dim_icc: Calculate intraclass correlation coefficients for reliability

In jmgirard/agreement: What the Package Does (One Line, Title Case)

Calculate intraclass correlation coefficients for reliability

Description

Analyze intra- and inter-rater reliability of dimensional data using various intraclass correlation coefficients. These coefficients are implemented using a generalized approach that accommodates missing data and multiple trials.

Usage

dim_icc(
  .data,
  model = c("1A", "1B", "2", "2A", "3", "3A"),
  type = c("agreement", "consistency"),
  unit = c("single", "average", "custom"),
  object = Object,
  rater = Rater,
  score = Score,
  customk = NULL,
  trial = NULL,
  bootstrap = 2000,
  warnings = TRUE
)

Arguments

.data	Required. A data frame containing variables identifying and quantifying each observation, in a "tall" format.
model	Optional. A string indicating which ICC model to use, according to Gwet's (2014) typology. Options include "1A", "1B", "2", "2A", "3", and "3A". (default = "1A")
type	Optional. A string indicating which ICC type to use, according to McGraw & Wong's (1999) typology. Options include "agreement" and "consistency". (default = "agreement")
unit	Optional. A string indicating which unit of analysis to use. Options include "single" for the reliability of a single randomly chosen rater, "average" for the reliability of the average of all observed raters, or "custom" for a specified number of raters. (default = "single")
object	Optional. The name of the variable in .data identifying the object of measurement for each observation, in non-standard evaluation without quotation marks. (default = Object)
rater	Optional. The name of the variable in .data identifying the rater or source of measurement for each observation, in non-standard evaluation without quotation marks. (default = Rater)
score	Optional. The name of the variable in .data containing the dimensional score or rating for each observation, in non-standard evaluation without quotation marks. (default = Score)
customk	Optional. Either NULL to be ignored or, if unit is set to "custom" then a positive integer specifying the number of raters to calculate the reliability of the average of. (default = NULL)
trial	Optional. The name of the variable in .data identifying the time or trial of measurement for each observation, in non-standard evaluation without quotation marks. (default = NULL)
bootstrap	Optional. A non-negative integer indicating how many bootstrap resamples to use in estimating confidence intervals. Set to 0 to forgo bootstrapping. (default = 2000)
warnings	Optional. A logical value indicating whether warnings should be generated and displayed during this analysis. (default = TRUE)

Value

A list object of class "agreement_icc" with the following elements:

Object	The estimated object variance
Rater	The estimated rater variance
Interaction	The estimated object-by-variance interaction variance
Residual	The estimated residual variance
Intra_ICC	The estimated intra-rater reliability
Inter_ICC	The estimated inter-rater reliability
boot_results	The bootstrap results from the boot package
formulation	The model, type, and k arguments
details	A list containing counts and data from the analysis
call	The function call that produced this output

jmgirard/agreement documentation built on Sept. 12, 2022, 12:39 a.m.