presize

presize: An R-package for precision-based sample size calculation in clinical research - Published in JOSS (2021)

https://github.com/ctu-bern/presize

Keywords

Scientific Fields

Repository

Precision Based Sample Size Calculation

README.Rmd

---
output: github_document
bibliography: paper/paper.bib
---



```{r, echo = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "README-"
)
```

# presize 


[![](https://www.r-pkg.org/badges/version/presize?color=green)](https://cran.r-project.org/package=presize) 
`r badger::badge_custom("dev version", as.character(packageVersion("presize")), "blue", "https://github.com/CTU-Bern/presize")`
[![Actions Status](https://github.com/CTU-Bern/presize/workflows/R-CMD-fullcheck/badge.svg)](https://github.com/CTU-Bern/presize/actions)
[![Codecov test coverage](https://codecov.io/gh/CTU-Bern/presize/branch/master/graph/badge.svg)](https://codecov.io/gh/CTU-Bern/presize?branch=master)
[![DOI](https://joss.theoj.org/papers/10.21105/joss.03118/status.svg)](https://doi.org/10.21105/joss.03118)
[![metacran downloads](https://cranlogs.r-pkg.org/badges/grand-total/presize)](https://cran.r-project.org/package=presize)

[Bland (2009)](https://www.bmj.com/content/339/bmj.b3985) recommended to
base study sizes on the width of the confidence interval rather the power of 
a statistical test. The goal of `presize` is to provide functions for such 
precision based sample size calculations. For a given sample size, the 
functions will return the precision (width of the confidence interval), and 
vice versa.

## Installation

`presize` can be installed from CRAN in the usual manner:

```{r cran-installation, eval = FALSE}
install.packages("presize")
```


You can install the development version of `presize` with:

```{r gh-installation, eval = FALSE}
install.packages('presize', repos = c('https://ctu-bern.r-universe.dev', 'https://cloud.r-project.org'))
```

## Overview
`presize` provides functions for

Measure | Function | Methods available 
-------- | ---------- | --------
**Descriptive measures** | |
Mean | `prec_mean` |
Proportion | `prec_prop` | Wilson, Agresti-Coull, exact, Wald [see @brown2001]
Rate | `prec_rate` | Score, variance stabilizing, exact, Wald [see @barker2002]
**Absolute differences** | |
Mean difference | `prec_meandiff` |
Risk difference | `prec_riskdiff` | Newcombe [@newcombe1998], Miettinen-Nurminen [@mn1985], Agresti-Caffo [@ac2000], Wald
**Relative differences** | |
Odds ratio | `prec_or` | Gart, Wolff, independence smoothed logit [see @fll2015]
Risk ratio | `prec_riskratio` | Koopman [@koopman1984], Katz [@kbap1978]
Rate ratio | `prec_rateratio` | Rothman [@rg2018]
**Correlation measures** | |
Correlation coefficient | `prec_cor` | Pearson, Kendall, Spearman [see @bw2000]
Intraclass correlation | `prec_icc` | @bonnett2002
Limit of agreement | `prec_lim_agree` | @ba1986
Cohen's kappa | `prec_kappa` | @rd2012
Cronbach’s alpha | `prec_cronb` | @bonet10
**Diagnostic measures** | |
Sensitivity1 | `prec_sens` | As per `prec_prop`
Specificity1 | `prec_spec` | As per `prec_prop`
Area under the curve | `prec_auc` | @hm1982
Negative likelihood ratio2 | `prec_neg_lr` | @simel1991
Positive likelihood ratio2 | `prec_pos_lr` | @simel1991
Generic likelihood ratio | `prec_lr` | @simel1991

1 Simple wrappers for `prec_prop`.

2 Wrappers for `prec_lr` with values provided via sens and spec

## Example

Suppose we want to estimate the proportion of hospital admissions with diabetes. 
Diabetes has a prevalence of approximately 10% (@diab). We assume a 
slightly higher proportion of diabetics, 
15%, as diabetes is a risk factor for a wide range of conditions. We want to 
estimate the prevalence of diabetes to within 5% (plus/minus 2.5%). With `presize`,
this is simple. We use the `prec_prop` (precision of a proportion) function and pass 
our 15% and 5% as arguments `p` and `conf.width`:

```{r}
library(presize) # load the package
prec_prop(p = 0.15, conf.width = 0.05)
```


