參數比的信賴區間估計廣泛應用於臨床試驗與流行病學研究。變異數估計恢復法為建構該區間之有效方法，惟實務中常見的資料缺失問題常使其應用受限。本研究針對獨立二項與卜瓦松分配之缺失資料，其中包含完全隨機缺失與隨機缺失，提出整合多重插補法與變異數估計恢復法之延伸框架，以建構參數比的信賴區間。模擬研究結果顯示，所提方法之覆蓋率穩定接近名目信心水準，文中亦總結各區間在不同資料情境下的最佳使用建議。最後，透過實例分析驗證各區間於實際數據之實用性。

Confidence interval estimation for the ratio of parameters is widely applied in clinical trials and epidemiological studies. While the MOVER-R(Method of Variance Estimates Recovery for the ratio) provides an effective framework for these estimations, its application is often limited by missing data issues commonly encountered in practice. Integrating multiple imputation with MOVER-R, this study develops a new procedure for constructing confidence intervals for the ratio of parameters under independent binomial and Poisson distributions, specifically addressing data that are missing completely at random and missing at random. The simulation study shows that the coverage probabilities of the proposed intervals remain stable and close to the nominal level. Furthermore, this study summarizes optimal recommendations for the application of each interval across various data scenarios. Finally, the practical utility of the proposed intervals is validated through illustrative examples using real-world data.

[1] Brown, L. D., Cai, T. T., & DasGupta, A. (2001). Interval estimation for a binomial proportion. Statistical Science, 16(2), 101–133. https://doi.org/10.1214/ss/1009213286
[2] Choi, S. C., & Stablein, D. M. (1982). Practical tests for comparing two proportions with incomplete data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 31(3), 256–262. https://doi.org/10.2307/2347999
[3] Detrano, R., Janosi, A., Steinbrunn, W., Pfisterer, M., Schmid, J.-J., Sandhu, S., Guppy, K. H., Lee, S., & Froelicher, V. F. (1989). International application of a new probability algorithm for the diagnosis of coronary artery disease. The American Journal of Cardiology, 64(5), 304–310. https://doi.org/10.1016/0002-9149(89)90524-9
[4] Donner, A., & Zou, G. Y. (2012). Closed-form confidence intervals for functions of the normal mean and standard deviation. Statistical Methods in Medical Research, 21(4), 347–359. https://doi.org/10.1177/0962280210383082
[5] Gart, J. J., & Nam, J. M. (1988). Approximate interval estimation of the ratio of binomial parameters: A review and corrections for skewness. Biometrics, 44(2), 323–338. https://doi.org/10.2307/2531848
[6] Harel, O., & Zhou, X.-H. (2006). Multiple imputation for correcting verification bias. Statistics in Medicine, 25(22), 3769–3786. https://doi.org/10.1002/sim.2494
[7] Howe, W. G. (1974). Approximate confidence limits on the mean of X + Y where X and Y are two tabled independent random variables. Journal of the American Statistical Association, 69(347), 789–794. https://doi.org/10.1080/01621459.1974.10480206
[8] Katz, D., Baptista, J., Azen, S. P., & Pike, M. C. (1978). Obtaining confidence intervals for the risk ratio in cohort studies. Biometrics, 34(3), 469–474. https://doi.org/10.2307/2530610
[9] Koopman, P. A. R. (1984). Confidence intervals for the ratio of two binomial proportions. Biometrics, 40(2), 513–517. https://doi.org/10.2307/2531405
[10] Krishnamoorthy, K., Lee, M., & Zhang, D. (2017). Closed-form fiducial confidence intervals for some functions of independent binomial parameters with comparisons. Statistical Methods in Medical Research, 26(1), 43–63. https://doi.org/10.1177/0962280214537809
[11] Lee, C. H. (2025). Multiple imputation confidence intervals for a risk difference with missing observations. Statistics in Medicine, 44(13–14), Article e70136. https://doi.org/10.1002/sim.70136
[12] Lee, C. H., & Wang, H. (2022). Multiple imputation confidence intervals for the mean of the discrete distributions for incomplete data. Statistics in Medicine, 41(7), 1172–1190. https://doi.org/10.1002/sim.9254
