testretest.multiverse {splithalf}R Documentation

Multiverse of data processing decisions on test retest reliability estimates.

Description

This function enables the user to run a multiverse of data processing options and extract the resulting test-retest reliability estimates. The user specifies a set of data processing decisions and passes this to the function, along with specifying key variables within several "var." inputs (so that the function knows where to find your participant ids and RTs for example)

Usage

testretest.multiverse(
  data,
  specifications,
  test = "ICC2",
  outcome = "RT",
  score = "difference",
  var.participant = "subject",
  var.ACC = "correct",
  var.RT = "RT",
  var.time = "time",
  var.compare = "congruency",
  compare1 = "Congruent",
  compare2 = "Incongruent"
)

Arguments

data

dataset

specifications

list of data processing specifications

test

test retest statistic, "ICC2", "cor", "ICC3"

outcome

from splithalf() specifies the RT outcome - only "RT" available currently

score

currently only "difference" scores are supported

var.participant

= "subject",

var.ACC

= "correct",

var.RT

= "RT"

var.time

codes the time variable (currently only works for 2 timepoints)

var.compare

= "congruency" trial type used to create difference scores

compare1

specifies the first trial type to be compared (e.g. "Congruent" trials)

compare2

specifies the second trial type to be compared (e.g. "Incongruent" trials)

Details

The (unofficial) function version name is "This function will help you pay the troll toll"

Value

Returns a multiverse object containing the reliability estimates and dataframes from all data processing specifications provided

Examples

## Not run: 
## see online documentation for examples
https://github.com/sdparsons/splithalf
## also see https://psyarxiv.com/y6tcz

n_participants <- 80 ## sample size
n_trials <- 120
n_blocks <- 2

sim_data_mv <- data.frame(participant_number = rep(1:n_participants,
                                                   each = n_blocks * n_trials),
                          trial_number = rep(1:n_trials,
                                             times = n_blocks * n_participants),
                          block_name = rep(c(1,2),
                                           each = n_trials,
                                           length.out = n_participants * n_trials * n_blocks),
                          trial_type = rep(c("congruent","congruent",
                                             "incongruent","incongruent"),
                                           length.out = n_participants * n_trials * n_blocks / 2),
                          RT = rnorm(n_participants * n_trials * n_blocks,
                                     500,
                                     200),
                          ACC = c(rbinom(n_participants *
                                           n_trials *
                                           n_blocks / 6,
                                         1, .5),
                                  rbinom(n_participants *
                                           n_trials *
                                           n_blocks / 6,
                                         1, .7),
                                  rbinom(n_participants *
                                           n_trials *
                                           n_blocks / 6,
                                         1, .9),
                                  rbinom(n_participants *
                                           n_trials *
                                           n_blocks / 6,
                                         1, .5),
                                  rbinom(n_participants *
                                           n_trials *
                                           n_blocks / 6,
                                         1, .7),
                                  rbinom(n_participants *
                                           n_trials *
                                           n_blocks / 6,
                                         1, .9)))

specifications <- list(
ACC_cutoff = c(0, 0.5),
RT_min           = c(0, 200),
RT_max            = c(2000, 3000),
RT_sd_cutoff      = c(0, 2),
split_by          = c("subject", "trial"),
averaging_method  = c("mean")
)

icc2 <- testretest.multiverse(data = sim_data_acc,
specifications,
test = "ICC2",
score = "difference",
var.participant = "participant_number",
var.ACC = "ACC",
var.RT = "RT",
var.time = "block_name",
var.compare = "trial_type",
compare1 = "congruent",
compare2 = "incongruent")

multiverse.plot(icc2)


## End(Not run)

[Package splithalf version 0.8.2 Index]