You are not currently logged in.
Access JSTOR through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Robust Tests for Survival Data Involving a Single Continuous Covariate
Michael P. Jones
Scandinavian Journal of Statistics
Vol. 18, No. 4 (1991), pp. 323-332
Published by: Wiley on behalf of Board of the Foundation of the Scandinavian Journal of Statistics
Stable URL: http://www.jstor.org/stable/4616214
Page Count: 10
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
For a general relative risk hazard model, the standard testing procedure is the Cox score test. Unfortunately, it is very sensitive to outliers among the covariates. For the case of one covariate, two general classes of statistics are proposed that should have both good efficiency and good robustness properties. Members of these classes along with the Cox score statistic and some ad-hoc robust procedures are compared for power, with and without covariate contamination, for both large and small sample settings. On the basis of local efficiency and robustness considerations, one statistic is recommended as a supplement to the Cox score test.
Scandinavian Journal of Statistics © 1991 Board of the Foundation of the Scandinavian Journal of Statistics