SemiParSampleSel-package: Semiparametric Sample Selection Modelling with Continuous or...

In SemiParSampleSel: Semi-Parametric Sample Selection Modelling with Continuous or Discrete Response

Description

SemiParSampleSel provides a function for fitting continuous and discrete response (copula) sample selection models with parametric and nonparametric predictor effects. Several bivariate copula distributions are supported. The dependence parameter of the copula distribution as well as the shape and dispersion parameters of the outcome distribution can be specified as functions of semiparametric predictors as well. Smoothness selection is achieved automatically and interval calculations are based on a Bayesian approach.

Details

SemiParSampleSel provides a function for flexible sample selection modelling with continuous or discrete response. The underlying representation and estimation of the model is based on a penalized regression spline approach, with automatic smoothness selection. The numerical routine carries out function minimization using a trust region algorithm from the package trust in combination with an adaptation of a low level smoothness selection fitting procedure from the package mgcv.

SemiParSampleSel supports the use of many smoothers as extracted from mgcv. Scale invariant tensor product smooths are not currently supported. Estimation is by penalized maximum likelihood with automatic smoothness selection by approximate Un-Biased Risk Estimator (UBRE) score, which can also be viewed as an approximate AIC. The depedence between the selection and outcome equations is modelled through the use of copulas.

Confidence intervals for smooth components and nonlinear functions of the model parameters are derived using a Bayesian approach. Approximate p-values for testing individual smooth terms for equality to the zero function are also provided and based on the approach implemented in mgcv. Functions plot.SemiParSampleSel and summary.SemiParSampleSel extract such information from a fitted SemiParSampleSel object. Model/variable selection is also possible via the use of shrinakge smoothers or information criteria.

Function aver calculates the average outcome corrected for non-random sample selection.

If it makes sense, the dependence parameter of the copula function as well as the shape and dispersion parameters of the outcome distribution can be specified as functions of semiparametric predictors.

Author(s)

Giampiero Marra (University College London, Department of Statistical Science), Rosalba Radice (Birkbeck, University of London, Department of Economics, Mathematics and Statistics), Malgorzata Wojtys (University of Plymouth, School of Computing and Mathematics), Karol Wyszynski (University College London, Department of Statistical Science)

Maintainer: Giampiero Marra [e-mail]

References

Marra G. and Radice R. (2013), Estimation of a Regression Spline Sample Selection Model. Computational Statistics and Data Analysis, 61, 158-173.

Wojtys M., Marra G. and Radice R. (in press), Copula Regression Spline Sample Selection Models: The R Package SemiParSampleSel. Journal of Statistical Software.

See Also

SemiParSampleSel

SemiParSampleSel documentation built on May 2, 2019, 6:35 a.m.