An improved estimator of the logarithmic odds ratio for small sample sizes using a Bayesian approach
-
Toru Ogura
and
Takemi Yanagimoto
Abstract
The logarithmic odds ratio is a well-known method for comparing binary data between two independent groups. Although various existing methods proposed for estimating a logarithmic odds ratio, most methods estimate two proportions in each group independently and then estimate the logarithmic odds ratio using the two estimated proportions. When using a logarithmic odds ratio, researchers are more interested in the logarithmic odds ratio than proportions for each group. Parameter estimations, generally, incur random and systematic errors. These errors in initially estimated parameter may affect later estimated parameter. We propose a Bayesian estimator to directly estimate a logarithmic odds ratio without using proportions for each group. Many existing methods need to estimate two parameters (two proportions in each group) to estimate a logarithmic odds ratio; however, the proposed method only estimates one parameter (logarithmic odds ratio). Therefore, the proposed estimator can be closer to the population’s logarithmic odds ratio than existing estimators. Additionally, the validity of the proposed estimator is verified using numerical calculations and applications.
Acknowledgments
The authors wish to thank the Editor and the Reviewers for their valuable comments and suggestions, which have contributed to the revised manuscript. This study was carried out under the ISM Cooperative Research Program (2023-ISMCRP-2042).
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: Not applicable.
References
1. Hauck, WW. A comparative study of conditional maximum likelihood estimation of a common odds ratio. Biometrics 1984;40:1117–23. https://doi.org/10.2307/2531163.Search in Google Scholar
2. Hanley, JA, Miettinen, OS. An ‘unconditional-like’ structure for the conditional estimator of odds ratio from 2 × 2 tables. Biomed J 2006;48:23–34. https://doi.org/10.1002/bimj.200510167.Search in Google Scholar PubMed
3. Babu, M, Mani, T, Sappani, M, George, S, Bangdiwala, SI, Jeyaseelan, L. Exact correction factor for estimating the OR in the presence of sparse data with a zero cell in 2 × 2 tables. Int J Biostat 2024;20:229–43. https://doi.org/10.1515/ijb-2022-0040.Search in Google Scholar PubMed
4. Haldane, JBS. The estimation and significance of the logarithm of a ratio of frequencies. Ann Hum Genet 1956;20:309–11. https://doi.org/10.1111/j.1469-1809.1955.tb01285.x.Search in Google Scholar PubMed
5. Gart, JJ, Zweifel, JR. On the bias of various estimators of the logit and its variance with application to quantal bioassay. Biometrika 1967;54:181–7. https://doi.org/10.1093/biomet/54.1-2.181.Search in Google Scholar
6. Hirji, KF, Tsiatis, AA, Mehta, CR. Median unbiased estimation for binary data. Am Statistician 1989;43:7–11. https://doi.org/10.1080/00031305.1989.10475597.Search in Google Scholar
7. Parzen, M, Lipsitz, S, Ibrahim, J, Klar, N. An estimate of the odds ratio that always exists. J Comput Graph Stat 2002;11:420–36. https://doi.org/10.1198/106186002760180590.Search in Google Scholar
8. Vasquez, VR, Whiting, WB. Analysis of random and systematic error effects on uncertainty propagation in process design and simulation using distribution tail characterization. Chem Eng Commun 2004;191:278–301. https://doi.org/10.1080/00986440490261890.Search in Google Scholar
9. Muysoms, FE, Hauters, J, Van Nieuwenhove, Y, Huten, N, Claeys, DA. Laparoscopic repair of parastomal hernias: a multi-centre retrospective review and shift in technique. Acta Chir Belg 2008;108:400–4. https://doi.org/10.1080/00015458.2008.11680249.Search in Google Scholar PubMed
10. Okuno, M, Hatano, E, Kasai, Y, Nishio, T, Seo, S, Taura, K, et al.. Feasibility of the liver-first approach for patients with initially unresectable and not optimally resectable synchronous colorectal liver metastases. Surg Today 2016;46:721–8. https://doi.org/10.1007/s00595-015-1242-z.Search in Google Scholar PubMed
11. Böhning, D, Sangnawakij, P, Holling, H. Estimating risk and rate ratio in rare events meta-analysis with the Mantel-Haenszel estimator and assessing heterogeneity. Int J Biostat 2023;19:21–38. https://doi.org/10.1515/ijb-2021-0087.Search in Google Scholar PubMed
