NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED205146
Record Type: RIE
Publication Date: 1980
Pages: 14
Abstractor: N/A
Reference Count: 0
ISBN: N/A
ISSN: N/A
Analysis and Classification of Entering Freshmen Mathematic Students Using Multiple Discriminate Function Analysis.
Ahrens, Steve
Predictor variables that could be used effectively to place entering freshmen methematics students into courses of instruction in mathematics were investigated at West Virginia University. Multiple discriminant analysis was used with nearly 6,000 student records collected over a three-year period, and a series of predictive equations were generated and later cross-validated. Beginning in August 1977 all incoming freshmen students who indicated an interest in mathematics in their registration packet were administered a one-hour timed departmental exam in mathematics. The exam consisted of 36 multiple choice questions divided into three sections of 12 questions each. The first section tested for knowledge of basic algebra; the second section tested for knowledge of trigonometry and analytic geometry; and the third section tested for knowledge of solid analytic geometry and the calculus of a single variable. At the end of the fall 1977 semester, grades for the students in the various mathematics courses were obtained and matched to the earlier individual test scores. Additionally the students' high school backgrounds in mathematics and the recommendations of the students' advisor were obtained, along with American College Testing program scores. Even before completion of the study, the prediction equations appeared to discriminate among the groups effectively (advisor recommendations were dropped from the analysis). The two best predictor variables were high school background and the grade on a departmental examination. (SW)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers: West Virginia University
Note: Paper presented at the Annual Meeting of the Southern Association of Institutional Research (Louisville, KY, Fall 1980).