Causal Considerations Can Inform the Interpretation of Surprising Associations in Medical Registries

Abstract

An exploratory analysis of registry data from 2437 patients with advanced gastric cancer revealed a surprising association between astrological birth signs and overall survival (OS) with p = 0.01. After dichotomizing or changing the reference sign, p-values <0.05 were observed for several birth signs following adjustments for multiple comparisons. Bayesian models with moderately skeptical priors still pointed to these associations. A more plausible causal model, justified by contextual knowledge, revealed that these associations arose from the astrological sign association with seasonality. This case study illustrates how causal considerations can guide analyses through what would otherwise be a hopeless maze of statistical possibilities.

Keywords:

• Zodiac sign
• horoscope
• causal inference
• Bayesian
• frequentist
• seasonality

Acknowledgments

Various statisticians and clinicians have commented on these results in https://discourse.datamethods.org, providing informal insights into the results. The insights of Sander Greenland greatly contributed to this manuscript, although we alone are responsible for any possible errors. We thank the anonymous reviewer for providing many insightful comments and suggestions. We also thank the IRICOM S.L. team for the support of the website registry.

Ethical approval

All procedures followed were in accordance with the ethical standards of the committee responsible for human experimentation (institutional and national) and with the Helsinki Declaration of 1964 and later versions. Informed consent was obtained from all patients before being included in the study. This work is original and has not been previously presented elsewhere. All authors have approved the manuscript and publication.

Author contributions

P.J.F., A.C.B., J.G., and P.M. developed the project, analyzed the data, and drafted the manuscript. The other authors recruited patients and provided clinical information, comments, and improvements to the manuscript. All authors participated in the interpretation and discussion of data, and the critical review of the manuscript.

Declaration of interest

P.M. has received honoraria for service on a Scientific Advisory Board for Mirati Therapeutics, Bristol Myers Squibb, and Exelixis; consulting for Axiom Healthcare Strategies; non-branded educational programs supported by Exelixis and Pfizer; and research funding for clinical trials from Takeda, Bristol Myers Squibb, Mirati Therapeutics, Gateway for Cancer Research, and UT MD Anderson Cancer Center. All other authors state no conflict of interest related to this study.

Data availability statement

All data will be provided upon request to the corresponding author.

Code availability

The R code is available as Supplementary File 1.

Additional information

Funding

This is an academic study. The study was supported by the authors themselves. Pavlos Msaouel is supported by a Career Development Award by the American Society of Clinical Oncology, a Research Award by KCCure, the MD Anderson Khalifa Scholar Award, the Andrew Sabin Family Foundation Fellowship, and the MD Anderson Physician-Scientist Award.