Repository files navigation

MOSS performs ensemble machine learning and Targeted Maximum Likelihood(TMLE) to estimate the counter-factual marginal survival functions,while non-parametrically adjusting for measured confounding. TMLEapproach is employed to create a doubly robust and semi-parametricallyefficient estimator. Simultaneous confidence bands of the entire curveis also available for inference. User can specify what kind of staticintervention on treatment (exposure).

The following comparable methods are also included in the package foryou to easily compare methods: - Inverse censoring probability weighted(IPCW) - Locally efficient one-step estimator (estimating equationmethods)

install.packages('MOSS')devtools::install_github('wilsoncai1992/MOSS')

• To see all available package documentation:

?MOSShelp(package='MOSS')

The data input of all methods in the package should be anRdata.frame in the following survival long data format:

#   ID W A T.tilde delta# 1  1 0 0      95     1# 2  2 1 1       1     0# 3  3 0 0     215     1# 4  4 1 1      15     1# 5  5 0 0      73     1# 6  6 0 0      15     1

1. perform SuperLearner fit of the conditional survival function offailure event, conditional survival function of censoring event,propensity scores (initial_sl_fit)
2. perform TMLE adjustment of the conditional survival fit(MOSS_hazard)
3. simultaneous confidence band (compute_simultaneous_ci)

To citeMOSS in publications, please use:

Cai W, van der Laan MJ (2019+).One-step TMLE for time-to-eventoutcomes. Working paper.

This software is distributed under the GPL-2 license.

Feedback, bug reports (and fixes!), and feature requests are welcome;file issues or seek supporthere.