Learn R Programming

`pammtools`: Piece-Wise Exponential Additive Mixed Modeling Tools

Installation

Install from CRAN or GitHub using:

# CRAN
install.packages("pammtools")
# Development version
remotes::install_github("adibender/pammtools")

Overview

pammtools facilitates the estimation of Piece-wise exponential Additive Mixed Models (PAMMs) for time-to-event data. PAMMs can be represented as generalized additive models and can therefore be estimated using GAM software (e.g. mgcv), which, compared to other packages for survival analysis, often offers more flexibility w.r.t. to the specification of covariate effects (e.g. non-linear, time-varying effects, cumulative effects, etc.). The package supports single-event analysis, left-truncation, recurrent events, competing risks and multi-state models.

To get started, see the Articles section.

Copy Link

Version

Install

install.packages('pammtools')

Monthly Downloads

4,924

Version

0.8.1

License

MIT + file LICENSE

Maintainer

Andreas Bender

Last Published

August 25th, 2026

Functions in pammtools (0.8.1)

Add transition probabilities

Extract cumulative coefficients (cumulative hazard differences)

Calculate (or plot) cumulative effect for all time-points of the follow-up

Extract model coefficients on the scale of the design matrix

Extract variables from the left-hand-side of a formula

Extract transition information from different objects

(Cumulative) (Step-) Hazard plots.

Expand time-dependent covariates to functionals

Construct or extract data that represents a lag-lead window

Extract plot information for all special model terms

Extract the (Bayesian) covariance matrix of the model coefficients

Calculate simulation based confidence intervals

geom_stepribbon

Step ribbon plots.

Extract variables from the left-hand-side of a formula

get_event_types

Extract event types

Point hazard predictor (backend primitive)

Information on intervals in which times fall

Plot lag-lead windows

Plot Normal QQ plots for random effects

Plot 1D (smooth) effects

Extract variables from the left-hand-side of a formula

get_smooth_terms

Enumerate plottable univariate smooth terms of a fitted model

Calculate survival probabilities

Extract the partial effect of a single smooth curve

get_cumu_hazard

Calculate cumulative hazard

Obtain interval break points

get_term_legacy

Extract a partial effect for models without a $smooth component

Visualize effect estimates for specific covariate combinations

Extract variables from the left-hand-side of a formula

Calculate CIF for one cause

Extract the partial effects of univariate smooth model terms

Forrest plot of fixed coefficients

Plot tensor product effects

Build the subject-by-interval prediction grid used for IC imputation

Analytic hazard with confidence interval (coefficient models)

gg_state_occupation

Plot state occupation probabilities

interval_censored

Detect, parse and transform interval-censored survival data

Create start/end times and interval information

Plot smooth 1d terms of gam objects

Fit a competing-risks PAMM to interval-censored data via multiple imputation

Checks if data contains time-dependent covariates

Create design matrix from a suitable object

Draw event times and causes for interval-censored competing-risks subjects

Construct a data frame suitable for prediction

Create nested data frame from data with time-dependent covariates

pamm_ic_pooling

Pooling of multiple-imputation PAMM fits

impute_ic_times

Draw event times for interval-censored subjects from the conditional hazard

Time until nuclear power plant construction in different regions.

Calculate the modus

Create design matrix from a suitable object

Parse the factor level from a factor-by smooth label

pammtools: Piece-wise exponential additive mixed modeling tools.

predictSurvProb.pamm

S3 method for pamm objects for compatibility with package pec

Fit a piece-wise exponential additive model

Fit a PAMM to interval-censored data via multiple imputation

prep_concurrent

Extract information on concurrent effects

reconstruct_intlen

Reconstruct intlen from time variable and stored cut points

Extract interval information and median/modus values for covariates

Pool a list of (stripped) imputation fits into a pooled summary object

Survival data of critically ill ICU patients

reconstruct_cutpoints

Ensure all breakpoints are present in newdata for cumulative calculations

Generate a sequence over the range of a vector

Resolve requested terms against the model's plottable smooths

Draw random numbers from piece-wise exponential distribution.

Draw hazard trajectories from a model's sampling distribution

Simulated data with cumulative effects

Draw coefficients from their approximate posterior distribution

Simulate survival times from the piece-wise exponential distribution

Simulate data for competing risks scenario

smooth.construct.fdl.smooth.spec

New basis for penalized lag selection

Extract fixed coefficient table from model object

Extract 2d smooth objects in tidy format.

Extract random effects in tidy data format.

Function to transform data without time-dependent covariates into piece-wise exponential data format

warn_about_new_time_points

Warn if new t_j are used

smooth_term_rows

Turn a single mgcv smooth into zero or more curve specifications

split_data_multistate

Split data to obtain recurrent event data in PED format

Extract 1d smooth objects in tidy data format.

Formula specials for defining time-dependent covariates

Slim down a fitted PAMM for storage inside a pamm_ic object

Time until staphylococcus aureaus infection in children, with possible recurrence

stop_if_undergrouped_for_cumulation

Guard against silently-wrong cumulative results from mis-grouped newdata

warn_about_new_time_points.glm

Warn if new t_j are used

Stomach area tumor data

Extract information of the sample contained in a data set

Add survival probability estimates

Add transition probabilities confidence intervals

Add time-dependent covariate to a data set

Add predicted (cumulative) hazard to data set

as.data.frame.crps

Transform crps object to data.frame

add_counterfactual_transitions

Add counterfactual observations for possible transitions

Embeds the data set with the specified (relative) term contribution

add_inspections

Turn exact event times into interval-censored observations

Add cumulative incidence function to data

Calculate confidence intervals

compute_cumu_diff

Calculate difference in cumulative hazards and respective standard errors

dplyr verbs for ped-objects

Competing risks trafo

Time-dependent covariates of the patient data set.

Transform data to piece-wise exponential data (PED)

Create a data frame from all combinations of data frames

Create matrix components for cumulative effects

A formula special used to handle cumulative effect specifications