R packages

 

The latest versions of my R packages are on GitHub

https://github.com/plambertULiege

 

• cubicBsplines  -  Computation of a Cubic B-Spline Basis and Its Derivatives 
  
  Computation of a cubic B-spline basis associated to a given vector of knots. In addition to the basis, the first and second derivatives and the integral of B-splines can also be calculated using Bsplines, D1Bsplines, D2Bsplines or IBsplines.
  
  Reference
• Lambert, P. (2021). cubicBsplines: Computation of a Cubic B-Spline Basis and Its Derivatives - R package version 1.0.0. https://CRAN.R-project.org/package=cubicBsplines ; GitHub: https://github.com/plambertULiege/cubicBsplines
  
  
• DALSM  -  Nonparametric Double Additive Location-Scale Model for right- and interval-censored data   
  
  Additive models are assumed for the conditional mean and the (log of the) standard deviation. A flexible form based on P-splines is assumed for the log-hazard of the error density. The unknown functions in the model are estimated using Laplace P-splines.
  
  References
• Lambert, P. (2021). Fast Bayesian inference using Laplace approximations in nonparametric double additive location-scale models with right- and interval-censored data. Computational Statistics and Data Analysis, 161: 107250. doi:10.1016/j.csda.2021.107250
• Lambert, P. (2021). DALSM: Nonparametric Double Additive Location-Scale Model - R package version 0.9.1. https://CRAN.R-project.org/package=DALSM ; GitHub: https://github.com/plambertULiege/DALSM
  
  
• degross  -   Density Estimation from GRouped Summary Statistics 
  
  The degross R-package enables to estimate a density from grouped (tabulated) summary statistics evaluated in each of the big bins (or classes) partitioning the support of the variable. These statistics include class frequencies and central moments of order one up to four.
  
  References
• Lambert, P. (2023). Nonparametric density estimation and risk quantification from tabulated sample moments. Insurance: Mathematics and Economics, 108: 177-189. doi:10.1016/j.insmatheco.2022.12.004 (Preprint) 
• Lambert, P. (2021). degross: Density Estimation from GROuped Summary Statistics - R package version 0.9.0. https://CRAN.R-project.org/package=degross ; GitHub: https://github.com/plambertULiege/degross

 

• ordgam  -  Additive Model for Ordinal Data using Laplace P-Splines 
  
  The ordgam package enables to fit an additive proportional odds model to ordinal data.
  The combination of Laplace approximations and of Bayesian P-splines (named LPS) enable fast and flexible inference in a Bayesian framework. Particular attention is paid to non-penalized parameters for which the Laplace approximation to the posterior distribution may be too coarse.
  
  References
  
  • Lambert, P. and Gressani, O. (2023). Penalty parameter selection and asymmetry corrections to Laplace approximations in Bayesian P-splines models. Statistical Modelling, 23(5-6): 409-423. 2023. doi:10.1177/1471082X231181173
  • Lambert, P. (2023). ordgam: Additive Model for Ordinal Data using Laplace P-Splines - R package version 0.9.1.  https://CRAN.R-project.org/package=ordgam ; GitHub: https://github.com/plambertULiege/ordgam
    
    
• tvcure  - Additive cure survival model with time-varying covariates 
  
  The tvcure package enables to fit of a double additive cure survival model with time-varying covariates. The additive terms in the long- and short-term survival submodels, modelling the cure probability and the event timing for susceptible units, are estimated using Laplace P-splines.
  
  References
• Lambert, P. and Kreyenfeld, M. (2025). Time-varying exogenous covariates with frequently changing values in double additive cure survival model: an application to fertility. Journal of the Royal Statistical Society: Series A. doi:10.1093/jrsssa/qnaf035.
• Lambert, P. (2025). tvcure:  Additive cure survival model with time-varying covariates - R-package version 0.6.6. Github:  https://github.com/plambertULiege/tvcure.
  
  

• blapsr  -  Bayesian Inference with Laplace Approximations and P-Splines 
   (Developed by O. Gressani and P. Lambert  ; maintained by O. Gressani)
  
  The blapsr package consists in a set of routines that can be used for analysis in survival models and (generalized) additive models. The methodology is based on the combination of Bayesian P-splines for flexible estimation of smooth functions and Laplace approximations to (selected) posterior distributions.
  
  References
• Gressani, O. and Lambert, P. (2021). Laplace approximation for fast Bayesian inference in generalized additive models based on P-splines. Computational Statistics and Data Analysis, 154: 107088. doi:10.1016/j.csda.2020.107088
• Gressani, O. and Lambert P. (2018). Fast Bayesian inference using Laplace approximations in a flexible promotion time cure model based on P-splines. Computational Statistics and Data Analysis, 124: 151-167. doi:10.1016/j.csda.2018.02.007
• Gressani O. and Lambert, P. (2021). blapsr: Bayesian Inference with Laplace Approximations and P-Splines - R package version 0.6.1.  https://CRAN.R-project.org/package=blapsr ; GitHub: https://github.com/oswaldogressani/blapsr
  
  
• stable  -  Probability Functions and Generalized Regression Models for Stable Distributions 
  (Created by P. Lambert and J.K. Lindsey in 1995 ; Currently maintained by Bruce Swihart)
  
  Density, distribution, quantile and hazard functions of a stable variate ; generalized regression models for the parameters of a stable distribution.
  
  References
• Lambert, P. and Lindsey, J.K. (1999). Analysing financial returns using  regression models based on non-symmetric stable distributions.  Applied Statistics, 48: 409-424. doi:10.1111/1467-9876.00161
• Lambert, P. and Lindsey, J.K.(1995). stable : Probability Functions and Generalized Regression Models for Stable Distributions. R package version 1.1.6 (currently maintained by Bruce Swihart).  https://CRAN.R-project.org/package=stable