Package {implicitMeasures}

IAT reliability

Description

Computes the practice–test reliability of the Implicit Association Test (IAT) as the correlation between the D-scores obtained in the practice and test blocks.

Usage

IAT_rel(data)

Arguments

Value

An object of class "IAT_rel", consisting of a list with:

Test-practice Reliability

The Pearson correlation between practice and test D-scores.

Number of participants

The number of participants on which the reliability was computed.

Examples

# Clean IAT data
data("raw_data")

iat_cleandata <- clean_iat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  mapA_practice = "practice.iat.Milkbad",
  mapA_test = "test.iat.Milkbad",
  mapB_practice = "practice.iat.Milkgood",
  mapB_test = "test.iat.Milkgood",
  latency_id = "latency",
  accuracy_id = "correct",
  trial_id = "trialcode",
  trial_eliminate = c("reminder", "reminder1"),
  demo_id = "blockcode",
  trial_demo = "demo"
)

iat_data <- iat_cleandata[[1]]

# Compute D-score
iat_dscore <- compute_iat(
  iat_data,
  Dscore = "d2"
)

# Compute practice--test reliability
IAT_rel(iat_dscore)

Prepare and clean IAT data.

Description

Select IAT blocks for the D-score computation and eventually save demographic data.

Usage

clean_iat(
  data,
  sbj_id = "participant",
  block_id = "blockcode",
  mapA_practice = "practice_MappingA",
  mapA_test = "test_MappingA",
  mapB_practice = "practice_MappingB",
  mapB_test = "test_MappingB",
  latency_id = "latency",
  accuracy_id = "correct",
  trial_id = NULL,
  trial_eliminate = NULL,
  demo_id = NULL,
  trial_demo = NULL
)

Arguments

Value

List of dataframe.

data_keep

Dataframe with class iat_clean. The dataframe contains the data of the blocks specified in mapA_practice, mapA_test, mapB_practice, mapB_test. If you have specified the trials to eliminate through trial_eliminate, data_keep will contain the already cleaned dataset. This dataset should be passed to the computeD function.

data_eliminate

Dataframe containing all the discarded blocks and trials.

data_demo

Dataframe containing demographic variables. It will be present only if you specified the demo_id and trial_demo arguments.

Examples

data("raw_data") # load data
iat_cleandata <- clean_iat(raw_data, sbj_id = "Participant",
                          block_id = "blockcode",
                          mapA_practice = "practice.iat.Milkbad",
                          mapA_test = "test.iat.Milkbad",
                          mapB_practice = "practice.iat.Milkgood",
                          mapB_test = "test.iat.Milkgood",
                          latency_id = "latency",
                          accuracy_id = "correct",
                          trial_id = "trialcode",
                          trial_eliminate = c("reminder", "reminder1"),
                          demo_id = "blockcode",
                          trial_demo = "demo")
iat_data <- iat_cleandata[[1]] # select the first element of the list (IAT data)
head(iat_data)
demo_data <- iat_cleandata[[3]] # select the third element of the list
                            # (demographic data)
head(demo_data)

Prepare and clean SC-IAT data

Description

Select the SC-IAT blocks, for either one or two SC-IATs. Eventually save demographic data.

Usage

clean_sciat(
  data,
  sbj_id = "participant",
  block_id = "blockcode",
  accuracy_id = "correct",
  latency_id = "latency",
  block_sciat_1 = NULL,
  block_sciat_2 = NULL,
  trial_id = NULL,
  trial_eliminate = NULL,
  demo_id = NULL,
  trial_demo = NULL
)

Arguments

Value

List of dataframe.

sciat1

Data frame with class sciat_clean containing the data of the first SC-IAT as specified block_sciat_1. If any labels was specified in trial_eliminate, data_keep will contain the already cleaned dataset.

sciat2

Data frame with class sciat_clean containing the data of the second (if any) SC-IAT as specified through block_sciat_2. If any labels was specified in trial_eliminate, data_keep will contain the already cleaned dataset.

data_demo

Data frame. Present only when variable_demo and trial_demo arguments are specified.

