A Dropout Prediction Model That Highlights Middle Level Variables

Belcher, Don; Hatley, Richard V.

doi:10.1080/10825541.1994.11670032

Cited by 8 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, the life course perspective posits that the school is the main influence on these students (rather than family or outside influences), and this is supported here by the significant negative impact of the student-teacher ratio variable in the slopes part of the model for the Low-Increasing students. Additionally, while we can only make a tentative claim at this point, it may be that the Low-Increasing students are also the students most affected by the well studied problematic transition from grade 8 to grade 9 (Allensworth & Easton, 2007;Belcher & Hatley, 1994;Benner & Graham, 2009;Bowers, 2010b;Rumberger, 1995;Zvoch, 2006), since they begin with the lowest average grades of the different trajectories. In contrast, in-line with the hypothesis that the Mid-Decreasing students are the "unexpected" dropouts that past dropout identification methods have failed to identify early as at risk of dropping out, a significant portion of the variance in the intercepts (20%) is explained by the background variables.…”

Section: Growth Model Trajectoriesmentioning

confidence: 91%

Examining the Multiple Trajectories Associated with Dropping Out of High School: A Growth Mixture Model Analysis

Bowers

Sprott

2012

The Journal of Educational Research

View full text Add to dashboard Cite

Historically, students who fail to graduate from secondary school are considered as a single category of school dropouts. However, emerging literature indicates that there may be multiple subgroups of high school dropouts, termed dropout typologies. The purpose of this study was to assess the extent to which different typologies of dropouts were present in a large national dataset, and to estimate the influence of the known covariates of dropping out on each of the subgroups. A growth mixture model was estimated using the ELS:2002 dataset and non-cumulative GPA during the first three semesters of high school. The model identified two main subgroups associated with dropping out which accounted for 24.6% of the sample but contained 91.8% of the dropouts.

show abstract

Section: Growth Model Trajectoriesmentioning

confidence: 91%

Examining the Multiple Trajectories Associated with Dropping Out of High School: A Growth Mixture Model Analysis

Bowers

Sprott

2012

The Journal of Educational Research

View full text Add to dashboard Cite

show abstract

“…Commonly used demographic variables in student risk prediction include race/ethnicity, whether a student's family home language is the local language of schooling (i.e., English as a Second Language/ESL status in the United States and United Kingdom), Special Education status (a classification for students diagnosed with certain disabilities, Belcher & Hatley, 1994), free or reduced price meal eligibility (an imperfect proxy for poverty, Domina et al 2018). Less commonly, variables such as homelessness status (Hyman et al, 2011), mobility (Goldhaber et., 2022), and military-connected status (Baker et al, 2020) are also used.…”

Section: Defining What a Demographic Variable Ismentioning

confidence: 99%

Using Demographic Data as Predictor Variables: a Questionable Choice

Baker¹,

Esbenshade²,

Vitale³

et al. 2022

Preprint

View full text Add to dashboard Cite

Predictive analytics methods in education are seeing widespread use and are producing increasingly accurate predictions of students’ outcomes. With the increased use of predictive analytics comes increasing concern about fairness for specific subgroups of the population. One approach that has been proposed to increase fairness is using demographic variables directly in models, as predictors. In this paper we explore issues of fairness in the use of demographic variables as predictors of long term student outcomes, studying the arguments for and against this practice. We analyze arguments for the inclusion of demographic variables, specifically claims that this approach improves model performance and concerns around ‘color-blind’ racism in this modeling approach. We also consider arguments against including demographic variables as predictors, including reduced actionability of predictions, risk of reinforcing bias, and limits of categorization. We then discuss how contextual factors of predictive models should influence case-specific decisions for the inclusion or exclusion of demographic variables and discuss the role of proxy variables. We conclude that, on balance, there are greater benefits to fairness if demographic variables are used to validate fairness rather than as predictors within models.

show abstract

“…Research suggests that not only should dropout prevention efforts begin early, but also they should continue across periods of transition and be sustained over time. Significant numbers of students begin to leave school as early as seventh grade (Bakken & Kortering, 1999;Belcher & Hatley, 1994;Christenson & Thurlow, 2004;Jennings, 1989). Young adolescents moving from middle to high school experience a more competitive and grade-oriented environment and may feel inadequate to make academic and extracurricular decisions, which may have a significant impact on their futures (Mizelle, 2005).…”

Section: Purpose Of the Studymentioning

confidence: 99%

An Investigation of Transition Practices for Middle School Youth

Weidenthal

Kochhar-Bryant

2007

Career Development for Exceptional Individuals

View full text Add to dashboard Cite

The Individuals with Disabilities Education Improvement Act of 2004 (IDEIA 2004) shifted the requirement to initiate transition services from age 14 back to age 16, a change with significant implications for middle school students with disabilities transitioning into high school. This study, based on practices under the Amendments to IDEA 1997 regulations, employed a survey and open-ended interviews to investigate transition practices of special education teachers who instructed eighth- and ninth-grade adolescents with learning disabilities (LD). The study focused on (a) student participation at Individualized Education Program (IEP) meetings, (b) strengths considered in IEP development, and (c) transition service needs focusing on a course of study. Findings demonstrated the significance of self-determination training and its application in the IEP process by the age of 14; reliance on assessments of students' strengths and needs, which include informal measures and information from family members; and teachers' support for long-range, coordinated transition planning for students beginning no later than middle school.

show abstract

A Dropout Prediction Model That Highlights Middle Level Variables

Cited by 8 publications

References 2 publications

Examining the Multiple Trajectories Associated with Dropping Out of High School: A Growth Mixture Model Analysis

Examining the Multiple Trajectories Associated with Dropping Out of High School: A Growth Mixture Model Analysis

Using Demographic Data as Predictor Variables: a Questionable Choice

An Investigation of Transition Practices for Middle School Youth

Contact Info

Product

Resources

About