Transferring summary-level auxiliary information from source domains to enhance statistical analysis in target domains is increasingly important, yet settings involving right-censored survival data remain underexplored. To address this gap, we developed a general methodology for incorporating subgroup Kaplan–Meier survival probabilities at multiple time points, a widely reported form of auxiliary information. Our framework handles both estimation of an abstractly defined target parameter, such as a regression coefficient or a causal estimand, and hypothesis testing for it. We first constructed a target-only estimator that possesses a unified structure applicable to a broad class of target parameters. This estimator was then linked, via a leveraging factor, to a transitional element computed from the target dataset in a manner analogous to the available auxiliary information. We proposed and compared two versions of this element. The model-free version is universally applicable and robust, whereas the model-based version delivers improved efficiency under a partly independent censoring assumption that has often been overlooked in existing literature. Our method requires no individual-level source data and maintains low computational complexity. Theoretical derivations and numerical experiments together demonstrated gains in estimation efficiency and testing power. In addition, Python implementations of the proposed approaches were provided.
Citation: Jie Ding, Bo Han. Auxiliary-survival-probabilities-informed survival analysis under Cox model[J]. Electronic Research Archive, 2026, 34(10): 7707-7738. doi: 10.3934/era.2026332
Transferring summary-level auxiliary information from source domains to enhance statistical analysis in target domains is increasingly important, yet settings involving right-censored survival data remain underexplored. To address this gap, we developed a general methodology for incorporating subgroup Kaplan–Meier survival probabilities at multiple time points, a widely reported form of auxiliary information. Our framework handles both estimation of an abstractly defined target parameter, such as a regression coefficient or a causal estimand, and hypothesis testing for it. We first constructed a target-only estimator that possesses a unified structure applicable to a broad class of target parameters. This estimator was then linked, via a leveraging factor, to a transitional element computed from the target dataset in a manner analogous to the available auxiliary information. We proposed and compared two versions of this element. The model-free version is universally applicable and robust, whereas the model-based version delivers improved efficiency under a partly independent censoring assumption that has often been overlooked in existing literature. Our method requires no individual-level source data and maintains low computational complexity. Theoretical derivations and numerical experiments together demonstrated gains in estimation efficiency and testing power. In addition, Python implementations of the proposed approaches were provided.
| [1] |
D. M. Witten, R. Tibshirani, Survival analysis with high-dimensional covariates, Stat. Methods Med. Res., 19 (2010), 29–51. https://doi.org/10.1177/0962280209105024 doi: 10.1177/0962280209105024
|
| [2] | J. Li, S. Ma, Survival Analysis in Medicine and Genetics, Chapman & Hall CRC Press, New York, 2013. |
| [3] |
K. Weiss, T. M. Khoshgoftaar, D. Wang, A survey of transfer learning, J. Big Data, 3 (2016), 9. https://doi.org/10.1186/s40537-016-0043-6 doi: 10.1186/s40537-016-0043-6
|
| [4] |
