Representational similarity and regression analyses: A comparative simulation study

Poster No:

1616 

Submission Type:

Abstract Submission 

Authors:

Chuanji Gao1, Svetlana Shinkareva2, Rutvik Desai2

Institutions:

1Nanjing Normal University, Nanjing, China, 2University of South Carolina, Columbia, SC

First Author:

Chuanji Gao  
Nanjing Normal University
Nanjing, China

Co-Author(s):

Svetlana Shinkareva  
University of South Carolina
Columbia, SC
Rutvik Desai, PhD  
University of South Carolina
Columbia, SC

Introduction:

Both representational similarity analysis (RSA) and regression approaches are widely used in psychology and neuroscience research for model selection. RSA offers several advantages, including the flexibility to relate models, brain regions, subjects, species, and behavior, making it a valuable analytical framework. However, the reliability and power of RSA, as compared to traditional regression approaches, has not been examined.

Methods:

In this study, we compared the finite sampling behavior of RSA and linear regression. We generated data using a linear regression model with known population parameters and repeatedly drew samples of size N from the population. The sampling distribution for each population parameter was estimated by aggregating the parameter estimates across all samples.

For RSA, the parameter of interest was the correlation coefficient between the dissimilarities of Y and X. For linear regression, the parameter of interest was the adjusted R². We calculated the percentage of correct model selections across 1,000 replications.

Results:

Our findings indicate that regression yielded a higher percentage of correct model selections than RSA when the number of trials was small (but larger than the number of features). The percentage of correct model selections increased with the sample size (number of stimuli) for both regression and RSA; however, regression consistently outperformed RSA until both methods reached a performance ceiling.

Similar patterns were observed for simulated fMRI datasets.

Conclusions:

These results suggest that while RSA is a powerful and versatile analysis technique, researchers should carefully consider the choices of RSA and regression approaches in contexts where both are applicable. Model selection based solely on RSA can be less reliable, providing potentially misleading results.

Modeling and Analysis Methods:

Multivariate Approaches 1
Univariate Modeling 2

Keywords:

Data analysis
FUNCTIONAL MRI
Multivariate
Statistical Methods
Univariate

1|2Indicates the priority used for review

Abstract Information

By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.

I accept

The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:

I am submitting this abstract as an original work to be reproduced. I am available to be the “source party” in an upcoming team and consent to have this work listed on the OSSIG website. I agree to be contacted by OSSIG regarding the challenge and may share data used in this abstract with another team.

Please indicate below if your study was a "resting state" or "task-activation” study.

Other

Healthy subjects only or patients (note that patient studies may also involve healthy subjects):

Healthy subjects

Was this research conducted in the United States?

Yes

Are you Internal Review Board (IRB) certified? Please note: Failure to have IRB, if applicable will lead to automatic rejection of abstract.

Not applicable

Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.

Not applicable

Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.

Not applicable

Please indicate which methods were used in your research:

Other, Please specify  -   Simulation (of behavioral and fMRI data)

Provide references using APA citation style.

n/a

UNESCO Institute of Statistics and World Bank Waiver Form

I attest that I currently live, work, or study in a country on the UNESCO Institute of Statistics and World Bank List of Low and Middle Income Countries list provided.

No