Examples

data("raw_data")
sciat_data <- clean_sciat(raw_data, sbj_id = "Participant",
                         block_id = "blockcode",
                         latency_id = "latency",
                         accuracy_id = "correct",
                         block_sciat_1 = c("test.sc_dark.Darkbad",
                                           "test.sc_dark.Darkgood"),
                         block_sciat_2 = c("test.sc_milk.Milkbad",
                                           "test.sc_milk.Milkgood"),
                         trial_id  = "trialcode",
                         trial_eliminate = c("reminder",
                                             "reminder1"))
sciat1 <- sciat_data[[1]]
sciat2 <- sciat_data[[2]]

Compute IAT D-score

Description

Compute D-score for the IAT according to different algorithms.

Usage

compute_iat(data, Dscore = c("d1", "d2", "d3", "d4", "d5", "d6"))

Arguments

Value

Dataframe with class "dscore". The number of rows of the dataframe corresponds to the total number of participants. Variables are defined as follows (the values are specific for each participant):

participant

Respondents' IDs.

n_trial

Number of trails before data cleaning.

nslow10000

Number of slow trials (> 10,000 ms).

nfast400

Number of fast trials (< 400 ms).

nfast300

Number of fast trials (< 300 ms).

accuracy.practice_MappingA

Proportion of correct responses in practice block of Mapping A.

accuracy.practice_MappingB

Proportion of correct responses in practice block of Mapping B.

accuracy.test_MappingA

Proportion of correct responses in test block of Mapping A.

accuracy.test_MappingB

Proportion of correct responses in test block of Mapping B.

accuracy.MappingA

Proportion of correct responses in Mapping A.

accuracy.MappingB

Proportion of correct responses in Mapping B.

RT_mean.MappingA

Mean response time in Mapping A.

RT_mean.MappingB

Mean response time in Mapping B.

mean_practice_MappingA

Mean response time in practice block of Mapping A.

mean_practice_MappingB

Mean response time in practice block of Mapping B.

mean_test_MappingA

Mean response time in test block of Mapping A.

mean_test_MappingB

Mean response time in test block of Mapping B.

d_practice_dX

D-scores compute_iat on the practice blocks. The X stands for the selected D-score procedure.

d_test_dX

D-scores compute_iat on the test blocks. The X stands for the selected D-score procedure.

dscore_dX

The average D-score for the practice and test D-scores. The X stands for the selected D-score procedure.

cond_ord

Indicates the order with which the associative conditions have been presented, either "MappingA_First" or "MappingB_First".

legendMappingA

Indicates the corresponding value of Mapping A in the original dataset.

legendMappingB

Indicates the corresponding value of Mapping B in the original dataset.

Examples

# compute D-score 2 for the IAT data ###
  data("raw_data") # import data
  iat_cleandata <- clean_iat(raw_data, sbj_id = "Participant",
                          block_id = "blockcode",
                          mapA_practice = "practice.iat.Milkbad",
                          mapA_test = "test.iat.Milkbad",
                          mapB_practice = "practice.iat.Milkgood",
                          mapB_test = "test.iat.Milkgood",
                          latency_id = "latency",
                          accuracy_id = "correct",
                          trial_id = "trialcode",
                          trial_eliminate = c("reminder", "reminder1"),
                          demo_id = "blockcode",
                          trial_demo = "demo")
  iat_data <- iat_cleandata[[1]]
# calculate D-score
  iat_dscore <- compute_iat(iat_data,
                         Dscore =  "d2")

Compute the D-score for the SC-IAT

Description

Compute the D-score for the SC-IAT.

Usage

compute_sciat(
  data,
  mappingA = "mappingA",
  mappingB = "mappingB",
  non_response = NULL
)

Arguments

Value

A dataframe with class compute_sciat. The number of rows of the dataframe corresponds to the total number of participants. Variables are defined as follows (the values are specific for each participant):

participant

Respondents' IDs.

n_trial

Number of trial before data cleaning.

no_response

If there were any trials identifying the non response, it indicates the number of non responses per each participant. Otherwise, it is equal for all participants ("none").

nslow10000

Number of slow trials (> 10,000 ms).

out_accuracy

Indicates whether the participants had more than 25 % of incorrect responses in at least one of the critical blocks and hence should be eliminated ("out") or not ("keep").

nfast400

Number of fast trials (< 400 ms).

nfast300

Number of fast trials (< 350 ms – deleted).

accuracy.mappingA

Proportion of correct responses in Mapping A.

accuracy.mappingB

Proportion of correct responses in mapping B.