T. Cai, M. Liu, Y. Xia, Individual data protected integrative regression analysis of high-dimensional heterogeneous data, J. Am. Stat. Assoc., 117 (2022), 2105–2119. https://doi.org/10.1080/01621459.2021.1904958 doi: 10.1080/01621459.2021.1904958
|
| [5] |
S. Li, T. T. Cai, H. Li, Transfer learning for high-dimensional linear regression: prediction, estimation and minimax optimality, J. R. Stat. Soc. B, 84 (2022), 149–173. https://doi.org/10.1111/rssb.12479 doi: 10.1111/rssb.12479
|
| [6] |
Y. Tian, Y. Feng, Transfer learning under high-dimensional generalized linear models, J. Am. Stat. Assoc., 118 (2023), 2684–2697. https://doi.org/10.1080/01621459.2022.2071278 doi: 10.1080/01621459.2022.2071278
|
| [7] |
S. Li, L. Zhang, T. T. Cai, H. Li, Estimation and inference for high-dimensional generalized linear models with knowledge transfer, J. Am. Stat. Assoc., 119 (2024), 1274–1285. https://doi.org/10.1080/01621459.2023.2184373 doi: 10.1080/01621459.2023.2184373
|
| [8] |
Z. Li, Y. Shen, J. Ning, Accommodating time-varying heterogeneity in risk estimation under the Cox model: a transfer learning approach, J. Am. Stat. Assoc., 118 (2023), 2276–2287. https://doi.org/10.1080/01621459.2023.2210336 doi: 10.1080/01621459.2023.2210336
|
| [9] |
Y. B. Pei, Z. Y. Yu, J. S. Shen, Transfer learning for accelerated failure time model with microarray data, BMC Bioinf., 26 (2025), 84. https://doi.org/10.1186/s12859-025-06056-w doi: 10.1186/s12859-025-06056-w
|
| [10] |
D. R. Cox, Regression models and life tables, J. R. Stat. Soc. B, 34 (1972), 187–202. https://doi.org/10.1111/j.2517-6161.1972.tb00899.x doi: 10.1111/j.2517-6161.1972.tb00899.x
|
| [11] |
M. Xie, T. Hu, J. Zhou, Transfer learning under the Cox model with interval-censored data, Stat. Anal. Data Min., 17 (2024), e11680. https://doi.org/10.1002/sam.11680 doi: 10.1002/sam.11680
|
| [12] |
D. Deng, L. Zhang, H. Feng, V. M. Chinchilli, C. Chen, M. Wang, Improving estimation efficiency for survival data analysis by integrating a coarsened time-to-event outcome from an external study, Biometrics, 81 (2025), ujae168. https://doi.org/10.1093/biomtc/ujae168 doi: 10.1093/biomtc/ujae168
|
| [13] |
J. Qin, Y. Liu, P. Li, A selective review of statistical methods using calibration information from similar studies, Stat. Theory Relat. Fields, 6 (2022), 175–190. https://doi.org/10.1080/24754269.2022.2037201 doi: 10.1080/24754269.2022.2037201
|
| [14] |
S. J. Pan, Q. Yang, A survey on transfer learning, IEEE Trans. Knowl. Data Eng., 22 (2010), 1345–1359. https://doi.org/10.1109/TKDE.2009.191 doi: 10.1109/TKDE.2009.191
|
| [15] | X. Hu, X. Zhang, Optimal parameter-transfer learning by semiparametric model averaging, J. Mach. Learn. Res., 24 (2023), 1–53. Available from: https://jmlr.org/papers/v24/23-0030.html. |
| [16] |
J. Qin, J. Lawless, Empirical likelihood and general estimating equations, Ann. Stat., 22 (1994), 300–325. https://doi.org/10.1214/aos/1176325370 doi: 10.1214/aos/1176325370
|
| [17] |
N. Chatterjee, Y. H. Chen, P. Maas, R. J. Carroll, Constrained maximum likelihood estimation for model calibration using summary-level information from external big data sources, J. Am. Stat. Assoc., 111 (2016), 107–117. https://doi.org/10.1080/01621459.2015.1123157 doi: 10.1080/01621459.2015.1123157
|
| [18] |
H. Zhang, L. Deng, M. Schiffman, J. Qin, K. Yu, Generalized integration model for improved statistical inference by leveraging external summary data, Biometrika, 107 (2020), 689–703. https://doi.org/10.1093/biomet/asaa014 doi: 10.1093/biomet/asaa014
|
| [19] |
