In tmsalab/ecdmdata: Data Sets for Psychometric Modeling

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "README-"
)

edmdata

The goal of edmdata R data package is to provide a set of assessment data sets for psychometric modeling.

Installation

The edmdata package is available on both CRAN and GitHub. The CRAN version is considered stable while the GitHub version is in a state of development and may break.

You can install the stable version of the edmdata package with:

#| label: cran-installation
#| eval: false
install.packages("edmdata")

For the development version, you can install the edmdata package from GitHub with:

#| label: gh-installation
#| eval: false

# install.packages("remotes")
remotes::install_github("tmsalab/edmdata")

Using data in the package

There are two ways to access the data contained within this package.

The first is to load the package itself and type the name of a data set. This approach takes advantage of R’s lazy loading mechanism, which avoids loading the data until it is used in R session. For details on how lazy loading works, please see Section 1.17: Lazy Loading of the R Internals manual.

# Load the `edmdata` package
library("edmdata")

# See the first 10 observations of the `items_revised_psvtr` dataset
head(items_revised_psvtr)

# View the help documentation for `items_revised_psvtr`
?items_revised_psvtr

The second approach is to use the data() command to load data on the fly without loading the package. After using data(), the data set will be available to use under the given name.

# Loading `items_revised_psvtr` without a `library(edmdata)` call
data("items_revised_psvtr", package = "edmdata")

# See the first 10 observations of the `items_revised_psvtr` dataset
head(items_revised_psvtr)

# View the help documentation for `items_revised_psvtr`
?items_revised_psvtr

Data Sets Included

#| echo: false
library(edmdata)