RT_mean.MappingA

Mean response time in Mapping A.

RT_mean.MappingB

Mean response time in Mapping B.

cond_ord

Indicates the order with which the associative conditions have been presented, either "MappingA_First" or "MappingB_First".

legendMappingA

Indicates the corresponding value of Mapping A in the original dataset.

legendMappingB

Indicates the corresponding value of Mapping B in the original dataset.

d_sciat

SC-IAT D.

Examples

# calculate D for the SCIAT
  data("raw_data") # load data
sciat_data <- clean_sciat(raw_data, sbj_id = "Participant",
                         block_id = "blockcode",
                         latency_id = "latency",
                         accuracy_id = "correct",
                         block_sciat_1 = c("test.sc_dark.Darkbad",
                                           "test.sc_dark.Darkgood"),
                         block_sciat_2 = c("test.sc_milk.Milkbad",
                                           "test.sc_milk.Milkgood"),
                         trial_id  = "trialcode",
                         trial_eliminate = c("reminder",
                                             "reminder1"))
 sciat1 <- sciat_data[[1]] # compute D for the first SC-IAT
 d_sciat1 <- compute_sciat(sciat1,
                    mappingA = "test.sc_dark.Darkbad",
                    mappingB = "test.sc_dark.Darkgood",
                    non_response = "alert")
 head(d_sciat1) # dataframe containing the SC-IAT D of the of the
                # first SC-IAT

 sciat2 <- sciat_data[[2]] # Compute D for the second SC-IAT
 d_sciat2 <- compute_sciat(sciat2,
                    mappingA = "test.sc_milk.Milkbad",
                    mappingB = "test.sc_milk.Milkgood",
                    non_response = "alert")
 head(d_sciat2)

Data set with SC-IAT D-scores (Dark)

Description

A data set containing the results of the computation of the D-score on the Dark SC-IAT data set. This data set is used for testing the replicability of the results obtained with the compute_sciat() functions.

Usage

data("dsciat1")

Format

A dataframe with 15 variables, as those described in the documentation for the compute_sciat()function.

Data set with SC-IAT D-scores (Milk)

Description

A data set containing the results of the computation of the D-score on the Dark SC-IAT data set. This data set is used for testing the replicability of the results obtained with the compute_sciat() functions.

Usage

data("dsciat2")

Format

A dataframe with 15 variables, as those described in the documentation for the compute_sciat() function.

Data set with IAT D-scores

Description

A data set containing the results for all the possible D-score algorithms for the IAT. All the algorithms are identified by their corresponding label (such as "dscore_d1"). This data set is used for testing the replicability of the results of the compute_iat() function over time.

Usage

data("iatdscores")

Format

A dataframe with 7 variables, the first one contains the respondents' id, the other 6 columns contain a specific D-score algorithm.

Compute multiple SC-IAT scores

Description

Computes the D-scores for all SC-IAT data sets contained in an object of class '"sciat_clean"'.

Computes multiple D-scores from cleaned IAT or SC-IAT data.

Usage

## S3 method for class 'iat_clean'
multi_dscore(
  data,
  algorithms = "all",
  mappingA = NULL,
  mappingB = NULL,
  labels = NULL,
  non_response = "alert"
)

## S3 method for class 'sciat_clean'
multi_dscore(
  data,
  algorithms = "all",
  mappingA = NULL,
  mappingB = NULL,
  labels = NULL,
  non_response = "alert"
)

multi_dscore(
  data,
  algorithms = "all",
  mappingA = NULL,
  mappingB = NULL,
  labels = NULL,
  non_response = "alert"
)

Arguments

Details

The SC-IAT data sets are identified among the elements of 'data' by selecting data frames that inherit from class '"sciat_clean"'. Other elements, such as demographic data, are ignored.

This is an S3 generic. The appropriate method is selected according to the class of 'data'.

Value

An object of class '"multi_dscore"' containing:

scores

A data frame containing participant identifiers and the SC-IAT scores in wide format.

scores_long

A data frame containing the variables 'participant', 'score_type', and 'score'.

source

The character value '"SC-IAT"'.

labels

The labels associated with the SC-IAT scores.

An object of class '"multi_dscore"'.

