A Multilevel Matched-Pair Analysis to Determine the Effect of Instruction Modality on Student Success and Course Satisfaction Ratings

• Activity Number: 256
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Education
• Author(s): Lori Thombs* and Kim Siegenthaler and Paula McFarling and Nai-En Tang
• Companies: University of Missouri and University of Missouri and University of Missouri and University of Missouri
• Keywords: education ; consulting ; online vs face-to-face ; multilevel models ; teaching modality

Abstract

This interdisciplinary research represents a collaborative effort between the MU Social Science Statistics Center, Mizzou Online and the Assessment Resource Center, and compares online and traditional face to face (f2f) modalities of instruction. Data on courses offered both online and f2f, and by the same instructor, were gathered for 102 matched courses and the 36K enrolled students. Taking advantage of the unique "matched-by-instructor" and multilevel features of the data, we compare student success attributes and instructor characteristics by class modality. Multilevel modeling techniques that incorporate both the demographic and academic variables from the student-level data, as well as the instructor-level attributes are used to determine which student and instructor characteristics correlate with success in online versus face-to-face class formats.