Benjamin Christoffersen

Benjamin Christoffersen

6 packages on CRAN

86th

Percentile

Contains functions that lets you fit dynamic hazard models using state space models. The first implemented model is described in Fahrmeir (1992) <doi:10.1080/01621459.1992.10475232> and Fahrmeir (1994) <doi:10.1093/biomet/81.2.317>. Extensions hereof are available where the Extended Kalman filter is replaced by an unscented Kalman filter and other options including particle filters. The implemented particle filters support more general state space models.

DtD

cran
73th

Percentile

Provides fast methods to work with Merton's distance to default model introduced in Merton (1974) <doi:10.1111/j.1540-6261.1974.tb03058.x>. The methods includes simulation and estimation of the parameters.

rollRegres

cran
61th

Percentile

Methods for fast rolling and expanding linear regression models. That is, series of linear regression models estimated on either an expanding window of data or a moving window of data. The methods use rank-one updates and downdates of the upper triangular matrix from a QR decomposition (see Dongarra, Moler, Bunch, and Stewart (1979) <doi:10.1137/1.9781611971811>).

parglm

cran
28th

Percentile

Provides a parallel estimation method for generalized linear models without compiling with a multithreaded LAPACK or BLAS.

mssm

cran
14th

Percentile

Provides methods to perform parameter estimation and make analysis of multivariate observed outcomes through time which depends on a latent state variable. All methods scale well in the dimension of the observed outcomes at each time point. The package contains an implementation of a Laplace approximation, particle filters like suggested by Lin, Zhang, Cheng, & Chen (2005) <doi:10.1198/016214505000000349>, and the gradient and observed information matrix approximation suggested by Poyiadjis, Doucet, & Singh (2011) <doi:10.1093/biomet/asq062>.

pre

cran
89th

Percentile

Derives prediction rule ensembles (PREs). Largely follows the procedure for deriving PREs as described in Friedman & Popescu (2008; <DOI:10.1214/07-AOAS148>), with adjustments and improvements. The main function pre() derives prediction rule ensembles consisting of rules and/or linear terms for continuous, binary, count, multinomial, and multivariate continuous responses. Function gpe() derives generalized prediction ensembles, consisting of rules, hinge and linear functions of the predictor variables.