Identifies datasets in the Item Response Warehouse (IRW) based on user-defined criteria. This function filters datasets using precomputed metadata, which contains summary statistics for each dataset (e.g., number of responses, number of participants, density scores, etc.), as well as tag-based metadata (e.g., age range, construct type, sample type, etc.).
Usage
irw_filter(
n_responses = NULL,
n_categories = NULL,
n_participants = NULL,
n_items = NULL,
responses_per_participant = NULL,
responses_per_item = NULL,
density = c(0.5, 1),
var = NULL,
age_range = NULL,
child_age__for_child_focused_studies_ = NULL,
construct_type = NULL,
sample = NULL,
measurement_tool = NULL,
item_format = NULL,
primary_language_s_ = NULL,
longitudinal = NULL
)
Arguments
- n_responses
Numeric vector of length 2 specifying range for total responses.
- n_categories
Numeric vector of length 2 specifying range for unique response categories.
- n_participants
Numeric vector of length 2 specifying range for number of participants.
- n_items
Numeric vector of length 2 specifying range for number of items.
- responses_per_participant
Numeric vector of length 2 specifying range for avg responses per participant.
- responses_per_item
Numeric vector of length 2 specifying range for avg responses per item.
- density
Numeric vector of length 2 specifying range for data density. Default
c(0.5, 1)
; disable withNULL
.- var
A character vector specifying one or more variables. For a list of available variables, see: https://datapages.github.io/irw/standard.html - If exact variable names are provided, only datasets containing all specified variables will be returned. - If a variable name contains an underscore (e.g.,
"cov_"
,"Qmatrix_"
), the function will match all datasets that contain at least one variable that starts with that prefix.- age_range
Character value specifying the age group of participants (e.g., "Adult (18+)", "Child (<18y)").
- child_age__for_child_focused_studies_
Character value indicating the age group for child-focused studies (e.g., "Early (<6y)").
- construct_type
Character value specifying the psychological or educational construct being measured.
- sample
Character value specifying the sample type or recruitment method (e.g., "Educational", "Clinical").
- measurement_tool
Character value specifying the type of instrument used for measurement (e.g., "Survey/questionnaire").
- item_format
Character value describing the format of the items (e.g., "Likert Scale/selected response").
- primary_language_s_
Character value indicating the primary language(s) used in the instrument.
- longitudinal
Logical or NULL. If TRUE, returns only longitudinal datasets (i.e., those with variables like 'wave' or 'date'). If FALSE, excludes those datasets. If NULL (default), includes all datasets.
Value
Sorted character vector of dataset names matching all specified criteria or empty if none found.
Details
Exploring Metadata and Tags
To understand available dataset properties before filtering, run summary(irw_metadata())
.
To explore tag-based metadata, use irw_tags()
to view the full tags table.
To see the valid values for a specific tag column (e.g., "age_range"), use:
irw_tag_options("column_name")
Examples
if (FALSE) { # \dontrun{
irw_filter(n_responses = c(1000, Inf), var = "rt")
irw_filter(var = "wave", density = NULL)
irw_filter(n_participants = c(500, Inf), density = c(0.3, 0.8))
irw_filter(var = c("treat", "rt", "cov_"), density= NULL)
# View valid options for a tag column
irw_tag_options("construct_type")
irw_filter(construct_type = "Affective/mental health")
} # }