diff --git a/README.Rmd b/README.Rmd index 0a7d43a..4f1ddae 100644 --- a/README.Rmd +++ b/README.Rmd @@ -16,7 +16,7 @@ knitr::opts_chunk$set( # morphmat -Hex sticker logo for morphmat package +Hex sticker logo for morphmat package @@ -28,11 +28,10 @@ A compilation of methods used to estimate size at (sexual) maturity based on mor `morphmat` is intended to help fisheries scientists and managers to implement the multitude of computational methods that have been developed for estimating crustacean size at maturity. This package is being developed as part of my graduate work at the University of Maine. **This is still a work in progress and should not yet be used for research purposes.** -`morphmat` will include user-friendly functions for estimating size at morphometric maturity, along with guidelines for choosing the optimal method for a given dataset and correctly interpreting results. Both novel and historically popular (e.g., broken-stick regression) methods will be included, and users will be able to obtain SM50 estimates from nearly a dozen different approaches with a single function call. Crucially, by combining code for the various models within a single package, morphmat will enable the application of multi-model inference to SM50 estimation, avoiding the arbitrary selection of a single “best” model [@katsanevakis2006]. By increasing the accessibility of modern statistical methods for estimating SM50, I hope to facilitate the widespread adoption of improved SM50 modeling procedures. +`morphmat` will include user-friendly functions for estimating size at morphometric maturity, along with guidelines for choosing the optimal method for a given dataset and correctly interpreting results. Both novel and historically popular (e.g., broken-stick regression) methods will be included, and users will be able to obtain SM50 estimates from nearly a dozen different approaches with a single function call. By combining code for the various models within a single package, morphmat will enable the application of multi-model inference to SM50 estimation, avoiding the arbitrary selection of a single “best” model [@katsanevakis2006]. By increasing the accessibility of modern statistical methods for estimating SM50, I hope to facilitate the widespread adoption of improved SM50 modeling procedures. `morphmat` will include versions of the methods implemented in these existing GitHub repositories: -| | | | | |---------------|---------------|---------------|---------------------------| | **Type** | **Authors** | **GitHub repository** | **Description/notes** | | Package | Josymar Torrejon-Magallanes | [ejosymart/sizeMat](https://github.com/ejosymart/sizeMat) | [sizeMat: An R Package to Estimate Size at Sexual Maturity](https://cran.r-project.org/web/packages/sizeMat/vignettes/sizeMat.html) | @@ -45,7 +44,6 @@ A compilation of methods used to estimate size at (sexual) maturity based on mor The following scripts do not use morphometric data and require individuals to already be classified as mature or immature. They provide various examples of how to fit maturity\~length binomial models to estimate SM50 and obtain confidence intervals. These tools can also be used to calculate size at maturity for non-crustacean fisheries. For a comprehensive examination of this type of model, see [@mainguy2024]. -| | | | | |--------------|--------------|-------------------|--------------------------| | **Type** | **Authors** | **GitHub repository** | **Description/notes** | | R scripts | Lucas Rodrigues | [lvcasrodrigues/maturity_at_size](https://github.com/lvcasrodrigues/maturity_at_size) | Does not use morphometric data; takes size classes with known numbers of mature individuals per size class and fits a binomial model (frequentist or Bayesian). Finds SM50 by generating new data from the model rather than from ratio of parameters | diff --git a/README.md b/README.md index 49fe6b7..7687c09 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,7 @@ # morphmat -\“Hex +Hex sticker logo for morphmat package @@ -32,28 +31,51 @@ morphometric maturity, along with guidelines for choosing the optimal method for a given dataset and correctly interpreting results. Both novel and historically popular (e.g., broken-stick regression) methods will be included, and users will be able to obtain SM50 estimates from -nearly a dozen different approaches with a single function call. -Crucially, by combining code for the various models within a single -package, morphmat will enable the application of multi-model inference -to SM50 