ERIC Number: ED235228
Record Type: RIE
Publication Date: 1983-Apr-13
Reference Count: 0
A Time Series Approach to the Longitudinal Study of Undergraduate Grades.
Rogers, Bruce G.
During the past 15 years, considerable attention has been given to a conspicuous longitudinal change in grading patterns in higher education. Commonly referred to as "grade inflation," the phenomenon has been perceived by some as seriously weakening the meaning of grades but by others as reflecting a positive tendency for students to select those courses which reflect their own ability. Researchers have continued to study the trends, but no models have yet been presented which explain the variations, across an extended time period, in terms of measurable independent variables. It was the purpose of this study to search for an explanatory model of longitudinal collegiate grade point average (GPA) data, using a time series methodological approach. Fifty-three years of GPA data from a midwestern university were analyzed with exogenous variables (changes in student ability, enrollment level, sex distribution, and the national economic status) and endogenous lagged variables. Only the enrollment level was found capable of explaining any significant part of grade variation. It was concluded that short term ex post facto studies may have limited value unless independent variables can be shown to have longitudinal explanatory power. (Author/PN)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Authoring Institution: N/A
Identifiers: Time Series Analysis; Time Series Design
Note: Paper presented at the Annual Meeting of the National Council on Measurement in Education (Montreal, Quebec, April 12-14, 1983).