12. Ghosh, JK, Delampady, M, Samanta, T. An introduction to Bayesian analysis: theory and methods. New York: Springer; 2006.Search in Google Scholar
13. Bolstad, WM, Curran, JM. Introduction to Bayesian statistics, 3rd ed. Hoboken, NJ: John Wiley & Sons; 2016.10.1002/9781118593165Search in Google Scholar
14. Ogura, T, Yanagimoto, T. Improving and extending the McNemar test using the Bayesian method. Stat Med 2016;35:2455–66. https://doi.org/10.1002/sim.6875.Search in Google Scholar PubMed
15. Thomas, DG, Gart, JJ. A table of exact confidence limits for differences and ratios of two proportions and their odds ratios. J Am Stat Assoc 1977;72:73–6. https://doi.org/10.1080/01621459.1977.10479909.Search in Google Scholar
16. Harkness, WL. Properties of the extended hypergeometric distribution. Ann Math Stat 1965;36:938–45. https://doi.org/10.1214/aoms/1177700066.Search in Google Scholar
17. R Core Team. R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing; 2024.Search in Google Scholar
18. Ogura, T, Yanagimoto, T. Estimation of highly heterogeneous multinomial probabilities observed at the beginning of COVID-19. Biostat Epidemiol 2022;6:164–81. https://doi.org/10.1080/24709360.2022.2064693.Search in Google Scholar
19. Ogura, T, Yanagimoto, T. Bayesian estimator of multiple Poisson means assuming two different priors. Commun Stat Simulat Comput 2023;52:649–57. https://doi.org/10.1080/03610918.2020.1861465.Search in Google Scholar
Supplementary Material
This article contains supplementary material (https://doi.org/10.1515/ijb-2024-0105).
© 2025 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Prognostic adjustment with efficient estimators to unbiasedly leverage historical data in randomized trials
- Homogeneity test and sample size of response rates for AC 1 in a stratified evaluation design
- A review of survival stacking: a method to cast survival regression analysis as a classification problem
- DsubCox: a fast subsampling algorithm for Cox model with distributed and massive survival data
- A hybrid hazard-based model using two-piece distributions
- Regression analysis of clustered current status data with informative cluster size under a transformed survival model
- Bayesian covariance regression in functional data analysis with applications to functional brain imaging
- Risk estimation and boundary detection in Bayesian disease mapping
- An improved estimator of the logarithmic odds ratio for small sample sizes using a Bayesian approach
- Short Communication
- A multivariate Bayesian learning approach for improved detection of doping in athletes using urinary steroid profiles
- Research Articles
- Guidance on individualized treatment rule estimation in high dimensions
- Weighted Euclidean balancing for a matrix exposure in estimating causal effect
- Penalized regression splines in Mixture Density Networks
Articles in the same Issue
- Frontmatter
- Research Articles
- Prognostic adjustment with efficient estimators to unbiasedly leverage historical data in randomized trials
- Homogeneity test and sample size of response rates for AC 1 in a stratified evaluation design
- A review of survival stacking: a method to cast survival regression analysis as a classification problem
- DsubCox: a fast subsampling algorithm for Cox model with distributed and massive survival data
- A hybrid hazard-based model using two-piece distributions
- Regression analysis of clustered current status data with informative cluster size under a transformed survival model
- Bayesian covariance regression in functional data analysis with applications to functional brain imaging
- Risk estimation and boundary detection in Bayesian disease mapping
- An improved estimator of the logarithmic odds ratio for small sample sizes using a Bayesian approach
- Short Communication
- A multivariate Bayesian learning approach for improved detection of doping in athletes using urinary steroid profiles
- Research Articles
- Guidance on individualized treatment rule estimation in high dimensions
- Weighted Euclidean balancing for a matrix exposure in estimating causal effect
- Penalized regression splines in Mixture Density Networks
