Date of Award
Summer 8-23-2025
Document Type
Dissertation
Degree Name
Ph.D. in Quantitative Research Methods
Organizational Unit
Morgridge College of Education, Research Methods and Information Science, Research Methods and Statistics
First Advisor
Yixiao Dong
Second Advisor
Robyn Thomas Pitts
Third Advisor
Keiko McCullough
Fourth Advisor
Inna Altschul
Copyright Statement / License for Reuse
All Rights Reserved.
Keywords
Causal relationships, Methodological pluralism, Ordinary least squares (OLS), Quantile regression (QR), Linear relationships
Abstract
Ordinary Least Squares (OLS) regression has traditionally been the preferred quantitative method for estimating linear relationships. However, it assumes that the effect of a predictor variable remains constant across the entire outcome distribution, which can miss important insights when data are heterogeneous. Quantile Regression (QR), on the other hand, offers a more detailed analysis by focusing on the full response variable distribution, thereby revealing different relationship patterns at various quantiles within the outcome. This study compares how OLS and QR perform in modeling conditional relationships within a causal-comparative framework based on ex post facto research. Using the mortality data from the Organization for Economic Co-operation and Development, this research applies both OLS and QR to examine how age influences weekly deaths across the entire range, not just at the mean. The results show clear differences between the two methods. OLS identifies the overall average effect of age but overlooks significant variations across the distribution of weekly deaths. QR, however, uncovers distinct patterns by analyzing the relationship at different quantiles. This emphasizes the importance of choosing modeling techniques that align with research goals and data characteristics. Consequently, this study recommends using QR alongside traditional regression methods in social science research, demonstrating how each captures variability differently. Overall, it advocates for methodological pluralism, which is essential for understanding complex causal relationships in intricate datasets.
Copyright Date
8-2025
Publication Statement
Copyright is held by the author. User is responsible for all copyright compliance.
Rights Holder
Samuel Nnorom
Provenance
Received from ProQuest
File Format
application/pdf
Language
English (eng)
Extent
164 pgs
File Size
1.3 MB
Recommended Citation
Nnorom, Samuel, "Comparing Ordinary Least Squares and Quantile Regression: A Causal-Comparative Approach to Modeling Conditional Relationships" (2025). Electronic Theses and Dissertations. 2640.
https://digitalcommons.du.edu/etd/2640