go-v.orgdoi

Explanatory and Predictive Modeling Within Improvement Science Projects

Andrew E. Krumm · American Educational Research Association Annual Meeting (AERA) · 2019

  • DOI 10.3102/1440887
  • Publisher OpenAlex
  • Type conference-paper
  • Issued 2019

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

American Educational Research Association Annual Meeting (AERA) · OpenAlex · conference-paper · 2019

Abstract

This paper explores the role of explanatory and predictive modeling within a large-scale, networked improvement community called the Carnegie Math Pathways.Drawing on multiple data sources from across multiple years, we demonstrate how both explanatory and predictive models helped in understanding what it means to be a successful student and learner in the Pathways.

PurposeA key aspect of using data for improvement is developing, tracking, and creating change ideas around predictive measures (Langley et al., 2009).In this paper, we describe the ways in which we drew on machine learning techniques to develop predictive measures and models of student success within the Carnegie Math Pathways (i.e., "Pathways").The Pathways is a networked improvement community (NIC) that was launched by the Carnegie Foundation for the Advancement of Teaching, currently resides at WestEd, and across both organizations, has been addressing the developmental math crisis in the United States.In helping students earn college-level mathematics credit, the Pathways represents a systems-focused approach that addresses, for example, quality curriculum, coherent professional learning opportunities, and explicit credit-earning pathways (Yamada & Bryk, 2016).

Open the resolved locator · 10.3102/1440887

Metadata licence: OpenAlex metadata (CC0)

Registry
OpenAlex DOI index + API
Fetched
2026-11-19 21:26 UTC
Cache state
not cached yet (bulk-index+openalex)
Locator
https://convention2.allacademic.com/one/aera/portal
Metadata licence
OpenAlex metadata (CC0)
Scope
Metadata as returned by the resolver; abstracts are never generated here.