PDF pending restoration
ERIC Number: ED175367
Record Type: RIE
Publication Date: 1979-Apr
Reference Count: 0
Path Analysis: The Development of a Suitable Methodology for the Study of Student Attrition.
Bean, John P.
The shortcomings of current research on student attrition are reviewed, and ways are described in which multiple regression, path analysis, and a recursive causal model can be used to better understand attrition. A review of the research shows that past theoretical models lack an adequate definition of variables which have resulted in their being unsuitable for path analysis, or combined in single regression variables which are temporally ordered. A causal model is proposed that contains background variables, organizational determinants, intervening variables, personal determinants, environmental determinants, and a dependent variable. Additionally, the model takes into account a set of control variables used both to select a homogeneous subpopulation and to test for an interaction effect in the data set. Each of the causal model elements are discussed and two problems with the model are noted. A graphic illustration of the causal model is provided, along with an extensive bibliography, and a glossary of the variables. (Author/PHR)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the American Educational Research Association (San Francisco, California, April 1979)