Examining tests for comparing survival curves with  right censored data

Pinar Gunel  Karadeniz; Ilker  Ercan

doi:https://doi.org/10.59170/stattrans-2017-016

Examining tests for comparing survival curves with right censored data

Pinar Gunel Karadeniz Uludag University, Faculty of Medicine, Department of Biostatistics Gorukle Campus Bursa/TURKEY 16059. , Ilker Ercan Uludag University, Faculty of Medicine, Department of Biostatistics Gorukle Campus Bursa/TURKEY 16059. Statistics in Transition new series, vol. 18, 2017, 2, pages: 311-328 Published online: 1 June 2017 https://doi.org/10.59170/stattrans-2017-016

241 Views 14 Downloads

ARTICLE

(English) PDF

ABSTRACT

In survival analysis, estimating the survival probability of a population is important, but on the other hand, investigators want to compare the survival experiences of different groups. In such cases, the differences can be illustrated by drawing survival curves, but this will only give a rough idea. Since the data obtained from survival studies contains frequently censored observations some specially designed tests are required in order to compare groups statistically in terms of survival. Methods: In this study, Logrank, Gehan-Wilcoxon, Tarone-Ware, Peto-Peto, Modified Peto-Peto tests and tests belonging to Fleming-Harrington test family with (p, q) values; (1, 0), (0.5, 0.5), (1, 1), (0, 1) ve (0.5, 2) are examined by means of Type I error rate obtained from a simulation study, which is conducted in the cases where the event takes place with equal probability along the follow-up time. Results: As a result of the simulation study, Type I error rate of Logrank test is equal or close to the nominal value. Conclusions: When survival data were generated from lognormal and inverse Gaussian distribution, Type I error rate of Gehan-Wilcoxon, Tarone-Ware, Peto-Peto, Modified Peto-Peto and Fleming-Harrington (1,0) tests were close to the nominal value.

KEYWORDS

survival analysis, survival curves, comparison of survival curves, right censored observations

REFERENCES

AKBAR, A, PASHA, G. R., (2009). Properties of Kaplan-Meier estimator: group comparison of survival curves. European Journal of Scientific Research,32 (3), pp. 391–397. https://www.researchgate.net/profile/Atif_Akbar2/publication/255648672_Properties_of_Kaplan-Meier_Estimator_Group_Comparison_of_Survival_Curves/links/549a82f00cf2b80371359dd2.pdf.

ALLISON, P. D., (2010). Survival analysis using SAS: a practical guide, 2nd edition, SAS Press, North Carolina.

ALTMAN, D. G., (1991). Practical statistics for medical research, Chapman&Hall, London.

BLAND, J. M., ALTMAN, D. G., (2004). The logrank test. British Medical Journal, 328, pp. 1073. http://www.bmj.com/content/328/7447/1073.long.

BELTANGADY, M. S., FRANKOWSKI, R. F., (1989). Effect of unequal censoring on the size and power of the logrank and Wilcoxon types of tests for survival data. Statistics in Medicine, 8 (8), pp. 937–945. https://www.ncbi.nlm.nih.gov/pubmed/2799123.

BUYSKE, S., FAGERSTROM, R., YING, Z., (2000). A class of weighted log rank tests for survival data when the event is rare. Journal of the American Statistical Association, 95 (449), pp. 249–258.https://www.jstor.org/stable/2669542?seq=1#page_scan_tab_contents.

COX, D. R., (1953). Some simple approximate tests for poisson variates. Biometrika, 40, pp. 354–360. https://www.jstor.org/stable/2333353?seq=1#page_scan_tab_contents.

DAWSON, B., TRAPP, R. G., (2001). Basic&Clinical Biostatistics. Boston: McGraw Hill.

FISHER, L. D., BELLE, G. V., (1993). Biostatistics, a methodology for the health sciences, John Wiley&Sons Inc, New York.

FLEMING, T. R., HARRINGTON, D. P., (1981). A class of hypothesis tests for one and two samples censored survival data. Communications in Statistics,10, pp. 763–794. http://www.tandfonline.com/doi/abs/10.1080/03610928108828073?journalCode=lsta20.

FLEMING, T. R., HARRINGTON, D. P., O'Sullivan, M., (1987). Supremum versions of the log-rank and generalized Wilcoxon statistics. Journal of the American Statistical Association, 82 (397), pp. 312–320.https://www.jstor.org/stable/2289169?seq=1#page_scan_tab_contents.

GEHAN, E. A., (1965). A generalized Wilcoxon test for comparing arbitrarily single-censored samples. Biometrika, 52, pp. 203–223. https://academic.oup.com/biomet/article-abstract/52/1-2/203/359447/A generalized-Wilcoxon-test-for-comparing.

GOMEZ, G., CALLE, M. L., OLLER, R., LANGOHR, K., (2009). Tutorial on methods for interval-censored data and their implementation in R. Statistical Modelling, 9 (4), pp. 259–297. http://journals.sagepub.com/doi/abs/10.1177/1471082X0900900402.

HARRINGTON, DP., FLEMING, T. R., (1982). A class of rank test procedures for censored survival data. Biometrika, 69 (3), pp. 553–566. https://www.jstor.org/stable/2335991.

HEINZE, G., GNANT, M., SCHEMPER, M., (2003). Exact log-rank tests for unequal follow-up. Biometrics, 59, pp. 1151–1157. https://www.ncbi.nlm.nih.gov/pubmed/14969496.

HINTZE, J. L., (2007). NCSS user guide V tabulation, item analysis, proportions, diagnostic tests, and survival / reliability, Published by NCSS, Kaysville, Utah.

