The Item Response Warehouse (IRW) is a collection of open, harmonized item response datasets.
Open: The data are licensed for reformatting and public reuse. Their provenance is documented and code used to transform original data to meet the IRW data standard is available.
Harmonized: The data are formatted to a common standard. The goal of the IRW is to make large quantities of data available for standardized analysis given the common formatting.
Item Response: The IRW is comprised of cross-classified item responses. The key element required of data for inclusion in the IRW is that the data need to report individual responses that are cross-classified by the focus of measurement (typically a person) and the measurement tool (typically an item).
These datasets in IRW span a wide range of measures; examples include measures of ability in education settings, measures of partisanship based on voting records, and personality measures based on survey questions. Responses can be scored in a variety of ways (dichotomous, polytomous, continuous) and may contain additional data (e.g., response time).
IRW Metadata
Examine sample sizes and other dataset summary statistics.
Code
metadata_trans =transpose(metadata)// selectors for x and y variablesvars =newMap([["Number responses","n_responses"], ["Number participants","n_participants"], ["Number items","n_items"], ["Responses per participant","responses_per_participant"], ["Responses per item","responses_per_item"], ["Density (#responses/(#ids*#items))","density"]])// vars = new Map(Object.entries(cont_vars))// console.log(Array.from(vars.values())[1])viewof x_var = Inputs.select(vars, {value:"n_items",label:"X axis"})viewof y_var = Inputs.select(vars, {value:"n_participants",label:"Y axis"})// selector for color variabledefault_color ="grey"color_opts =newMap([["None",null], ["Dichotomous vs. Polytomous","partition"]])viewof color_var = Inputs.select(color_opts, {label:"Color"})plt_color = color_var || default_color// histogramviewof metadata_hist = Plot.plot({// x: {type: "log"},y: {grid:true},color: {legend: color_var !=null},marks: [ Plot.rectY(metadata_trans, Plot.binX({y:"count"}, {x: x_var,fill: plt_color})), Plot.ruleY([0]) ]})// scatter plotviewof metadata_scatter = Plot.plot({x: {type:"log"},y: {type:"log"},grid:true,color: {legend: color_var !=null},marks: [// points Plot.dot(metadata_trans, {x: x_var,y: y_var,stroke: plt_color}),// tooltips Plot.tip(metadata_trans, Plot.pointer({x: x_var,y: y_var,stroke: plt_color,title:"dataset_name"})),// regression line Plot.linearRegressionY(metadata_trans, {x: x_var,y: y_var,stroke: plt_color}) ]})// display histogram and scatter plots side by sidehtml`<div style="display: flex;"> <div style="flex-basis:50%"> ${viewof metadata_hist} </div> <div style="flex-basis:50%"> ${viewof metadata_scatter} </div></div>`