We propose a novel approach to address the issue of college student attrition by developing a hybrid model that combines a structural neural network with a piecewise exponential model. This hybrid model not only shows the potential to robustly identify students who are at high risk of dropout, but also provides insights into which factors are most…

This paper combines a theoretical-based model with a data-driven approach to develop an Early Warning System that detects students who are more likely to dropout. The model uses innovative multilevel statistical and machine learning methods. The paper demonstrates the validity of the approach by applying it to administrative data from a leading…

Examined dropping out of school in four schools in Israel. Found significant differences in attitudes of persistent students and dropouts even before act of dropping out occurred. In vocational, comprehensive, and agricultural schools, dropouts scored more positively than persistent students on Anderson's Alienation Scales: self-estrangement,…

As a response to legislative demands, the Texas School Dropout Survey described in this document attempted to identify the magnitude of the dropout problem, regional characteristics or causes of the problem, costs associated with dropping out, and programs currently available for serving the dropout population. Twenty-four major findings of the…

Administered Self-Directed Search to 596 American Indian high school students, 168 of whom dropped out during the time frame of the study. Found above average dropout rates for girls with Realistic and Social interest preferences. Boys with Enterprising codes had above average dropout rates. Lowest dropout rates were for girls with Investigative…

A sample of dropouts is surveyed to determine their reasons for dropping out of school and to assess the factors currently used by the Dade County (Florida) school system to identify at-risk students. Data from telephone surveys of a randomly-selected sample of 2,779 persons who dropped out of grades 7 through 12 during 1986-87, 1987-88, and…

Presented in this annotated bibliography of 12 publications on students at risk are descriptions of (1) a study of 100 Austin, Texas, dropouts that identifies characteristics and conditions of high-risk students; (2) a study recommending a variety of programs to improve the progression of high-risk high school and college students; (3) a manual…

This study examined the Stratil Counseling Inventory (SCI) used for identifying college freshmen prone to dropping out and a program designed to increase student retention which stresses early, frequent, and rewarding faculty-student contact. The SCI was administered to college freshmen (N=213) who became involved in a retention management program…

A FIVE-YEAR LONGITUDINAL STUDY WAS CONDUCTED OF 1550 CHILDREN, 384 OF WHOM WERE INTENSIVELY STUDIED AFTER BEING IDENTIFIED BY THEIR TEACHERS AS DEMONSTRATING SOCIALLY APPROVED OR SOCIALLY DISAPPROVED BEHAVIOR. AFTER 5 YEARS, THE SOCIALLY DISRUPTIVE GROUP OF 192 STUDENTS WAS LOWER IN ACADEMIC ACHIEVEMENT AND SOCIAL ADJUSTMENT THAN THEIR APPROVED…