Asee peer logo

Latent variable modeling with applications to education assessment and NSF-REU projects for engineering students

Download Paper |


2017 Mid-Atlantic Section Fall Conference


Penn State University - Berks Campus - Reading, Pennsylvania

Publication Date

October 6, 2017

Start Date

October 6, 2017

End Date

October 7, 2017

Conference Session

Mid Atlantic Papers

Tagged Topic

Mid-Atlantic Section Fall Conference

Page Count




Permanent URL

Download Count


Request a correction

Paper Authors


Tak Cheung

visit author page

Tak Cheung, Ph.D., professor of physics, teaches in CUNY Queensborough Community College. He also conducts research and mentors student research projects.

visit author page


sunil Dehipawala Queensborough Community College

visit author page

Sunil Dehipawala received his B.S. degree from University of Peradeniya in Sri Lanka and Ph.D from City University of New York. Currently, he is working as a faculty member at Queensborough Community College of CUNY.

visit author page


Rex Taibu

visit author page

Dr. Rex Taibu has taught studio physics classes for several years. His teaching experience has shaped his research focus. Currently, Dr. Taibu is actively engaged in

1) promoting scientific inquiry attitudes in students through designing, implementing, and assessing innovative inquiry based physics labs.

2) conducting research regarding the role of language in conceptual understanding.

3) exploring cosmic rays (detection, data collection, and analysis).

visit author page


Vazgen Shekoyan

visit author page

Dr. Vazgen Shekoyan is a professor of physics and his experiences include pedagogy, CubeSat, etc.

visit author page

Download Paper |


The latent variable modeling technique in education assessment is illustrated using problem solving examples in first semester physics for engineering and technology students. The regression modeling of data in the Newton second law laboratory class has equivalence to an analysis with the internal force serving as the latent variable. A path diagram would contain the internal force as a latent variable which manifest its influence on the observed datasets, namely, acceleration and force. Similarly, the pre-score and post-score data collected for education assessment can be studied with latent variable modeling to broaden the scope beyond regression which requires an independent variable. The numerical and flexibility advantages of latent variable modeling versus regression modeling in education assessment are presented. Free LISREL student version working details and free confirmatory factor analysis Microsoft Excel software from university faculty are presented. The adaptation of Queensborough Community College Physics faculty education research into Queensborough NSF-REU projects for engineering students is discussed.

Cheung, T., & Dehipawala, S., & Taibu, R., & Shekoyan, V. (2017, October), Latent variable modeling with applications to education assessment and NSF-REU projects for engineering students Paper presented at 2017 Mid-Atlantic Section Fall Conference, Penn State University - Berks Campus - Reading, Pennsylvania. 10.18260/1-2--29384

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2017 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015