Abstract
Log-rank, Wilcoxon and Tarone-Ware tests are most commonly used tests for testing the overall homogeneity of survival curves, but in certain situation it appears that they have a significant loss of statistical testing power. One such case is the more than one time crossing of survival curves. The problem considered often occurs in medical research. To overcome this problem, in this article, we present and study a non-parametric test procedure based on a new weight. The proposed new weighted test has greater power to detect overall differences between more than one time crossing survival curves. Simulation studies are performed to compare the proposed method with existing methods. Furthermore, the advantage of the new test is finally exemplified in the analysis of a β-thalassaemia major data.
Reference19 articles.
1. Csalódi, R., Bagyura, Z., Vathy-Fogarassy, Á., & Abonyi, J. (2024). Time-dependent frequent sequence mining-based survival analysis. Knowledge-Based Systems, 296, 111885.
2. Li, X., Marcus, D., Russell, J., Aboagye, E. O., Ellis, L. B., Sheeka, A., ... & Rockall, A. G. (2024). Weibull parametric model for survival analysis in women with endometrial cancer using clinical and T2-weighted MRI radiomic features. BMC Medical Research Methodology, 24(1), 107.
3. Srujana, B., Verma, D., & Naqvi, S. (2024). Machine learning vs. survival analysis models: a study on right censored heart failure data. Communications in Statistics-Simulation and Computation, 53(4), 1899-1916.
4. Wang, P., Li, Y., & Reddy, C. K. (2019). Machine learning for survival analysis: A survey. ACM Computing Surveys (CSUR), 51(6), 1-36.
5. Mantel, N. (1966). Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemother Rep, 50(3), 163-170.