Examples

data("raw_data")

sciat_data <- clean_sciat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  latency_id = "latency",
  accuracy_id = "correct",
  block_sciat_1 = c(
    "test.sc_dark.Darkbad",
    "test.sc_dark.Darkgood"
  ),
  block_sciat_2 = c(
    "test.sc_milk.Milkbad",
    "test.sc_milk.Milkgood"
  ),
  trial_id = "trialcode",
  trial_eliminate = c(
    "reminder",
    "reminder1"
  )
)

multiple_sciat <- multi_dscore(
  sciat_data,
  mappingA = c(
    "test.sc_dark.Darkbad",
    "test.sc_milk.Milkbad"
  ),
  mappingB = c(
    "test.sc_dark.Darkgood",
    "test.sc_milk.Milkgood"
  ),
  labels = c(
    "Dark chocolate",
    "Milk chocolate"
  ),
  non_response = "alert"
)

multiple_sciat$scores
multiple_sciat$scores_long

plot(multiple_sciat)


# Clean IAT data
data("raw_data")

iat_cleandata <- clean_iat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  mapA_practice = "practice.iat.Milkbad",
  mapA_test = "test.iat.Milkbad",
  mapB_practice = "practice.iat.Milkgood",
  mapB_test = "test.iat.Milkgood",
  latency_id = "latency",
  accuracy_id = "correct",
  trial_id = "trialcode",
  trial_eliminate = c("reminder", "reminder1"),
  demo_id = "blockcode",
  trial_demo = "demo"
)

iat_data <- iat_cleandata[[1]]

# Compute multiple IAT D-scores
iat_multi <- multi_dscore(
  iat_data,
  algorithms = "all"
)

str(iat_multi)

Plot IAT and SC-IAT scores

Description

Produces a histogram, density plot, boxplot, or participant-level point plot for IAT and SC-IAT scores.

Usage

## S3 method for class 'dsciat'
plot(
  x,
  graph = c("histogram", "density", "boxplot", "points"),
  n_bin = 80,
  col_fill = "royalblue",
  col_point = "firebrick",
  point_size = 1,
  x_label = "Participant",
  x_values = TRUE,
  order_sbj = c("default", "D-increasing", "D-decreasing"),
  include_stats = FALSE,
  ...
)

## S3 method for class 'dscore'
plot(
  x,
  graph = c("histogram", "density", "boxplot", "points"),
  n_bin = 80,
  col_fill = "royalblue",
  col_point = "firebrick",
  point_size = 1,
  x_label = "Participant",
  x_values = TRUE,
  order_sbj = c("default", "D-increasing", "D-decreasing"),
  include_stats = FALSE,
  ...
)

Arguments

Details

The appropriate score column and score-axis label are selected automatically according to the class of 'x'.

The arguments 'point_size', 'x_label', 'x_values', and 'order_sbj' are relevant when 'graph = "points"'. The argument 'n_bin' is relevant when 'graph = "histogram"'.

The appropriate S3 method is selected automatically by 'plot()': objects of class '"dscore"' are handled by 'plot.dscore()', whereas objects of class '"dsciat"' are handled by 'plot.dsciat()'.

Value

A 'ggplot' object.

Examples

## IAT ------------------------------------------------------------------

data("raw_data")

iat_clean <- clean_iat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  mapA_practice = "practice.iat.Milkbad",
  mapA_test = "test.iat.Milkbad",
  mapB_practice = "practice.iat.Milkgood",
  mapB_test = "test.iat.Milkgood",
  latency_id = "latency",
  accuracy_id = "correct",
  trial_id = "trialcode",
  trial_eliminate = c("reminder", "reminder1"),
  demo_id = "blockcode",
  trial_demo = "demo"
)

iat_data <- iat_clean[[1]]

iat_dscore <- compute_iat(
  iat_data,
  Dscore = "d2"
)

# Histogram
plot(iat_dscore)

# Density plot
plot(
  iat_dscore,
  graph = "density",
  include_stats = TRUE
)

# Boxplot
plot(
  iat_dscore,
  graph = "boxplot",
  col_point = "salmon"
)

# Participant-level point plot
plot(
  iat_dscore,
  graph = "points",
  order_sbj = "D-increasing"
)

# Participant-level point plot without participant labels
plot(
  iat_dscore,
  graph = "points",
  order_sbj = "D-decreasing",
  col_point = "salmon",
  include_stats = TRUE,
  x_values = FALSE
)


