Stochastic Frontier Models

• • New parametric specifications
  • Normal-Rayleigh
  • New FIML estimator for sample selection correction
  • Sample selection with panel data
  • Partially inefficient latent class stochastic frontier model

Panel Data Stochastic Frontier Models

• • Rayleigh model
  • Belotti and Ilardi partial differences
  • True fixed and random effects
  • Wikstrom method of moments
  • Generalized true random effects

New Partial Effects and Simulation Tools

• • New graphical devices
  • Transition matrices for categorical variables
  • Krinsky and Robb method for standard errors
  • Extended to more models

Expanded Graphics

Histograms

• • Overlay histograms with box plots or kernel density estimators
  • Group up to 4 histograms

Box Plots

• • Up to 40 plots in one figure
  • New BOXPLOTS command
  • Simultaneous plots

Bubble Plots

Kernel Density Estimator

• • Several new specifications for plotting kernel density estimators
  • Simultaneous plots

Treatment Effects Procedures

• • Endogenous treatment effects
  • FIML estimation for probit, ordered probit, Poisson and negative binomial

New Tools for Estimation and Inference

New Analysis Tools

• • Over 30 new CREATE functions for panel data transformations
  • Dozens of new functions for CALCULATE and MATRIX
  • New random number generators

More Models and Features

• • Cluster covariance matrices for all models
  • Inverse hyperbolic sine model
  • Fractional regression for cross section and panel data
  • New panel data functions for MAXIMIZE

Data Descriptive Devices

• • Obtain separate strata means for stratified data
  • New commands for correlation matrices
  • New TABLE command for descriptive statistics by strata
  • New commands for quantiles and frequencies
  • New Cronbach’s alpha correlation device

Character Data

• • Observation labels
  • Labellists
  • Observation tags

Loglinear Models

• • Generalized beta of the second kind
  • Generalized gamma model

Enhanced EXECUTE and Procedures

• • New specifications for bootstrap and jackknife iterations
  • Block bootstrap for panel data

Comparing Alternative Specifications of a Model