Package: MRTSampleSizeBinary 0.1.2

Tianchen Qian

MRTSampleSizeBinary: Sample Size Calculator for MRT with Binary Outcomes

Provides a sample size calculator for micro-randomized trials (MRTs) with binary outcomes based on Cohn et al. (2023) <doi:10.1002/sim.9748>. Also provides a power calculator when the sample size is input by the user.

Authors:Eliot Wong-Toi, Thabat Dahdoul, Tianchen Qian

MRTSampleSizeBinary_0.1.2.tar.gz
MRTSampleSizeBinary_0.1.2.tar.gz(r-4.5-noble)MRTSampleSizeBinary_0.1.2.tar.gz(r-4.4-noble)
MRTSampleSizeBinary_0.1.2.tgz(r-4.4-emscripten)MRTSampleSizeBinary_0.1.2.tgz(r-4.3-emscripten)
MRTSampleSizeBinary.pdf |MRTSampleSizeBinary.html✨
MRTSampleSizeBinary/json (API)
NEWS

# Install 'MRTSampleSizeBinary' in R:
install.packages('MRTSampleSizeBinary', repos = 'https://cloud.r-project.org')
Datasets:
  • alpha_1 - Vector that defines the success probability null curve.
  • beta_1 - Vector that defines the MEE under the alternative hypothesis.
  • f_t_1 - A matrix defining the MEE under the alternative hypothesis.
  • g_t_1 - A matrix defining the success probability null curve.
  • m_matrix_1 - An example matrix for "bread" of sandwich estimator of variance.
  • p_t_1 - A vector of randomization probabilities for each time point.
  • sigma_matrix_1 - An example matrix for "meat" of sandwich estimator of variance.
  • tau_t_1 - Vector that holds the average availability at each time point.

On CRAN:

Conda:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

2.70 score 194 downloads 9 exports 28 dependencies

Last updated 1 years agofrom:838952648e. Checks:3 OK. Indexed: yes.

TargetResultLatest binary
Doc / VignettesOKMar 28 2025
R-4.5-linuxOKMar 28 2025
R-4.4-linuxOKMar 28 2025

Exports:compute_m_sigmacompute_ncpis_full_column_rankmax_sampmin_sampmrt_binary_powermrt_binary_sspower_summarypower_vs_n_plot

Dependencies:clicolorspacefansifarverggplot2gluegtableisobandlabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigR6RColorBrewerrlangscalestibbleutf8vctrsviridisLitewithr

Sample Size Calculator for Micro-Randomized Trials with Binary Outcomes

Eliot Wong-Toi, Thabat Dahdoul, Tianchen Qian

Rendered fromsample-size-calcualtor-for-mrt.Rmdusingknitr::rmarkdownon Mar 28 2025.

Last update: 2023-12-04
Started: 2021-03-04

Citation

To cite package ‘MRTSampleSizeBinary’ in publications use:

Wong-Toi E, Dahdoul T, Qian T (2023). MRTSampleSizeBinary: Sample Size Calculator for MRT with Binary Outcomes. R package version 0.1.2, https://CRAN.R-project.org/package=MRTSampleSizeBinary.

ATTENTION: This citation information has been auto-generated from the package DESCRIPTION file and may need manual editing, see ‘help("citation")’.

Corresponding BibTeX entry: 

  @Manual{,
    title = {MRTSampleSizeBinary: Sample Size Calculator for MRT with
      Binary Outcomes},
    author = {Eliot Wong-Toi and Thabat Dahdoul and Tianchen Qian},
    year = {2023},
    note = {R package version 0.1.2},
    url = {https://CRAN.R-project.org/package=MRTSampleSizeBinary},
  }

Readme and manuals

MRTSampleSizeBinary

This package provides a sample size calculator for Micro-randomized Trials with binary outcomes, based on the following article. Cohn, E. R., Qian, T., & Murphy, S. A. (2023). Sample size considerations for micro‐randomized trials with binary proximal outcomes. Statistics in Medicine.

Before using the calculator the user should have knowledge of the following:

  1. Study Setup The number of decision time points and the randomization probability, i.e. the probability of assigning the treatment at each decision time point.

  2. Availability Treatment can only be provided when an individual is available. The expected availability is the probability a person is available to receive the intervention at the decision times. You need to select a time-varying pattern for the expected availability.

  3. Success Probability Null Curve The Success Probability Null Curve at each decision time point is defined as the probability of the proximal outcome equal to 1 for available individuals who are not assigned treatment. You need to provide the trend of success probability null curve.

  4. Proximal Treatment Effect The Proximal Treatment Effect at each decision time point is defined as the mean difference in the proximal outcome between available people who are assigned a treatment versus available people who are not assigned treatment. In this work, we only consider the binary treatment. You need to provide the trend of proximal treatment effects.

The outputs one can get using this package are mainly two values, power and sample size. In both cases, you will need to input the desired significance level.

Help Manual

Help pageTopics
Vector that defines the success probability null curve.alpha_1
Vector that defines the MEE under the alternative hypothesis.beta_1
Computes "M" and "Sigma" matrices for the sandwich estimator of variance-covariance matrix.compute_m_sigma
Computes the non-centrality parameter for an F distributed random variable in the context of a MRT with binary outcome.compute_ncp
A matrix defining the MEE under the alternative hypothesis.f_t_1
A matrix defining the success probability null curve.g_t_1
Check if a matrix is full column rank.is_full_column_rank
An example matrix for "bread" of sandwich estimator of variance.m_matrix_1
Returns default maximum sample size to end power_vs_n_plot().max_samp
Compute minimum sample size.min_samp
Calculate power for binary outcome MRTmrt_binary_power
Calculate sample size for binary outcome MRTmrt_binary_ss
A vector of randomization probabilities for each time point.p_t_1
Calculate sample size at a range of power levels.power_summary
Returns a plot of power vs sample size in the context of a binary outcome MRT. See the vignette for more details.power_vs_n_plot
An example matrix for "meat" of sandwich estimator of variance.sigma_matrix_1
Vector that holds the average availability at each time point.tau_t_1