|
Activity Number:
|
303
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2003 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Education
|
| Abstract - #301211 |
|
Title:
|
Identifying Predictors of Student Performance in an Introductory Statistics Course
|
|
Author(s):
|
Felicity T. Boyd*+ and Marie Diener-West
|
|
Companies:
|
Johns Hopkins University and Johns Hopkins University
|
|
Address:
|
Department of Biostatistics, School of Public Health, Baltimore, MD, 21205,
|
|
Keywords:
|
statistical education ; educational research
|
|
Abstract:
|
Identifying predictors of student performance in an introductory statistics may help instructors tailor educational materials to better suit individual student needs. 255 consenting students in an introductory statistics course for public health graduate students completed a survey on prior knowledge and skills and demographic information at the start of a 16-week course. Males were more likely to report belief that they could learn statistics than females, despite similarities by gender on other characteristics. Results of a multivariable generalized linear model indicated that after adjustment course examination scores (on a 400-point scale) were improved by the following: 5.6 points for each point of a 10-point prior statistical knowledge scale (95% CI: 3.3, 7.9); 8.6 points for each point of a 5-point mathematical skill scale (95% CI: 4.5, 12.7); and 6.6 points for each point of a 5-point likert scale reflecting lower reported need for a tutor (95% CI: 2.0, 11.2). In addition, younger age and employment were associated with higher course examination scores, and positive effect modification was observed between age and mathematical skill and between age and employment.
|