## SC-IAT ---------------------------------------------------------------

sciat_clean <- clean_sciat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  latency_id = "latency",
  accuracy_id = "correct",
  block_sciat_1 = c(
    "test.sc_dark.Darkbad",
    "test.sc_dark.Darkgood"
  ),
  block_sciat_2 = c(
    "test.sc_milk.Milkbad",
    "test.sc_milk.Milkgood"
  ),
  trial_id = "trialcode",
  trial_eliminate = c(
    "reminder",
    "reminder1"
  )
)

sciat_data <- sciat_clean[[1]]

sciat_dscore <- compute_sciat(
  sciat_data,
  mappingA = "test.sc_dark.Darkbad",
  mappingB = "test.sc_dark.Darkgood",
  non_response = "alert"
)

# Histogram
plot(sciat_dscore)

# Density plot
plot(
  sciat_dscore,
  graph = "density",
  include_stats = TRUE
)

# Boxplot
plot(
  sciat_dscore,
  graph = "boxplot",
  col_point = "salmon"
)

# Participant-level point plot
plot(
  sciat_dscore,
  graph = "points",
  order_sbj = "D-decreasing",
  col_point = "salmon",
  include_stats = TRUE
)

Plot multiple IAT or SC-IAT scores

Description

Produces group-level or participant-level graphical representations of multiple IAT or SC-IAT scores.

Usage

## S3 method for class 'multi_dscore'
plot(
  x,
  graph = c("boxplot", "violin", "individual"),
  col_fill = "royalblue",
  col_point = "firebrick",
  col_line = "gray50",
  point_size = 1.5,
  line_width = 0.5,
  line_alpha = 0.35,
  include_points = TRUE,
  jitter_width = 0.15,
  x_label = NULL,
  y_label = NULL,
  col_mean = "black",
  mean_size = 3,
  col_inversion = "darkorange2",
  participants = NULL,
  ...
)

Arguments

Details

Group-level comparisons can be displayed using boxplots or violin plots. For multiple IAT scores, participant-level trajectories can also be displayed to compare the scores obtained with different D-score algorithms.

Value

A 'ggplot' object.

Dataset with one IAT and two SC-IATs

Description

A dataset containing the data from 152 participants who completed one IAT and two SC-IATs. The object of both the implicit measures was chocolate, either Milk or Dark chocolate:

Usage

data(raw_data)

Format

A dataframe with 6 variables, as follows:

• Participant. Participants ID.

• latency. Latency of the response times in millisecond.

• correct. Response accuracy (0–correct, 1–error).

• trialcode. Factor with 32 levels identifying the trial for each response, both for the implicit measures and the demographic questionnaire. It contains also the trials that have to be eliminated, defined as follows:

  • alert. Defines the SC-IAT trials beyond the response time window.

  • Reminder, Reminder1. Identify the instruction page.

• blockcode. Factor with 13 levels as follow:

  • practice.iat.Milkbad. IAT practice blocks, Mapping A.

  • practice.iat.Milkbad. IAT practice blocks, Mapping B.

  • practice.sc_dark.Darkbad. Dark SC-IAT practice blocks, Mapping A.

  • practice.sc_dark.Darkbad. Dark SC-IAT practice blocks, Mapping B.

  • practice.sc_milk.Milkbad. Milk SC-IAT practice blocks, Mapping A.

  • practice.sc_milk.Milkgood. Milk SC-IAT practice blocks, Mapping B.

  • test.iat.Milkbad. IAT test blocks, Mapping A.

  • test.iat.Milkgood. IAT test blocks, Mapping B.

  • test.sc_dark.Darkbad. Dark SC_IAT test blocks, Mapping A.

  • test.sc_dark.Darkbad. Dark SC-IAT test blocks, Mapping B.

  • test.sc_milk.Milkbad. Milk SC-IAT test blocks, Mapping A.

  • test.sc_milk.Milkgood. Milk SC-IAT test blocks, Mapping B.

  • demo. Demographic questionnaire.

• response. Character registering the type of response for the demographic .

Summarize an SC-IAT D-score object

Description

Computes descriptive statistics for an object of class '"dsciat"'.

