Test Score Gap Robustness to Scaling : The Scale Transformation Command

Social scientists frequently rely on the cardinal comparability of test scores to assess achievement gaps between population subgroups and their evolution over time. This approach has been criticized due to the ordinal nature of test scores and th...

Full description

Bibliographic Details
Main Author:	Chang, Andres Yi
Format:	Working Paper
Language:	English
Published:	World Bank, Washington, DC 2019
Subjects:	TEST SCORES STUDENT ACHIEVEMENT PSYCHOMETRICS STATA SCALE TRANSFORMATION ACHIEVEMENT GAPS EDUCATION MEASUREMENT ABILITY
Online Access:	http://documents.worldbank.org/curated/en/942501566218257874/Test-Score-Gap-Robustness-to-Scaling-The-Scale-Transformation-Command http://hdl.handle.net/10986/32311

id	okr-10986-32311
recordtype	oai_dc
spelling	okr-10986-323112022-08-15T00:16:22Z Test Score Gap Robustness to Scaling : The Scale Transformation Command Chang, Andres Yi TEST SCORES STUDENT ACHIEVEMENT PSYCHOMETRICS STATA SCALE TRANSFORMATION ACHIEVEMENT GAPS EDUCATION MEASUREMENT ABILITY Social scientists frequently rely on the cardinal comparability of test scores to assess achievement gaps between population subgroups and their evolution over time. This approach has been criticized due to the ordinal nature of test scores and the sensibility of results to order-preserving transformations, which are theoretically plausible. Bond and Lang (2013) document the sensitivity of measured ability to scaling choices and develop a method to assess the robustness of changes in ability over time to scaling choices. This paper presents the scale transformation command, which expands the Bond and Lang method to more general cases and optimizes their algorithm to work with large data sets. The program assesses the robustness of an achievement gap between two subgroups to any arbitrary choice of scale by finding bounds for the original gap estimation. Additionally, the program finds scale transformations that are very likely and unlikely to benchmark against the results obtained. Finally, the program also allows the user to measure how much gap growth coefficients change when including controls in their specifications. 2019-08-22T15:55:45Z 2019-08-22T15:55:45Z 2019-08 Working Paper http://documents.worldbank.org/curated/en/942501566218257874/Test-Score-Gap-Robustness-to-Scaling-The-Scale-Transformation-Command http://hdl.handle.net/10986/32311 English Policy Research Working Paper;No. 8986 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper
repository_type	Digital Repository
institution_category	Foreign Institution
institution	Digital Repositories
building	World Bank Open Knowledge Repository
collection	World Bank
language	English
topic	TEST SCORES STUDENT ACHIEVEMENT PSYCHOMETRICS STATA SCALE TRANSFORMATION ACHIEVEMENT GAPS EDUCATION MEASUREMENT ABILITY
spellingShingle	TEST SCORES STUDENT ACHIEVEMENT PSYCHOMETRICS STATA SCALE TRANSFORMATION ACHIEVEMENT GAPS EDUCATION MEASUREMENT ABILITY Chang, Andres Yi Test Score Gap Robustness to Scaling : The Scale Transformation Command
relation	Policy Research Working Paper;No. 8986
description	Social scientists frequently rely on the cardinal comparability of test scores to assess achievement gaps between population subgroups and their evolution over time. This approach has been criticized due to the ordinal nature of test scores and the sensibility of results to order-preserving transformations, which are theoretically plausible. Bond and Lang (2013) document the sensitivity of measured ability to scaling choices and develop a method to assess the robustness of changes in ability over time to scaling choices. This paper presents the scale transformation command, which expands the Bond and Lang method to more general cases and optimizes their algorithm to work with large data sets. The program assesses the robustness of an achievement gap between two subgroups to any arbitrary choice of scale by finding bounds for the original gap estimation. Additionally, the program finds scale transformations that are very likely and unlikely to benchmark against the results obtained. Finally, the program also allows the user to measure how much gap growth coefficients change when including controls in their specifications.
format	Working Paper
author	Chang, Andres Yi
author_facet	Chang, Andres Yi
author_sort	Chang, Andres Yi
title	Test Score Gap Robustness to Scaling : The Scale Transformation Command
title_short	Test Score Gap Robustness to Scaling : The Scale Transformation Command
title_full	Test Score Gap Robustness to Scaling : The Scale Transformation Command
title_fullStr	Test Score Gap Robustness to Scaling : The Scale Transformation Command
title_full_unstemmed	Test Score Gap Robustness to Scaling : The Scale Transformation Command
title_sort	test score gap robustness to scaling : the scale transformation command
publisher	World Bank, Washington, DC
publishDate	2019
url	http://documents.worldbank.org/curated/en/942501566218257874/Test-Score-Gap-Robustness-to-Scaling-The-Scale-Transformation-Command http://hdl.handle.net/10986/32311
_version_	1764476268836814848

Test Score Gap Robustness to Scaling : The Scale Transformation Command

Similar Items