Model Estimation and Data Analysis: Robust, Semiparametric & Nonparametric Estimation

LIMDEP and NLOGIT offer a variety of procedures of robust, semiparametric and nonparametric estimation and inference tools.

Robust Covariance Matrix Estimators

  • Cluster based asymptotic covariance matrices
  • Bootstrapping standard errors for any estimator
  • White and heteroscedasticity corrected estimators
  • Newey-West estimators
  • Choice based sampling discrete choice estimators
  • Jackknife estimators of standard errors for any estimator

Robust Estimators

  • GMM estimation for user specified models
  • Kernel density estimation
  • Spectral density estimation
  • Random parameters models
  • Kernel weights for estimation

Non- and Semiparametric Estimators

  • Least absolute deviations linear regression
  • Quantile regression, linear or count
  • Maximum score for binary choice
  • Klein and Spady estimator for binary choice
  • Nonparametric, kernel density regression
  • LOWESS regression

Stratified Data

  • Cluster corrections
  • Stratification and clustering
  • Finite population weights

Robust Tests

  • Rank correlation
  • Coefficient of concordance
  • Kolmogorov-Smirnov
  • Normality test - chi-squared
  • Box-Pierce and Box-Ljung
  • Poe combinatorial comparison

Multiple Imputation

  • Up to 30 variables imputed simultaneously
  • Six types of imputation procedures for
    • Continuous variables using multiple regression
    • Binary variables using logistic regression
    • Count variables using Poisson regression
    • Likert scale (ordered outcomes) using ordered probit
    • Fractional (proportional outcome) using logistic regression
    • Unordered multinomial choice using multinomial logit
  • No duplication of the base data set
  • All models supported by built in procedures
  • Any model written by the user with GMME, MAXIMIZE, NLSQ, etc.
  • Estimate any number of models using each imputed data set