C. Y. Huang, J. Qin, H. T. Tsai, Efficient estimation of the Cox model with auxiliary subgroup survival information, J. Am. Stat. Assoc., 111 (2016), 787–799. https://doi.org/10.1080/01621459.2015.1044090 doi: 10.1080/01621459.2015.1044090
|
| [20] |
Z. Chen, J. Ning, Y. Shen, J. Qin, Combining primary cohort data with external aggregate information without assuming comparability, Biometrics, 77 (2021), 1024–1036. https://doi.org/10.1111/biom.13356 doi: 10.1111/biom.13356
|
| [21] |
J. He, H. Li, S. Zhang, X. Duan, Additive hazards model with auxiliary subgroup survival information, Lifetime Data Anal., 25 (2019), 128–149. https://doi.org/10.1007/s10985-018-9426-7 doi: 10.1007/s10985-018-9426-7
|
| [22] |
B. Han, I. van Keilegom, X. Wang, Semiparametric estimation of the non-mixture cure model with auxiliary survival information, Biometrics, 78 (2022), 448–459. https://doi.org/10.1111/biom.13450 doi: 10.1111/biom.13450
|
| [23] |
Y. J. Cheng, Y. C. Liu, C. Y. Tsai, C. Y. Huang, Semiparametric estimation of the transformation model by leveraging external aggregate data in the presence of population heterogeneity, Biometrics, 79 (2023), 1996–2009. https://doi.org/10.1111/biom.13778 doi: 10.1111/biom.13778
|
| [24] |
L. P. Hansen, Large sample properties of generalized method of moments estimators, Econometrica, 50 (1982), 1029–1054. https://doi.org/10.2307/1912775 doi: 10.2307/1912775
|
| [25] |
W. Shang, X. Wang, The generalized moment estimation of the additive-multiplicative hazard model with auxiliary survival information, Comput. Stat. Data Anal., 112 (2017), 154–169. https://doi.org/10.1016/j.csda.2017.03.013 doi: 10.1016/j.csda.2017.03.013
|
| [26] | Y. Sheng, Y. Sun, D. Deng, C. Y. Huang, Censored linear regression in the presence or absence of auxiliary survival information, Biometrics, 76 (2020), 734–745. https://www.jstor.org/stable/48584672 |
| [27] |
J. Ding, J. Li, Y. Han, I. W. McKeague, X. Wang, Fitting additive risk models using auxiliary information, Stat. Med., 42 (2023), 894–916. https://doi.org/10.1002/sim.9649 doi: 10.1002/sim.9649
|
| [28] |
J. Ding, J. Li, M. Zhang, X. Wang, CureAuxSP: An R package for estimating mixture cure models with auxiliary survival probabilities, Comput. Methods Programs Biomed., 251 (2024), 108212. https://doi.org/10.1016/j.cmpb.2024.108212 doi: 10.1016/j.cmpb.2024.108212
|
| [29] |
J. Ding, J. Li, X. Wang, Efficient auxiliary information synthesis for cure rate model, J. R. Stat. Soc. C, 73 (2024), 497–521. https://doi.org/10.1093/jrsssc/qlad106 doi: 10.1093/jrsssc/qlad106
|
| [30] |
C. Y. Huang, J. Qin, A unified approach for synthesizing population-level covariate effect information in semiparametric estimation with survival data, Stat. Med., 39 (2020), 1573–1590. https://doi.org/10.1002/sim.8499 doi: 10.1002/sim.8499
|
| [31] |
P. Xie, J. Ding, X. Wang, Leveraging external aggregated information for the marginal accelerated failure time model, Stat. Med., 43 (2024), 5203–5216. https://doi.org/10.1002/sim.10224 doi: 10.1002/sim.10224
|
| [32] |
Z. Chen, Y. Shen, J. Qin, J. Ning, Likelihood adaptively incorporated external aggregate information with uncertainty for survival data, Biometrics, 80 (2024), ujae120. https://doi.org/10.1093/biomtc/ujae120 doi: 10.1093/biomtc/ujae120
|
| [33] |
P. F. Su, J. Zhong, Y. C. Liu, T. H. Lin, H. T. Ou, Efficient estimation of a Cox model when integrating the subgroup incidence rate information, J. Appl. Stat., 50 (2023), 2151–2170. https://doi.org/10.1080/02664763.2022.2068512 doi: 10.1080/02664763.2022.2068512
|
| [34] |