[13] Li, H.-Q., Chan, I. S., Tang, M.-L., Tian, G.-L., & Tang, N.-S. (2014). Confidence-interval construction for rate ratio in matched-pair studies with incomplete data. Journal of Biopharmaceutical Statistics, 24(3), 546–568. https://doi.org/10.1080/10543406.2014.888438
[14] Li, H. Q., Tang, M. L., & Wong, W. K. (2014). Confidence intervals for ratio of two Poisson rates using the method of variance estimates recovery. Computational Statistics, 29(3–4), 869–889. https://doi.org/10.1007/s00180-013-0467-9
[15] Li, X., Mehrotra, D. V., & Barnard, J. (2006). Analysis of incomplete longitudinal binary data using multiple imputation. Statistics in Medicine, 25(12), 2107–2124. https://doi.org/10.1002/sim.2343
[16] Little, R. J. A. (1988). A test of missing completely at random for multivariate data with missing values. Journal of the American Statistical Association, 83(404), 1198–1202. https://doi.org/10.1080/01621459.1988.10478722
[17] Liu, B., & Reiter, J. P. (2022). Multiple imputation inference with integer-valued point estimates. The American Statistician, 76(4), 323–328. https://doi.org/10.1080/00031305.2021.2006780
[18] Lott, A., & Reiter, J. P. (2020). Wilson confidence intervals for binomial proportions with multiple imputation for missing data. The American Statistician, 74(2), 109–115. https://doi.org/10.1080/00031305.2018.1473796
[19] Martín Andrés, A., & Álvarez Hernández, M. (2014). Two-tailed approximate confidence intervals for the ratio of proportions. Statistics and Computing, 24(1), 65–75. https://doi.org/10.1007/s11222-012-9353-5
[20] Newcombe, R. G. (1998). Interval estimation for the difference between independent proportions: Comparison of eleven methods. Statistics in Medicine, 17(8), 873–890. https://doi.org/10.1002/(SICI)1097-0258(19980430)17:8<873::AID-SIM779>3.0.CO;2-I
[21] Newcombe, R. G. (2001). Estimating the difference between differences: Measurement of additive scale interaction for proportions. Statistics in Medicine, 20(19), 2885–2893. https://doi.org/10.1002/sim.925
[22] Newcombe, R. G. (2012). Confidence intervals for proportions and related measures of effect size. CRC Press. https://doi.org/10.1201/b12670
[23] Price, R. M., & Bonett, D. G. (2000). Estimating the ratio of two Poisson rates. Computational Statistics & Data Analysis, 34(3), 345–356. https://doi.org/10.1016/S0167-9473(99)00100-0
[24] Price, R. M., & Bonett, D. G. (2008). Confidence intervals for a ratio of two independent binomial proportions. Statistics in Medicine, 27(26), 5497–5508. https://doi.org/10.1002/sim.3376
[25] Rubin, D. B. (1987). Multiple imputation for nonresponse in surveys. Wiley. https://doi.org/10.1002/9780470316696
[26] Santos, M. S., Abreu, P. H., García-Laencina, P. J., Simão, A., & Carvalho, A. (2015). A new cluster-based oversampling method for improving survival prediction of hepatocellular carcinoma patients. Journal of Biomedical Informatics, 58, 49–59. https://doi.org/10.1016/j.jbi.2015.09.012
[27] Sidi, Y., & Harel, O. (2022). Difference between binomial proportions using Newcombe’s method with multiple imputation for incomplete data. The American Statistician, 76(1), 29–36. https://doi.org/10.1080/00031305.2021.1898468
[28] Tang, M.-L., Ng, K. W., Tian, G.-L., & Tan, M. (2007). On improved EM algorithm and confidence interval construction for incomplete r × c tables. Computational Statistics & Data Analysis, 51(6), 2919–2933. https://doi.org/10.1016/j.csda.2006.11.035
[29] Wang, P., Ma, Y., Xu, S., Wang, Y.-X., Zhang, Y., Lou, X., Li, M., Wu, B., Gao, G., Yin, P., & Liu, N. (2023). MOVER-R and penalized MOVER-R confidence intervals for the ratio of two quantities. The American Statistician, 77(4), 381–389. https://doi.org/10.1080/00031305.2023.2173294
[30] Zou, G. Y., & Donner, A. (2008). Construction of confidence limits about effect measures: A general approach. Statistics in Medicine, 27(10), 1693–1702. https://doi.org/10.1002/sim.3095