estimation, avoiding the arbitrary selection of a single “best” -model ([Katsanevakis 2006](#ref-katsanevakis2006)). By increasing the -accessibility of modern statistical methods for estimating SM50, I hope -to facilitate the widespread adoption of improved SM50 modeling -procedures. +nearly a dozen different approaches with a single function call. By +combining code for the various models within a single package, morphmat +will enable the application of multi-model inference to SM50 estimation, +avoiding the arbitrary selection of a single “best” model ([Katsanevakis +2006](#ref-katsanevakis2006)). By increasing the accessibility of modern +statistical methods for estimating SM50, I hope to facilitate the +widespread adoption of improved SM50 modeling procedures. `morphmat` will include versions of the methods implemented in these existing GitHub repositories: -| | | | | -|----|----|----|----| -| **Type** | **Authors** | **GitHub repository** | **Description/notes** | -| Package | Josymar Torrejon-Magallanes | [ejosymart/sizeMat](https://github.com/ejosymart/sizeMat) | [sizeMat: An R Package to Estimate Size at Sexual Maturity](https://cran.r-project.org/web/packages/sizeMat/vignettes/sizeMat.html) | -| Package | Rodrigo Sant’Ana, Fernando Mayer | [rodrigosantana/Regrans: Fits Segmented Linear Regression Models](https://github.com/rodrigosantana/Regrans) | Older repository: [fernandomayer/Regrans](https://github.com/fernandomayer/Regrans/blob/master/change.point.R) | -| Package | Derek Sonderegger | [siZer](https://cran.r-project.org/web/packages/SiZer/index.html) | [Conduct size at morphometric maturity analysis (SMM) and plot results using the SiZer extension package](https://zenodo.org/records/5002120) by Olson, Andrew P., Siddon, Chris E., and Eckert, Ginny L. | -| Package | Vito M. R. Muggeo | [segmented](https://cran.r-project.org/web/packages/segmented/index.html) | [package reference manual](https://cran.r-project.org/web/packages/segmented/segmented.pdf) | -| Package | Youyi Fong | [chngpt](https://doi.org/10.32614/CRAN.package.chngpt) | [Fitting Threshold Regression Models Using chngpt](https://cran.r-project.org/web/packages/chngpt/vignettes/chngpt-vignette.pdf) (vignette) | -| Package | Tobie Surette | [TobieSurette/gulf.stats](https://github.com/TobieSurette/gulf.stats) | See files [morphometric.maturity.R](https://github.com/TobieSurette/gulf.stats/blob/master/R/morphometric.maturity.R) and [morphometry.R](https://github.com/TobieSurette/gulf.stats/blob/master/R/morphometry.R) | -| R scripts | Bradley Stevens | [Crabman52/Crustacean_Sensation](https://github.com/Crabman52/Crustacean_Sensation) | Include three different methods for separating mature from immature crabs based on allometric growth of body parts, with code based on Somerton’s (1980) program MATURE | +\|—————\|—————\|—————\|—————————\| \| **Type** \| **Authors** \| +**GitHub repository** \| **Description/notes** \| \| Package \| Josymar +Torrejon-Magallanes \| +[ejosymart/sizeMat](https://github.com/ejosymart/sizeMat) \| [sizeMat: +An R Package to Estimate Size at Sexual +Maturity](https://cran.r-project.org/web/packages/sizeMat/vignettes/sizeMat.html) +\| \| Package \| Rodrigo Sant’Ana, Fernando Mayer \| +[rodrigosantana/Regrans: Fits Segmented Linear Regression +Models](https://github.com/rodrigosantana/Regrans) \| Older repository: +[fernandomayer/Regrans](https://github.com/fernandomayer/Regrans/blob/master/change.point.R) +\| \| Package \| Derek Sonderegger \| +[siZer](https://cran.r-project.org/web/packages/SiZer/index.html) \| +[Conduct size at morphometric maturity analysis (SMM) and plot results +using the SiZer extension package](https://zenodo.org/records/5002120) +by Olson, Andrew P., Siddon, Chris E., and Eckert, Ginny L. \| \| +Package \| Vito M. R. Muggeo \| +[segmented](https://cran.r-project.org/web/packages/segmented/index.html) +\| [package reference +manual](https://cran.r-project.org/web/packages/segmented/segmented.pdf) +\| \| Package \| Youyi Fong \| +[chngpt](https://doi.org/10.32614/CRAN.package.chngpt) \| [Fitting +Threshold Regression Models Using +chngpt](https://cran.r-project.org/web/packages/chngpt/vignettes/chngpt-vignette.pdf) +(vignette) \| \| Package \| Tobie Surette \| +[TobieSurette/gulf.stats](https://github.com/TobieSurette/gulf.stats) \| +See files +[morphometric.maturity.R](https://github.com/TobieSurette/gulf.stats/blob/master/R/morphometric.maturity.R) +and +[morphometry.R](https://github.com/TobieSurette/gulf.stats/blob/master/R/morphometry.R) +\| \| R scripts \| Bradley