern empirical investigation are provided.
Model Estimation & Data Analysis
Nearly 200 model formulations for continuous, discrete, limited and censored dependent variables are provided, including:- Linear regression
- Robust estimation
- Nonlinear and loglinear regression
- Probit and logit models for binary choice
- Ordered choice models
- Multinomial choice
- Censoring and truncation
- Sample selection models
- Quantile regression (linear and count)
- Poisson and negative binomial models for count data
- Stochastic frontier and DEA
- Time series models
- Panel data models
Statistical Analysis
Programming language allows extensions of supported estimators:- Model estimation
- Testing and restrictions
- Post estimation analysis
- Simulations
- Partial effects
- Oaxaca decomposition
- Delta and Krinsky/Robb methods
Panel Data Models
All of the linear and nonlinear models may be analyzed with special forms of panel data, including:- Fixed and random effects linear models
- Nonlinear fixed effects models
- Random effects models
- Random parameters - mixed models
- Latent class models
Statistics & Graphics
Descriptive statistics and graphical analysis tools include:- Descriptive statistics for cross sections and panels
- Tables of means and quantiles
- Time series
- Spectral density
- Graphics tools
- Kernel density
- Discriminant analysis
- Contour plots
Count Data
The widest range of specifications for count data of any package is provided, including several newly developed models:- Poisson and negative binomial models
- New specifications for NB models
- Gamma, generalized Poisson, Polya-Aeppli
- Zero inflation and hurdle
- Fixed and random effects
- Latent class
- Quantile Poisson regression
Programming
Programming language including matrix and data manipulation commands is provided for building new estimators:SFA & DEA
All forms of the stochastic frontier model are provided:- Fixed and random effects
- True fixed and random effects
- Latent class stochastic frontier
- Battese and Coelli
- Heteroscedasticity
- Technical inefficiency estimation
- Data envelopment analysis (This is the only package with both SFA and DEA.)
Discrete Choice in LIMDEP
Discrete choice estimators for binary, multinomial, ordered, count and multivariate discrete data are provided:- Probit and logit models for binary choice
- Ordered choice including univariable, bivariate, hierarchical and sample selection
- Panel data
- Multinomial logit
- Count data models
Multinomial Choice in NLOGIT
NLOGIT contains all of LIMDEP plus numerous extensions of the multinomial choice models that do not appear in LIMDEP, including:- Data analysis
- Model estimation
- Mixed (random parameters) logit model
- Generalized mixed logit
- Estimation in WTP space
- Multinomial probit model
- Latent class model
- Error components (RE) logit model
- Random regret MNL
- Dynamic random effects MNL model
- Generalized nested logit model
- Model specification
- Model simulation
Time Series Analysis
A range of estimators for time series are provided including:- ARMAX models
- GARCH and GARCH-in-mean models
- Spectral density estimation
- ACF and PACF
- Phillips-Perron tests
- Newey-West estimator