In the n column, we see that we would need to ask 784 (rounding 783.5 up) patients to achieve the desired CI width. 
Disappointingly, we also know that we only have funds to collect the data from 
600 patients. 
We wonder if 600 patients would yield sufficient precision - we could 
also accept a CI width of 6% (plus/minus 3%).
In such a case, we can pass the arguments `p` and `n`.

```{r}
prec_prop(p = 0.15, n = 600)
```

Now we see that with 600 patients, the CI would have a width of 
5.7%. We are happy with this and continue planning our study with those values. 
All of the functions listed in Table 1 can be used similarly.

We can also look at a range of scenarios simulatenously by passing a vector to 
one of the arguments, which could be used to create something analogous to a 
power curve: 

```{r}
prec_prop(p = 0.15, n = seq(600, 800, 50))
```


## Shiny app

An online interactive version of the package is available [here](https://shiny.ctu.unibe.ch/presize). The app can also be launched locally via `launch_presize_app()` in RStudio.

```{r, echo=FALSE}
knitr::include_graphics("man/figures/app.png")
```

## Getting help

The package website, including more details on the functions, can be found [here](https://ctu-bern.github.io/presize/).

If you have a question, feel free to make a thread on the [discussion](https://github.com/CTU-Bern/presize/discussions) page.

If you encounter a bug, please create an [issue](https://github.com/CTU-Bern/presize/issues).

## Contributing

Contributions to `presize` are welcome. If you have ideas, open an [issue](https://github.com/CTU-Bern/presize/issues) or a [discussion thread](https://github.com/CTU-Bern/presize/discussions) on GitHub. 

If you want to contribute code, please feel free to fork the repository, make your changes and make a pull request to have them integrated into the package.  New functionality should have accompanying tests and pass continuous integration. See also the [contributing guidelines](https://github.com/CTU-Bern/presize/blob/master/CONTRIBUTING.md).

## Funding

`presize` was largely developed at CTU Bern, with collaboration from CTU Basel. Funding was provided by the Swiss Clinical Trial Organisation.

```{r, echo=FALSE}
knitr::include_graphics("man/figures/SCTO_Platforms.png")
```



## Citation [![DOI](https://joss.theoj.org/papers/10.21105/joss.03118/status.svg)](https://doi.org/10.21105/joss.03118)

If you use `presize`, please cite it in your publication as:  
Haynes et al., (2021). presize: An R-package for precision-based sample size calculation in clinical research. Journal of Open Source Software, 6(60), 3118, https://doi.org/10.21105/joss.03118


### Acknowledgements

The package logo was created with [`ggplot2`](https://ggplot2.tidyverse.org/) and [`hexSticker`](https://github.com/GuangchuangYu/hexSticker) with icons from [Font Awesome](https://fontawesome.com/) (via the [emojifont package](https://github.com/GuangchuangYu/emojifont)).

## References

Owner

JOSS Publication

presize: An R-package for precision-based sample size calculation in clinical research

Published

April 14, 2021

DOI

10.21105/joss.03118

Volume 6, Issue 60, Page 3118

Authors

Alan G. Haynes
CTU Bern, University of Bern, Bern, Switzerland, Statistics and Methodology Platform of the Swiss Clinical Trial Organisation (SCTO), Bern, Switzerland

Armando Lenz
CTU Bern, University of Bern, Bern, Switzerland, Statistics and Methodology Platform of the Swiss Clinical Trial Organisation (SCTO), Bern, Switzerland

Odile Stalder
CTU Bern, University of Bern, Bern, Switzerland, Statistics and Methodology Platform of the Swiss Clinical Trial Organisation (SCTO), Bern, Switzerland

Andreas Limacher
CTU Bern, University of Bern, Bern, Switzerland, Statistics and Methodology Platform of the Swiss Clinical Trial Organisation (SCTO), Bern, Switzerland

Editor

Mark A. Jensen

Tags

R software clinical trials sample size calculation

View PDF Review Thread Software Archive

GitHub Events

Committers

Last synced: 5 months ago

Issues and Pull Requests

Last synced: 4 months ago

Packages