Stevens \| +[Crabman52/Crustacean_Sensation](https://github.com/Crabman52/Crustacean_Sensation) +\| Include three different methods for separating mature from immature +crabs based on allometric growth of body parts, with code based on +Somerton’s (1980) program MATURE \| The following scripts do not use morphometric data and require individuals to already be classified as mature or immature. They provide @@ -63,12 +85,25 @@ used to calculate size at maturity for non-crustacean fisheries. For a comprehensive examination of this type of model, see ([Mainguy et al. 2024](#ref-mainguy2024)). -| | | | | -|----|----|----|----| -| **Type** | **Authors** | **GitHub repository** | **Description/notes** | -| R scripts | Lucas Rodrigues | [lvcasrodrigues/maturity_at_size](https://github.com/lvcasrodrigues/maturity_at_size) | Does not use morphometric data; takes size classes with known numbers of mature individuals per size class and fits a binomial model (frequentist or Bayesian). Finds SM50 by generating new data from the model rather than from ratio of parameters | -| R scripts | Mainguy et al. | [rafamoral/L50](https://github.com/rafamoral/L50): Monitoring reproduction in fish: Assessing the adequacy of ogives and the predicted uncertainty of their *L*50 estimates for more reliable biological inferences | Over a dozen methods for estimating L50 values and obtaining confidence intervals from (frequentist or Bayesian) binomial models (Delta, Fieller, bootstrap resampling, profile-likelihood, etc.). See accompanying manuscript by Mainguy et al. ([2024](#ref-mainguy2024)). | -| R script | [Alastair V. Harry](https://scholar.google.com.au/citations?user=hb4nzPYAAAAJ&hl) | [Alharry/Maturity.ogive.R](https://gist.github.com/alharry/4576675) | Includes bootstrap resampling to obtain 95% CIs | +\|————–\|————–\|——————-\|————————–\| \| **Type** \| **Authors** \| +**GitHub repository** \| **Description/notes** \| \| R scripts \| Lucas +Rodrigues \| +[lvcasrodrigues/maturity_at_size](https://github.com/lvcasrodrigues/maturity_at_size) +\| Does not use morphometric data; takes size classes with known numbers +of mature individuals per size class and fits a binomial model +(frequentist or Bayesian). Finds SM50 by generating new data from the +model rather than from ratio of parameters \| \| R scripts \| Mainguy et +al. \| [rafamoral/L50](https://github.com/rafamoral/L50): Monitoring +reproduction in fish: Assessing the adequacy of ogives and the predicted +uncertainty of their *L*50 estimates for more reliable +biological inferences \| Over a dozen methods for estimating L50 values +and obtaining confidence intervals from (frequentist or Bayesian) +binomial models (Delta, Fieller, bootstrap resampling, +profile-likelihood, etc.). See accompanying manuscript by Mainguy et al. +([2024](#ref-mainguy2024)). \| \| R script \| [Alastair V. +Harry](https://scholar.google.com.au/citations?user=hb4nzPYAAAAJ&hl) \| +[Alharry/Maturity.ogive.R](https://gist.github.com/alharry/4576675) \| +Includes bootstrap resampling to obtain 95% CIs \| ## Installation diff --git a/vignettes/classification.Rmd b/vignettes/classification.Rmd index 834acff..4b2ef6a 100644 --- a/vignettes/classification.Rmd +++ b/vignettes/classification.Rmd @@ -43,14 +43,14 @@ knitr::opts_chunk$set(message = FALSE) #| label: setup-2 #| echo: false -mytheme <- theme_classic()+ #define custom theme for ggplots +mytheme <- theme_classic() + # define custom theme for ggplots theme( axis.title.y = element_text(margin = margin(t = 0, r = 10, b = 0, l = 0)), axis.title.x = element_text(margin = margin(t = 10, r = 0, b = 0, l = 0)), - text=element_text(size=13)) + text = element_text(size = 13)) ``` -Here I will write a vignette explaining all of the methods that first classify points as mature or immature, enabling the use of logistic regression to find SM50 as would be done with a physiological metric of maturity. This vignette will be useful for referring readers to more complex options available in packages like `mclust` that are not available within `morphmat`. +This vignette describes methods that first classify individual data points as mature or immature, enabling the use of logistic regression to find SM50 as would be done with a physiological metric of maturity. This vignette will be useful for referring readers to more complex options available in packages like `mclust` that are not available within `morphmat`. We will start by simulating a data set with a known SM50 value of 75 mm to demonstrate the use (and limitations) of broken-stick methods.