bsw: Fitting a log-binomial model using the...

In BSW: Fitting a Log-Binomial Model Using the Bekhit–Schöpe–Wagenpfeil (BSW) Algorithm

Fitting a log-binomial model using the Bekhit-Schöpe-Wagenpfeil (BSW) algorithm

Description

bsw() fits a log-binomial model using a modified Newton-type algorithm (BSW algorithm) for solving the maximum likelihood estimation problem under linear inequality constraints.

Usage

bsw(formula, data, maxit = 200L, conswitch = 1)

Arguments

formula	An object of class "formula" (or one that can be coerced to that class): a symbolic description of the model to be fitted.
data	A data frame containing the variables in the model.
maxit	A positive integer giving the maximum number of iterations.
conswitch	Specifies how the constraint matrix is constructed: 1 (default) Generates all possible combinations of minimum and maximum values for the predictors (excluding the intercept), resulting in 2^{m-1} constraints. This formulation constrains model predictions within the observed data range, making it suitable for both risk factor identification and prediction (prognosis). 0 Uses the raw design matrix x as the constraint matrix, resulting in n constraints. This is primarily suitable for identifying risk factors, but not for prediction tasks, as predictions are not bounded to realistic ranges.

Value

An object of S4 class "bsw" containing the following slots:

call	An object of class "call".
formula	An object of class "formula".
coefficients	A numeric vector containing the estimated model parameters.
iter	A positive integer indicating the number of iterations.
converged	A logical constant that indicates whether the model has converged.
y	A numerical vector containing the dependent variable of the model.
x	The model matrix.
data	A data frame containing the variables in the model.

Author(s)

Adam Bekhit, Jakob Schöpe

References

Wagenpfeil S (1996) Dynamische Modelle zur Ereignisanalyse. Herbert Utz Verlag Wissenschaft, Munich, Germany

Wagenpfeil S (1991) Implementierung eines SQP-Verfahrens mit dem Algorithmus von Ritter und Best. Diplomarbeit, TUM, Munich, Germany

Examples

set.seed(123)
x <- rnorm(100, 50, 10)
y <- rbinom(100, 1, exp(-4 + x * 0.04))
fit <- bsw(formula = y ~ x, conswitch = 1, data = data.frame(y = y, x = x))
summary(fit)

BSW documentation built on Nov. 5, 2025, 6:26 p.m.