Type:	Package
Title:	Mander and Thompson Designs
Version:	0.1.2
Date:	2024-11-01
Description:	Implements Mander & Thompson's (2010) <doi:10.1016/j.cct.2010.07.008> methods for two-stage designs optimal under the alternative hypothesis for phase II [cancer] trials. Also provides an implementation of Simon's (1989) <doi:10.1016/0197-2456(89)90015-9> original methodology and allows exploration of the operating characteristics of sub-optimal designs.
Language:	en-GB
License:	GPL (≥ 3)
Encoding:	UTF-8
URL:	https://github.com/openpharma/mtdesign
BugReports:	https://github.com/openpharma/mtdesign/issues
RoxygenNote:	7.3.2
Imports:	dplyr, futile.logger, ggplot2, magrittr, methods, Rcpp, rlang, tibble, tidyr
LinkingTo:	Rcpp, BH
Suggests:	parallel, testthat (≥ 3.0.0), withr
Config/testthat/edition:	3
NeedsCompilation:	yes
Packaged:	2024-11-05 12:07:07 UTC; kirkpatj
Author:	John Kirkpatrick [aut, cre]
Maintainer:	John Kirkpatrick <mtdesign@puzzledface.net>
Repository:	CRAN
Date/Publication:	2024-11-05 14:10:15 UTC

Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

Arguments

Value

The result of calling 'rhs(lhs)'.

Augment a grid of candidate designs with type 1 and type 2 error probabilities, expected sample sizes and probabilities of early termination

Description

Augment a grid of candidate designs with type 1 and type 2 error probabilities, expected sample sizes and probabilities of early termination

Usage

augmentGrid(d, parallel = TRUE, cores = NA, minChunkSize = 1e+05)

Arguments

Value

an augmented grid tibble

Usage Notes

Regardless of the value of 'parallel', parallelisation is only used if the size of the grid is greater than <code>chunkSize</code>. If paralellisation is requested and needed, an exception is thrown if the parallel package is not available.

Examples

x <- createGrid(p0 = 0.1, p1 = 0.30, alpha = 0.1, beta = 0.1, nMin = 24, nMax = 32) %>%
  augmentGrid(parallel = FALSE)

Create a grid of candidate designs

Description

Create a grid of candidate designs

Usage

createGrid(
  p0,
  p1,
  alpha = 0.1,
  beta = NA,
  power = ifelse(is.na(beta), 0.9, 1 - beta),
  nMin = NA,
  nMax = NA,
  mander = TRUE
)

Arguments

Value

a tibble. See Usage notes for a list and description of columns.

Examples

# Standard use for a Simon's 2-stage design
x <- createGrid(p0 = 0.1, p1 = 0.5, alpha = 0.1, beta = 0.1, mander = FALSE)
# Custom search bounds for a Mander & Thompson design
y <- createGrid(p0 = 0.1, p1 = 0.4, alpha = 0.1, beta = 0.1, nMin = 20, nMax = 30)

Finds optimal and minimax designs for either Simon's 2-stage or Mander & Thompson studies

Description

obtainDesign is essentially a wrapper for calls to createGrid and augmentGrid followed by some simple filtering of the candidate designs to identify the optimal and minimax designs.

Usage

obtainDesign(
  grid = NULL,
  p0 = NA,
  p1 = NA,
  alpha = ifelse(is.null(grid), 0.05, NA),
  beta = ifelse(is.null(grid), 0.1, NA),
  fullGrid = FALSE,
  ...
)

Arguments

Value

a tibble created by createGrid. If fullGrid == FALSE the table contains an additional column, Criterion indicating the type of design. Possible values for Criterion are "optimal" and "minimax" for Simon's designs and "optimalNull", "optimalAlt", "minimaxNull" and "minimaxAlt" for Mander & Thompson designs.

Usage notes

If grid is not NULL it is possible that none of the candidate designs are acceptable (that is, satisfy both the significance level and power requirements). If this is the case and fullGrid == FALSE, then an empty tibble is returned. If versbose == TRUE a warning message is also printed. If fullGrid == TRUE the full grid of all designs considered is returned. This can then be further interrogated to find optimal designs under constraints - for example with fixed stage sizes.

Examples

# Standard use (Simon's 2-stage design)
createGrid(p0 = 0.05, p1 = 0.25, alpha = 0.05, beta = 0.2, mander = FALSE) %>%
  augmentGrid(parallel = FALSE) %>%
  obtainDesign()
# Constrained stage sizes
createGrid(p0 = 0.25, p1 = 0.45, alpha = 0.05, beta = 0.2) %>%
  dplyr::filter(nStage1 == 8) %>%
  augmentGrid(parallel = FALSE) %>%
  obtainDesign()

Plot the power curve(s) for the given design(s)

Description

Plot the power curve(s) for the given design(s)

Usage

powerPlot(grid, probs = seq(0, 1, 0.01))

Arguments

Value

the ggplot object containing the power curve(s)

Examples

createGrid(p0 = 0.05, p1 = 0.25, alpha = 0.05, beta = 0.2, mander = FALSE) %>%
  augmentGrid(cores = 2) %>%
  obtainDesign() %>%
  powerPlot(probs = seq(0, 0.5, 0.025))

Obtain default bounds for the construction of the search grid.

Description

The formula used is the continuity corrected Normal approximation from Fleiss et al (2003).

Usage

searchBounds(p0, p1, alpha = 0.05, beta = 0.2, twoSided = TRUE)

Arguments

Value

a list with three elements: "n" - the single stage sample size from Fleiss et al; "min" - the lower bound, 0.8*n; "max" - the upper bound, 2*n. floor() and ceiling() are applied as appropriate.