home - login - register

Journal Article Detail Page

Physical Review Physics Education Research
written by Elli J. Theobald, Melissa Aikens, Sarah L. Eddy, and Hannah Jordt
[This paper is part of the Focused Collection on Quantitative Methods in PER: A Critical Examination.] A common goal in discipline-based education research (DBER) is to determine how to improve student outcomes. Linear regression is a common technique used to test hypotheses about the effects of interventions on continuous outcomes (such as exam score) as well as control for student nonequivalence in quasirandom experimental designs. However, many types of outcome data cannot be appropriately analyzed with linear regression. In these instances, researchers must move beyond linear regression and implement alternative regression techniques. For example, student outcomes can be measured on binary scales (e.g., pass or fail), tightly bound scales (e.g., strongly agree to strongly disagree), or nominal scales (i.e., different discrete choices, for example, multiple tracks within a physics major), each necessitating alternative regression techniques. Here, we review extensions of linear modeling--generalized linear models (glms)--and specifically compare five glms that are useful for analyzing DBER data: logistic, binomial, proportional odds (also called ordinal; including censored regression), multinomial, and Poisson (including negative binomial, hurdle, and zero-inflated) regression. We introduce a diagnostic tool to facilitate a researcher's identification of the most appropriate glm for their own data. For each model type, we explain when, why, and how to implement the regression approach. When: we provide examples of the types of research questions and outcome data that would motivate this regression approach, including citations to articles in the DBER literature. Why: we name which linear regression assumption is violated by the data type. How: we detail implementation and interpretation of this modeling approach in R, including R syntax and code, and how to discuss the regression output in research papers. Code accompanying each analysis is linked within the paper.
Physical Review Physics Education Research: Volume 15, Issue 2, Pages 020110
Subjects Levels Resource Types
Education - Basic Research
- Research Design & Methodology
= Data
= Evaluation
= Statistics
General Physics
- Physics Education Research
Other Sciences
- Mathematics
- Graduate/Professional
- Reference Material
= Article
= Nonfiction Reference
PER-Central Type Intended Users Ratings
- PER Literature
- Researchers
- Professional/Practitioners
  • Currently 0.0/5

Want to rate this material?
Login here!


Formats:
application/pdf
text/html
Access Rights:
Free access
License:
This material is released under a Creative Commons Attribution 4.0 license.
Rights Holder:
American Physical Society
DOI:
10.1103/PhysRevPhysEducRes.15.020110
Keywords:
data-based research, predictive analysis, probabilistic model, statistical analysis, statistics
Record Creator:
Metadata instance created August 23, 2019 by Sam McKagan
Record Updated:
March 8, 2023 by Caroline Hall
Last Update
when Cataloged:
July 3, 2019
ComPADRE is beta testing Citation Styles!

Record Link
AIP Format
E. Theobald, M. Aikens, S. Eddy, and H. Jordt, , Phys. Rev. Phys. Educ. Res. 15 (2), 020110 (2019), WWW Document, (https://doi.org/10.1103/PhysRevPhysEducRes.15.020110).
AJP/PRST-PER
E. Theobald, M. Aikens, S. Eddy, and H. Jordt, Beyond linear regression: A reference for analyzing common data types in discipline based education research, Phys. Rev. Phys. Educ. Res. 15 (2), 020110 (2019), <https://doi.org/10.1103/PhysRevPhysEducRes.15.020110>.
APA Format
Theobald, E., Aikens, M., Eddy, S., & Jordt, H. (2019, July 3). Beyond linear regression: A reference for analyzing common data types in discipline based education research. Phys. Rev. Phys. Educ. Res., 15(2), 020110. Retrieved December 14, 2024, from https://doi.org/10.1103/PhysRevPhysEducRes.15.020110
Chicago Format
Theobald, E, M. Aikens, S. Eddy, and H. Jordt. "Beyond linear regression: A reference for analyzing common data types in discipline based education research." Phys. Rev. Phys. Educ. Res. 15, no. 2, (July 3, 2019): 020110, https://doi.org/10.1103/PhysRevPhysEducRes.15.020110 (accessed 14 December 2024).
MLA Format
Theobald, Elli J., Melissa Aikens, Sarah L. Eddy, and Hannah Jordt. "Beyond linear regression: A reference for analyzing common data types in discipline based education research." Phys. Rev. Phys. Educ. Res. 15.2 (2019): 020110. 14 Dec. 2024 <https://doi.org/10.1103/PhysRevPhysEducRes.15.020110>.
BibTeX Export Format
@article{ Author = "Elli J. Theobald and Melissa Aikens and Sarah L. Eddy and Hannah Jordt", Title = {Beyond linear regression: A reference for analyzing common data types in discipline based education research}, Journal = {Phys. Rev. Phys. Educ. Res.}, Volume = {15}, Number = {2}, Pages = {020110}, Month = {July}, Year = {2019} }
Refer Export Format

%A Elli J. Theobald %A Melissa Aikens %A Sarah L. Eddy %A Hannah Jordt %T Beyond linear regression: A reference for analyzing common data types in discipline based education research %J Phys. Rev. Phys. Educ. Res. %V 15 %N 2 %D July 3, 2019 %P 020110 %U https://doi.org/10.1103/PhysRevPhysEducRes.15.020110 %O application/pdf

EndNote Export Format

%0 Journal Article %A Theobald, Elli J. %A Aikens, Melissa %A Eddy, Sarah L. %A Jordt, Hannah %D July 3, 2019 %T Beyond linear regression: A reference for analyzing common data types in discipline based education research %J Phys. Rev. Phys. Educ. Res. %V 15 %N 2 %P 020110 %8 July 3, 2019 %U https://doi.org/10.1103/PhysRevPhysEducRes.15.020110


Disclaimer: ComPADRE offers citation styles as a guide only. We cannot offer interpretations about citations as this is an automated procedure. Please refer to the style manuals in the Citation Source Information area for clarifications.

Citation Source Information

The AIP Style presented is based on information from the AIP Style Manual.

The AJP/PRST-PER presented is based on the AIP Style with the addition of journal article titles and conference proceeding article titles.

The APA Style presented is based on information from APA Style.org: Electronic References.

The Chicago Style presented is based on information from Examples of Chicago-Style Documentation.

The MLA Style presented is based on information from the MLA FAQ.

Beyond linear regression: A reference for analyzing common data types in discipline based education research:

Is Part Of Focused Collection of Physical Review PER: Quantitative Methods in PER: A Critical Examination

A link to the full APS focused collection on quantitative methods in PER, published in 2019.

relation by Caroline Hall

Know of another related resource? Login to relate this resource to it.
Save to my folders

Contribute

Related Materials

Similar Materials