Translating sophisticated data analytic strategies regarding school attendance and absenteeism into targeted educational policy

School attendance and absenteeism are critical targets of educational policies and practices that often depend heavily on aggregated attendance/absenteeism data. School attendance/absenteeism data in aggregated form, in addition to having suspect quality and utility, minimizes individual student var...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Improving schools Ročník 26; číslo 1; s. 5 - 22
Hlavní autoři: Kearney, Christopher A., Childs, Joshua
Médium: Journal Article
Jazyk:angličtina
Vydáno: London, England SAGE Publications 01.03.2023
Témata:
Algorithms
Attendance
Causal Models
Data Analysis
Data Collection
Educational Policy
Identification
Multi Tiered Systems of Support
school attendance
school absenteeism
educational policy
data mining
model-based analyses
Algorithm-based analyses
early warning system
multi-tiered systems of support
root cause analysis
ISSN:1365-4802, 1475-7583
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:School attendance and absenteeism are critical targets of educational policies and practices that often depend heavily on aggregated attendance/absenteeism data. School attendance/absenteeism data in aggregated form, in addition to having suspect quality and utility, minimizes individual student variation, distorts detailed and multilevel modeling, and obscures underlying causes and disparities of absenteeism. Recent advances in data analytics/mining and modeling may assist researchers and other stakeholders by evaluating large-scale data sets in more targeted ways to identify key root causes and patterns of school absenteeism in a particular community, school, or group of students. This would allow for more accurate educational policies tailored to unique local conditions and student/family circumstances. This article provides a summary of recent algorithm- and model-based efforts in this regard. Algorithm-based efforts include classification and regression tree analysis, ensemble analysis, support vector machines, receiver operating characteristic analysis, and random forests. Model-based efforts include multilevel modeling, structural equation modeling, latent class analysis, and meta-analytic modeling. We then illustrate how these efforts can enhance a full and nuanced understanding of the root, interconnected causes of absenteeism, improve early warning systems, and assist multi-tiered systems of support interventions for absenteeism.
ISSN:1365-4802
1475-7583
DOI:10.1177/13654802231174986