JURKIEWICZ, T., WYCINKA, E., (2011). Significance tests of differences between two crossing survival curves for small samples. Acta Universitatis Lodziensis Folia Oeconomica, 255, pp. 114. http://cejsh.icm.edu.pl/cejsh/element/bwmeta1.element.hdl_11089_690?print View=true.

KALBFLEISCH, J. D., PRENTICE, R. L., (2002). The Statistical Analysis of Failure Time Data. New York: John Wiley&Sons Inc.

KIM, J., KANG, D. R., NAM, C. M., (2006). Logrank-type tests for comparing survival curves with interval-censored data. Computational Statistics & Data Analysis, 50 (11), pp. 3165–3178. http://www.sciencedirect.com/science/article/pii/S0167947305001441

KIM, J. S., DAILEY, R. J., (2008). Biostatistics for oral healthcare, Blackwell Publishing Company, Iowa, pp. 287–291.

KLEIN, J. P., RIZZO, J. D., ZHANG, M. J., KEIDING, N., (2001). Statistical methods for the analysis and presentation of the results of bone marrow transplants. Part I: Unadjusted analysis. Bone Marrow Transplantation, 28,pp. 909–915. https://www.ncbi.nlm.nih.gov/pubmed/11753543.

KLEINBAUM, D. G., KLEIN, M., (2005). Survival Analysis a Self-Learning Text. New York: Springer.

LATTA, R. B., (1981). A monte carlo study of some two-sample rank tests with censored data. Journal of American Statistical Association, 76 (375), pp. 713–719. https://www.jstor.org/stable/2287536?seq=1#page_scan_tab_contents .

LEE, E. T., DESU, M. M., GEHAN, E. A., (1975). A Monte Carlo study of the power of some two-sample tests. Biometrika, 62 (2), pp. 425–432. https://www.jstor.org/stable/2335383?seq=1#page_scan_tab_contents.

LEE, J. W., (1996). Some versatile tests based on the simultaneous use of weighted log-rank statistics. Biometrics, 52 (2), pp. 721–725. http://www.jstor.org/stable/2532911?seq=1#page_scan_tab_contents.

LEE, E. T., WANG, J. W., (2003). Statistical Methods for Survival Data Analysis. New Jersey: John Wiley&Sons Inc.

LETON, E., ZULUAGA, P., (2001). Equivalence between score and weighted tests for survival curves. Communications in Statistics - Theory and Methods,30 (4), pp. 591–608.http://www.tandfonline.com/doi/abs/10.1081/STA-100002138.

LETON, E., ZULUAGA, P., (2005). Relationships among tests for censored data. Biometrical Journal, 47 (3), pp. 377–387. http://onlinelibrary.wiley.com/doi/10.1002/bimj.200410115/abstract.

LOGAN, B. R., KLEIN, J. P., ZHANG, M. J., (2008). Comparing treatments in the presence of crossing survival curves: an application to bone marrow transplantation. Biometrics, 64 (3), pp. 733–740. https://www.ncbi.nlm.nih.gov/pubmed/18190619.

MANTEL, N., HAENSZEL, W., (1959). Statistical aspects of the analysis of data from retrospective studies of disease. Journal of National Cancer Institute, 22 (4), pp. 719–748. https://www.ncbi.nlm.nih.gov/pubmed/13655060.

MANTEL, N., (1966). Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemotherapy Reports, 50 (3),pp. 163–170. https://www.ncbi.nlm.nih.gov/pubmed/5910392.

MARTINEZ, RLMC, NARANJO, J. D., (2010). A pretest for choosing between logrank and Wilcoxon tests in the two-sample problem. Metron: International Journal of Statistics, 68 (2), pp. 111–125. https://link.springer.com/article/10.1007/BF03263529.

OLLER, R., GOMEZ, G., (2012). A generalized Fleming and Harrington’s class of tests for interval-censored data. The Canadian Journal of Statistics, 40 (3),pp. 501–516. http://onlinelibrary.wiley.com/doi/10.1002/cjs.11139/abstract.

PEPE, M. S., FLEMING, T. R., (1989). Weighted Kaplan-Meier statistics: a class of distance tests for censored survival data. Biometrics, 45, pp. 497–507. https://www.jstor.org/stable/2531492?seq=1#page_scan_tab_contents.

PETO, R, PETO, J., (1972). Asymptotically efficient rank invariant test procedures. Journal of the Royal Statistical Society, 135 (2), pp. 185–207. https://www.jstor.org/stable/2344317?seq=1#page_scan_tab_contents.

PRENTICE, R. L., MAREK, P., (1979). A qualitative discrepancy between censored data rank tests. Biometrics, 35 (4), pp. 861–867. https://www.jstor.org/stable/2530120?seq=1#page_scan_tab_contents.

STEVENSON, M., (2009). An Introduction to Survival Analysis, EpiCentre, IVABS. Massey Massey University. http://www.massey.ac.nz/massey/fms/Colleges/College%20of%20Sciences/Epicenter/docs/ASVCS/Stevenson_survival_analysis_195_721.pdf.

TARONE, R. E., WARE, J., (1977). On distribution-free tests for equality of survival distributions. Biometrika, 64, pp. 156–160. https://www.jstor.org/stable/2335790?seq=1#page_scan_tab_contents.

WANG, R., LAGAKOS, S. W., GRAY, R. J., (2010). Testing and interval estimation for two-sample survival comparisons with small sample sizes and unequal censoring. Biostatistics, 11 (4), pp. 676–692. https://www.ncbi.nlm.nih.gov/pubmed/20439258.

XIE, J., LIU, C., (2005). Adjusted Kaplan-Meier estimator and log-rank test with inverse probability of treatment weighting for survival data. Statistics in Medicine, 24 (20), pp. 3089–3110. http://onlinelibrary.wiley.com/doi/10.1002/sim.2174/abstract