Research on Measuring User Behavior Response Differences Supported by Propensity Scoring Method

Zhimeng Liu

doi:10.71222/1fwt6g02

Authors

Zhimeng Liu Harvard T.H. Chan School of Public Health, Harvard University, Boston, United States Author

DOI:

https://doi.org/10.71222/1fwt6g02

Keywords:

propensity score, user behavior, sample matching, intervention evaluation, data analytics

Abstract

Measuring the differences in user behavior responses is increasingly crucial for identifying targeted intervention effects and improving overall digital platform operation in the era of big data. However, observational studies often face significant methodological challenges. To overcome the profound influence of user characteristic differences, inherent sample selection bias, and unobserved confounding factors, the propensity score method is systematically utilized to construct a robust measurement system. This study meticulously classifies users based on the specific type of behavior response and deeply explores the empirical possibility of applying this advanced statistical approach in complex groups that were not randomly sampled. A comprehensive and complete model is constructed around critical methodological issues, including the precise selection of dependent variables, the rigorous elimination of covariates, the accurate estimation of propensity scores, and the implementation of advanced sample matching and weighting techniques. Furthermore, analytical methods such as inter-group comparison, heterogeneity testing, and extensive robustness testing are adopted to significantly enhance the accuracy, reliability, and persuasiveness of the measurement results. Ultimately, this research provides vital technical support and actionable insights for platform administrators and marketers in identifying nuanced behavioral characteristics, rigorously evaluating marketing intervention effects, and strategically optimizing enterprise operations for sustainable growth and improved user engagement.

References

1. J. A. Rios and J. Deng, "Is effort moderated scoring robust to multidimensional rapid guessing?," Educational and Psychological Measurement, vol. 85, no. 1, pp. 134-155, 2025.

2. L. L. Li, J. Fu, C. Xu, M. Ni, W. Chai, L. B. Hao, ... and J. Y. Chen, "Gender Differences in Ankylosing Spondylitis Patients with Advanced Hip Involvement: Results from A Matched Retrospective Cohort Study," Orthopaedic Surgery, vol. 14, no. 2, pp. 405-410, 2022.

3. Y. Wang, Q. Tu, and Z. Tao, "Optimizing customer engagement in fintech marketing: A telecom-centric approach to precision targeting using mobile app data," in *2024 10th International Conference on Big Data and Information Analytics (BigDIA)*, pp. 826-832, Oct. 2024.

4. B. Doleschal, D. Niedersüß-Beke, P. Kirchweger, A. Petzer, J. Thaler, and H. Rumpold, "Survival outcome in early-onset metastatic colorectal cancer: a multicenter-matched pair analysis," Oncology, vol. 102, no. 2, pp. 107-113, 2024.

5. X. Li, S. Zhang, and X. Song, "The impact of Internet use and involvement on residents’ attitudes to healthcare in China: A propensity score matching analysis," Plos one, vol. 19, no. 8, p. e0305664, 2024.

6. X. Cao and Y. Fan, "Exploring the influences of density on travel behavior using propensity score matching," Environment and Planning B: Planning and Design, vol. 39, no. 3, pp. 459-470, 2012.

7. F. J. Thoemmes and E. S. Kim, "A systematic review of propensity score methods in the social sciences," Multivariate Behavioral Research, vol. 46, no. 1, pp. 90-118, 2011.

8. S. Valenzuela, A. Arriagada, and A. Scherman, "Facebook, Twitter, and youth engagement: A quasi-experimental study of social media use and protest behavior using propensity score matching," International Journal of Communication, vol. 8, p. 25, 2014.

9. X. Cao, "Exploring causal effects of neighborhood type on walking behavior using stratification on the propensity score," Environment and Planning A, vol. 42, no. 2, pp. 487-504, 2010.

10. M. Li, "Using the propensity score method to estimate causal effects: A review and practical guide," Organizational Research Methods, vol. 16, no. 2, pp. 188-226, 2013.

11. R. M. Pruzek, "Introduction to the special issue on propensity score methods in behavioral research," Multivariate Behavioral Research, vol. 46, no. 3, pp. 389-398, 2011.

12. B. Keller and E. Tipton, "Propensity score analysis in R: A software review," Journal of Educational and Behavioral Statistics, vol. 41, no. 3, pp. 326-348, 2016.

13. Z. Qin, S. J. Chen, D. Metzler, Y. Noh, J. Qin, and X. Wang, "Attribute-based propensity for unbiased learning in recommender systems: Algorithm and case studies," in *Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining*, pp. 2359-2367, Aug. 2020.

14. Y. Wang, H. Zhang, T. Feng, and H. Wang, "Does internet use affect levels of depression among older adults in China? A propensity score matching approach," BMC Public Health, vol. 19, no. 1, p. 1474, 2019.