Purpose: In an era of unprecedented student measurement and emphasis on data-driven educational decision making, the full potential for using data to target resources to students has yet to be realized. This study explores the utility of machine-learning techniques with large-scale administrative data to identify student dropout risk. Research…

Drawing on the self-system model, this study conceptualized school engagement as a multidimensional construct, including behavioral, emotional, and cognitive engagement, and examined whether changes in the three types of school engagement related to changes in problem behaviors from 7th through 11th grades (approximately ages 12-17). In addition,…

The purpose of this study was to examine student characteristics related to completing high school within four years, with particular emphasis on graduation outcomes for male and English language learner students. The authors looked at a cohort of students who began grade 9 in the 2007/08 school year in four Oregon districts. Factors related to…

Nineteen percent of 1997-98 North Carolina 3rd graders were observed to drop out of high school. A series of logits predict probabilities of dropping out on determinants such as math and reading test scores, absenteeism, suspension, and retention, at the following grade levels: 3rd, 5th, 8th, and 9th. The same cohort and variables are used to…

Educational success is often synonymous with attainment of academic qualifications. However for some students, simply continuing to attend school rather than dropping out may represent an important attainment, and completion of secondary school significantly reduces chances of subsequent chronic poverty. The longitudinal US NELS dataset was…

This study of high school outcomes in the Baltimore City Public Schools builds on substantial prior research on the early warning indicators of dropping out. It sought to investigate whether the same variables that predicted a non-graduation outcome in other urban districts--attendance, behavior problems, and course failure--were also significant…

Studies of student risk of school dropout have shown that present predictors of at-risk status do not accurately identify a large percentage of students who eventually drop out. Through the analysis of the entire Grade 1-12 longitudinal cohort-based grading histories of the class of 2006 for two school districts in the United States, the author…

This research brief provides highlights from the full report (published separately). In the report on AISD students, with a focus on the graduating class of 2009, the most powerful predictors of overall student dropout risk were having an 8th-grade attendance rate of less than 90% and failing both the 8th-grade reading and math TAKS tests. [For…

This study examined eighth grade predictor variables for predictive power in identifying students at-risk for dropping out of high school in a northwest Georgia school district. This study involved 340 participants from the 2005/2006 ninth grade class in the selected school district. This quantitative study employed correlation analyses to…

This prospective cohort study investigated whether leisure boredom predicts high school dropout. Leisure boredom is the perception that leisure experiences do not satisfy the need for optimal arousal. Participants completed a self-report questionnaire which included the Leisure Boredom Scale. The original cohort of grade 8 students (n=303) was…

In this report on AISD students, with a focus on the graduating class of 2009, the most powerful predictors of overall student dropout risk were having an 8th-grade attendance rate of less than 90% and failing both the 8th-grade reading and math TAKS tests. A separate research brief also was published. [For the research brief, see ED628171.]

Data from a population-based repository in Manitoba showed that students who are male, young for grade, and in Grades 1, 2, 7, and 8 were the most likely to be retained. After controlling for key student factors including socioeconomic status, school changes, and key school characteristics including stability of the student body, retention was a…

The 12th iteration of the International Conference on Educational Data Mining (EDM 2019) is organized under the auspices of the International Educational Data Mining Society in Montreal, Canada. The theme of this year's conference is EDM in Open-Ended Domains. As EDM has matured it has increasingly been applied to open-ended and ill-defined tasks…

This study extends previous research on the social psychological implications of pubertal timing to education by applying a life course framework to data from the National Longitudinal Study of Adolescent Health and from the Adolescent Health and Academic Achievement Study. Early pubertal timing, which has previously been associated with major…

Understanding and preventing high school failure is a national priority. Structural strain and general deviance theories attempt to explain late high school failure. The authors tested the hypotheses that general (vs. specific) deviance and academic competence mediate the relationships between structural strain factors (gender, ethnicity, and…