J. Y. Hung, J. Zhong, H. T. Ou, P. F. Su, Efficient estimation of the Cox model when incorporating the subgroup restricted mean survival time, J. Biopharm. Stat., 36 (2025), 527–548. https://doi.org/10.1080/10543406.2024.2444242 doi: 10.1080/10543406.2024.2444242
|
| [35] | J. D. Kalbfleisch, D. E. Schaubel, Fifty years of the Cox model, Annu. Rev. Stat. Appl., 10 (2023), 1–23. https://doi.org/10.1146/annurev-statistics-033021-014043 |
| [36] |
K. M. Leung, R. M. Elashoff, A. A. Afifi, Censoring issues in survival analysis, Annu. Rev. Public Health, 18 (1997), 83–104. https://doi.org/10.1146/annurev.publhealth.18.1.83 doi: 10.1146/annurev.publhealth.18.1.83
|
| [37] | J. P. Klein, M. L. Moeschberger, Survival Analysis: Techniques for Censored and Truncated Data, 2nd edition, Springer-Verlag, New York, 2003. https://doi.org/10.1007/b97377 |
| [38] |
E. L. Kaplan, P. Meier, Nonparametric estimation from incomplete observations, J. Am. Stat. Assoc., 53 (1958), 457–481. https://doi.org/10.1080/01621459.1958.10501452 doi: 10.1080/01621459.1958.10501452
|
| [39] | A. Sklar, Fonctions de répartition à $n$ dimensions et leurs marges, Publ. Inst. Stat. Univ. Paris, 8 (1959), 229–231. |
| [40] | D. R. Cox, Partial likelihood, Biometrika, 62 (1975), 269–276. https://doi.org/10.1093/biomet/62.2.269 |
| [41] |
P. K. Andersen, R. D. Gill, Cox's regression model for counting processes: a large sample study, Ann. Stat., 10 (1982), 1100–1120. https://doi.org/10.1214/aos/1176345976 doi: 10.1214/aos/1176345976
|
| [42] |
N. Reid, H. Crépeau, Influence functions for proportional hazards regression, Biometrika, 72 (1985), 1–9. https://doi.org/10.1093/biomet/72.1.1 doi: 10.1093/biomet/72.1.1
|
| [43] | M. R. Kosorok, Introduction to Empirical Processes and Semiparametric Inference, Springer, New York, 2008. https://doi.org/10.1007/978-0-387-74978-5 |
| [44] | A. W. Van der Vaart, Asymptotic Statistics, Cambridge University Press, Cambridge, 2012. https://doi.org/10.1017/CBO9780511802256 |
| [45] |
T. Martinussen, S. Vansteelandt, P. K. Andersen, Subtleties in the interpretation of hazard ratios, Lifetime Data Anal., 26 (2020), 833–855. https://doi.org/10.1007/s10985-020-09501-5 doi: 10.1007/s10985-020-09501-5
|
| [46] | M. J. Stensrud, M. A. Hernán, Why test for proportional hazards? JAMA, 323 (2020), 1401–1402. https://doi.org/10.1001/jama.2020.1267 |
| [47] | M. A. Hernán, J. M. Robins, Causal Inference: What If, Chapman & Hall/CRC, Boca Raton, 2020. |
| [48] |
J. M. Robins, A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect, Math. Modell., 7 (1986), 1393–1512. https://doi.org/10.1016/0270-0255(86)90088-6 doi: 10.1016/0270-0255(86)90088-6
|
| [49] |
S. Li, T. Cai, R. Duan, Targeting underrepresented populations in precision medicine: a federated transfer learning approach, Ann. Appl. Stat., 17 (2023), 2970–2992. https://doi.org/10.1214/23-AOAS1747 doi: 10.1214/23-AOAS1747
|
| [50] |
Y. Zhai, P. Han, Data integration with oracle use of external information from heterogeneous populations, J. Comput. Graphical Stat., 31 (2022), 1001–1012. https://doi.org/10.1080/10618600.2022.2050248 doi: 10.1080/10618600.2022.2050248
|
| [51] | T. R. Fleming, D. P. Harrington, Counting Processes and Survival Analysis, Wiley, New York, 1991. |
| [52] |
L. P. Rivest, M. T. Wells, A martingale approach to the copula-graphic estimator for the survival function under dependent censoring, J. Multivar. Anal., 79 (2001), 138–155. https://doi.org/10.1006/jmva.2000.1959 doi: 10.1006/jmva.2000.1959
|
Jie Ding, Bo Han. Auxiliary-survival-probabilities-informed survival analysis under Cox model[J]. Electronic Research Archive, 2026, 34(10): 7707-7738. doi: 10.3934/era.2026332
DownLoad: