MyNixOS website logo
Description

Marginal Structural Models with Latent Class Growth Analysis of Treatment Trajectories.

Implements marginal structural models combined with a latent class growth analysis framework for assessing the causal effect of treatment trajectories. Based on the approach described in "Marginal Structural Models with Latent Class Growth Analysis of Treatment Trajectories" Diop, A., Sirois, C., Guertin, J.R., Schnitzer, M.E., Candas, B., Cossette, B., Poirier, P., Brophy, J., Mésidor, M., Blais, C. and Hamel, D., (2023) <doi:10.1177/09622802231202384>.

R-package-trajmsm

The trajmsm package is inspired by the paper "Marginal Structural Models with Latent Class Growth Analysis of Treatment Trajectories," published in Statistical Methods for Medical Research. Read the paper.

Latent Class Growth Analysis (LCGA) is increasingly used to summarize longitudinal treatment data into distinct groups. However, combining LCGA with standard methods like Cox proportional hazards models often fails to control time-dependent confounding due to covariates acting as both confounders and mediators. Our solution employs LCGA to classify individuals into latent classes based on their medication adherence patterns. We then utilize a Marginal Structural Model (MSM) to relate outcomes to these groups. The key parameter is nonparametrically defined, projecting the true MSM onto the selected working model.

Integrating LCGA with MSM (termed LCGA-MSM) offers an effective way to describe treatment adherence and control time-dependent confounding. Common methods to estimate MSM parameters include Inverse Probability Weighting (IPW), which creates a pseudo-population for balanced treatment groups. In longitudinal settings, IPW adjusts for time-varying covariates impacted by previous exposures and selection bias.

In this initial version of trajmsm, we estimate LCGA-MSM parameters using IPW, g-computation, and pooled Longitudinal Targeted Maximum Likelihood Estimation (LTMLE). We also introduce an extension for time-dependent outcomes, termed LCGA-History-Restricted MSM (LCGA-HRMSM), with the same three estimators.

For access to the R codes, visit our GitHub repository.

For additional insights on trajectory analysis, check out the trajectory_analysis repository.

Metadata

Version

0.1.0

License

Unknown

Platforms (77)

    Darwin
    FreeBSD
    Genode
    GHCJS
    Linux
    MMIXware
    NetBSD
    none
    OpenBSD
    Redox
    Solaris
    WASI
    Windows
Show all
  • aarch64-darwin
  • aarch64-freebsd
  • aarch64-genode
  • aarch64-linux
  • aarch64-netbsd
  • aarch64-none
  • aarch64-windows
  • aarch64_be-none
  • arm-none
  • armv5tel-linux
  • armv6l-linux
  • armv6l-netbsd
  • armv6l-none
  • armv7a-darwin
  • armv7a-linux
  • armv7a-netbsd
  • armv7l-linux
  • armv7l-netbsd
  • avr-none
  • i686-cygwin
  • i686-darwin
  • i686-freebsd
  • i686-genode
  • i686-linux
  • i686-netbsd
  • i686-none
  • i686-openbsd
  • i686-windows
  • javascript-ghcjs
  • loongarch64-linux
  • m68k-linux
  • m68k-netbsd
  • m68k-none
  • microblaze-linux
  • microblaze-none
  • microblazeel-linux
  • microblazeel-none
  • mips-linux
  • mips-none
  • mips64-linux
  • mips64-none
  • mips64el-linux
  • mipsel-linux
  • mipsel-netbsd
  • mmix-mmixware
  • msp430-none
  • or1k-none
  • powerpc-netbsd
  • powerpc-none
  • powerpc64-linux
  • powerpc64le-linux
  • powerpcle-none
  • riscv32-linux
  • riscv32-netbsd
  • riscv32-none
  • riscv64-linux
  • riscv64-netbsd
  • riscv64-none
  • rx-none
  • s390-linux
  • s390-none
  • s390x-linux
  • s390x-none
  • vc4-none
  • wasm32-wasi
  • wasm64-wasi
  • x86_64-cygwin
  • x86_64-darwin
  • x86_64-freebsd
  • x86_64-genode
  • x86_64-linux
  • x86_64-netbsd
  • x86_64-none
  • x86_64-openbsd
  • x86_64-redox
  • x86_64-solaris
  • x86_64-windows