Nonparametric kernel regression 
- Multiple covariates supported
- Continuous covariates
(8 kernels available)
- Discrete covariates
(2 kernels available)
- Techniques
- local constant regression
- local linear regression
- Point estimates with SEs and CIs
- Derivative estimates with SEs and CIs
- Automatic optimal bandwidth selection
- Interface to margins for advanced
inference
- Estimates of population-averaged and
subpopulation-averaged means and effects
- Fully conditional means and effects at
any specified values of the covariates
- Confidence intervals
- Tests
- Graphs via marginsplot
Nonparametric series regression
- Multiple covariates supported
- Continuous covariates
- Discrete covariates
- Series approximation with series
- B-splines basis
- Piecewise polynomial splines
- Polynomials
- Additively separable nonparametric models
- Semiparametric regression models
- Optimal knot and polynomial selection
- cross-validation
- generalized cross-validation
- AIC
- BIC
- Mallows's Cp
- Interface to margins
- Estimates of population and subpopulation means and effects
- Fully conditional means and effects
- Confidence intervals
- Graphs via marginsplot
Spline basis function generation New
- B-spline
- Piecewise polynomial splines
- Restricted cubic splines
- Flexible knot selection
- number of knots
- knot list
- knots matrix
Nonparametric correlation coefficients
- Spearman’s rank order
- Kendall’s rank order
Survival analysis
- Kaplan–Meier curves
- Nelson–Aalen curves
- Logrank and other tests of equality
Multivariate analysis
- KNN discriminant analysis
Causal inference/Treatment effects
- Nearest-neighbor matching
- Propensity-score matching
Additional resources
See New in Stata 18 to learn about what was added in Stata 18.
;)