Usage

## S3 method for class 'dsciat'
summary(object, ...)

Arguments

Details

The summary includes the number of participants, the total number of trials considered for score computation, response-time means and standard deviations for Mapping A and Mapping B, accuracy means and standard deviations for Mapping A and Mapping B, and the mean and standard deviation of the SC-IAT D-score.

Value

An object of class '"summary_dsciat"'. The returned object is a list containing:

general

A data frame containing the total number of participants and the total number of trials.

statistics

A data frame containing the mean and standard deviation for response times, accuracies, and the SC-IAT D-score.

Examples

data("raw_data")

sciat_clean <- clean_sciat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  latency_id = "latency",
  accuracy_id = "correct",
  block_sciat_1 = c(
    "test.sc_dark.Darkbad",
    "test.sc_dark.Darkgood"
  ),
  block_sciat_2 = c(
    "test.sc_milk.Milkbad",
    "test.sc_milk.Milkgood"
  ),
  trial_id = "trialcode",
  trial_eliminate = c(
    "reminder",
    "reminder1"
  )
)

sciat_data <- sciat_clean[[1]]

sciat_dscore <- compute_sciat(
  sciat_data,
  mappingA = "test.sc_dark.Darkbad",
  mappingB = "test.sc_dark.Darkgood",
  non_response = "alert"
)

summary(sciat_dscore)

Summarize an IAT D-score object

Description

Computes descriptive statistics for an object of class '"dscore"'.

Usage

## S3 method for class 'dscore'
summary(object, ...)

Arguments

Details

The summary includes the number of participants, the total number of trials considered for score computation, response-time means and standard deviations for Mapping A and Mapping B, accuracy means and standard deviations for Mapping A and Mapping B, and the mean and standard deviation of the computed D-score.

Value

An object of class '"summary_dscore"'. The returned object is a list containing:

general

A data frame containing the total number of participants and the total number of trials.

statistics

A data frame containing the mean and standard deviation for response times, accuracies, and the D-score.

algorithm

The D-score algorithm identified from the score-column name.

Examples

data("raw_data")

iat_clean <- clean_iat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  mapA_practice = "practice.iat.Milkbad",
  mapA_test = "test.iat.Milkbad",
  mapB_practice = "practice.iat.Milkgood",
  mapB_test = "test.iat.Milkgood",
  latency_id = "latency",
  accuracy_id = "correct",
  trial_id = "trialcode",
  trial_eliminate = c(
    "reminder",
    "reminder1"
  ),
  demo_id = "blockcode",
  trial_demo = "demo"
)

iat_data <- iat_clean[[1]]

iat_dscore <- compute_iat(
  iat_data,
  Dscore = "d2"
)

summary(iat_dscore)

Summarize multiple IAT D-scores

Description

Computes descriptive statistics for an object of class '"multi_dscore"' containing multiple IAT D-scores.

Usage

## S3 method for class 'multi_dscore'
summary(object, ...)

Arguments

Details

The summary includes the total number of participants, the mean and standard deviation of each D-score algorithm, and the percentage of participants involved in at least one rank inversion across algorithms.

A rank inversion occurs when the relative ordering of two participants changes across at least two D-score algorithms.

Value

An object of class '"summary_multi_dscore"'. The returned object is a list containing:

general

A data frame containing the total number of participants, the number of participants involved in at least one rank inversion, and the percentage of participants involved in at least one rank inversion.

statistics

A data frame containing the mean and standard deviation of each D-score algorithm.

inversion_participants

A character vector containing the identifiers of participants involved in at least one rank inversion.

Examples

data("raw_data")

iat_clean <- clean_iat(
  raw_data,
  sbj_id = "Participant",
  block_id = "blockcode",
  mapA_practice = "practice.iat.Milkbad",
  mapA_test = "test.iat.Milkbad",
  mapB_practice = "practice.iat.Milkgood",
  mapB_test = "test.iat.Milkgood",
  latency_id = "latency",
  accuracy_id = "correct",
  trial_id = "trialcode",
  trial_eliminate = c(
    "reminder",
    "reminder1"
  ),
  demo_id = "blockcode",
  trial_demo = "demo"
)

iat_data <- iat_clean[[1]]

multiple_iat <- multi_dscore(
  iat_data,
  algorithms = "all"
)

summary(multiple_iat)