Examination for the Certificate of Proficiency in English (ECPE) [@Templin:2013:DCMECPE; @Templin:2014:HierarchicalDCM].
- items_ecpe: N = r nrow(items_ecpe) subject responses to J = r ncol(items_ecpe) items.
- qmatrix_ecpe: J = r nrow(qmatrix_ecpe) items and K = r ncol(qmatrix_ecpe) traits.
- TMSA Papers: @Culpepper:2019:ErRUM
Fraction Addition and Subtraction [@Tatsuoka:1984:FractionSubtraction; @Tatsuoka:2002:FractionSubtractionRelease].
- items_fractions: N = r nrow(items_fractions) subject responses to J = r ncol(items_fractions) items.
- qmatrix_fractions: J = r nrow(items_fractions) items and K = r ncol(items_fractions) traits.
- TMSA Papers: @Chen:2021:InferK, @Chen:2020:SLCMDC, @Culpepper:2019:EGDM, @Culpepper:2019:ErRUM, @Chen:2018:EDINA
Elementary Probability Theory [@Heller:2013:ProbabilityKS].
- items_probability_part_one_full: N = r nrow(items_probability_part_one_full) subject responses to J = r ncol(items_probability_part_one_full) items.
- items_probability_part_one_reduced: N = r nrow(items_probability_part_one_reduced) subject responses to J = r ncol(items_probability_part_one_reduced) items.
- qmatrix_probability_part_one: J = r nrow(qmatrix_probability_part_one) items and K = r ncol(qmatrix_probability_part_one) traits.
- TMSA Papers: @Chen:2021:InferK
Revised PSVT:R [@Yoon:2011:RevisedPSVTR; @Culpepper:2017:ChoiceIRT].
- items_revised_psvtr: N = r nrow(items_revised_psvtr) subject responses to J = r ncol(items_revised_psvtr) items.
- TMSA Papers: @Culpepper:2017:ChoiceIRT, @Culpepper:2015:BayesianDINA
Subset of Early Childhood Longitudinal Study, Kindergarten Class of 1998-1999's Approaches to Learning [@ECLSK:2010:ATLData].
- items_ordered_eclsk_atl: N = r nrow(items_ordered_eclsk_atl) subject responses to J = r ncol(items_ordered_eclsk_atl) items.
- TMSA Papers: @Culpepper:2019:EODM
Trends in International Mathematics and Science Study 2015 (TIMSS) Grade 8 Student Background Survey Item Responses [@TIMSS:2015:Background].
- items_ordered_timss15_background: N = r nrow(items_ordered_timss15_background) subject responses to J = r ncol(items_ordered_timss15_background) items.
Calculus-based probability and statistics course homework problems [@Culpepper:2014:SequentialIRT, @Jimenez:2023:OPGEDM]
- items_ordered_pswc_hw: N = r nrow(items_ordered_pswc_hw) subject responses to J = r ncol(items_ordered_pswc_hw) items.
Programme for International Student Assessment (PISA) 2012 U.S. Student Questionnaire Problem-Solving Vignettes [@Culpepper:2021:OHOEGDM].
- items_ordered_pisa12_us_vignette: N = r nrow(items_ordered_pisa12_us_vignette) subject responses to J = r ncol(items_ordered_pisa12_us_vignette) items.
Programme for International Student Assessment (PISA) 2012 U.S. Math Assessment.
- items_pisa12_us_math: N = r nrow(items_pisa12_us_math) subject responses to J = r ncol(items_pisa12_us_math) items.
Last Series of the Standard Progressive Matrices (SPM-LS) [@Raven:1941:SPM; @Myszkowski:2018:IRTSPMLS; @Robitzsch:2020:IRTRCLMSPMLS].
- items_spm_ls: N = r nrow(items_spm_ls) subject responses to J = r ncol(items_spm_ls) items.
Human Connectome Project's Penn Progressive Matrices Fluid Intelligence Assessment
- items_hcp_penn_matrix: N = r nrow(items_hcp_penn_matrix) subject responses to J = r ncol(items_hcp_penn_matrix) items.
- items_hcp_penn_matrix_missing: N = r nrow(items_hcp_penn_matrix_missing) subject responses with missing data indicators to J = r ncol(items_hcp_penn_matrix_missing) items.
Experimental Matrix Reasoning Test [@OpenPsychometrics:2012:IQ1].
- items_matrix_reasoning: N = r nrow(items_matrix_reasoning) subject responses to J = r ncol(items_matrix_reasoning) items.
- TMSA Papers: @Chen:2020:SLCMDC
Taylor Manifest Anxiety Scale [@Taylor:1953:TMI; @OpenPsychometrics:2012:TaylorAnxietyScale].
- items_taylor_manifest_anxiety_scale: N = r nrow(items_taylor_manifest_anxiety_scale) subject responses to J = r ncol(items_taylor_manifest_anxiety_scale) items.
Narcissistic Personality Inventory [@Raskin:1988:NPI; @OpenPsychometrics:2013:NPI].
- items_narcissistic_personality_inventory: N = r nrow(items_narcissistic_personality_inventory) subject responses to J = r ncol(items_narcissistic_personality_inventory) items.
Pre-generated identified Q matrices.
- qmatrix_oracle_k2_j12: 12 items and 2 traits.
- qmatrix_oracle_k3_j20: 20 items and 3 traits.
- qmatrix_oracle_k4_j20: 20 items and 4 traits.
- qmatrix_oracle_k5_j30: 30 items and 5 traits.
Pre-generated strategy sets.
- strategy_oracle_k3_j20_s2: 20 items, 3 traits, and 2 strategies.
- strategy_oracle_k3_j30_s2: 30 items, 3 traits, and 2 strategies.
- strategy_oracle_k3_j40_s2: 40 items, 3 traits, and 2 strategies.
- strategy_oracle_k3_j50_s2: 50 items, 3 traits, and 2 strategies.
- strategy_oracle_k4_j20_s2: 20 items, 4 traits, and 2 strategies.
- strategy_oracle_k4_j30_s2: 30 items, 4 traits, and 2 strategies.
- strategy_oracle_k4_j40_s2: 40 items, 4 traits, and 2 strategies.
- strategy_oracle_k4_j50_s2: 50 items, 4 traits, and 2 strategies.

Build Scripts

Want to see how each data set was imported? Check out the data-raw folder!

Authors

James Joseph Balamuta, Steven Andrew Culpepper, Jeffrey Douglas

Citing the `edmdata` package

To ensure future development of the package, please cite edmdata package if used during an analysis or simulation study. Citation information for the package may be acquired by using in R: