In MargotBr/AgreeClust: Agreement-based unsupervised clustering of a panel of raters through a latent class regression modeling framework

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
pkgload::load_all()

agreeclust

The website presenting the package is: https://margotbr.github.io/agreeclust/

The {agreeclust} package considers a latent class regression modeling framework for highlighting the structure of disagreement among panels of raters involved in an inquiry. On the contrary to popular approaches, the present method considers the ratings data provided by all raters when studying the structure of disagreement among the panel. More precisely, the structure of disagreement is captured through the profiles of residuals of a no-latent class regression model adjusted on the entire set of binary ratings, and can be visualized by using exploratory data analysis tools. The disagreement between two raters is then quantify in a concise way through the Euclidean distance between their respective profiles of residuals, this disagreement index being used as a basis to construct a dendrogram representing the structure of disagreement among the panel. The proper number of disagreed clusters among the panel of raters is then chosen by implementing a sequential strategy to test the significance of each $K$-clusters structure of disagreement.

Installation

You can install the package from GitHub with:

if(!requireNamespace("remotes")){install.packages("remotes")}
remotes::install_github("MargotBr/agreeclust", build_vignettes = TRUE) # create vignettes

You can install the development version with:

if(!requireNamespace("remotes")){install.packages("remotes")}
remotes::install_github("MargotBr/agreeclust", ref = "dev", build_vignettes = TRUE) # create vignettes

Package functionalities

To get an overview of the functionalities of the package, you can read the vignettes:

vignette(topic = "a- Global overview of the statistical methodology", package = "agreeclust")
vignette(topic = "b- Using the proper format of data", package = "agreeclust")
vignette(topic = "c- Use of the package with binary ratings", package = "agreeclust")

Or access the website presenting the package: https://margotbr.github.io/agreeclust/

Usage

library(agreeclust)
data(binary_data_for_example)
res_pedag <- get_agreeclust_bin(dta = binary_data_for_example,
                                id_info_rater = 9 : nrow(binary_data_for_example),
                                type_info_rater = c(rep("cat", 2), "cont"),
                                id_info_stim = 21 : ncol(binary_data_for_example),
                                type_info_stim = c(rep("cont", 4), "cat"),
                                )
res_pedag

library(agreeclust)
data(binary_data_for_example)
res_pedag <- get_agreeclust_bin(dta = binary_data_for_example,
                                id_info_rater = 9 : nrow(binary_data_for_example),
                                type_info_rater = c(rep("cat", 2), "cont"),
                                id_info_stim = 21 : ncol(binary_data_for_example),
                                type_info_stim = c(rep("cont", 4), "cat"),
                                paral_null = FALSE,
                                graph = FALSE)
print.agreeclust_binary(res_pedag)

# Visualisation of the clustering process
plot_agreeclust(res_pedag, choice = "seg")

# Visualisation of the multidimensional structure of disagreement
plot_agreeclust(res_pedag, choice = "mul")

# Interactive version
plot_agreeclust(res_pedag, choice = "mul", interact = TRUE)

MargotBr/AgreeClust documentation built on Jan. 29, 2021, 1:12 a.m.