skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Joint non-parametric correction estimator for excess relative risk regression in survival analysis with exposure measurement error

Authors:
 [1];  [2];  [3];  [1]
  1. Fred Hutchinson Cancer Research Center, Seattle USA
  2. Radiation Effects Research Foundation, Hiroshima Japan
  3. University of Georgia, Athens USA
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1401054
Grant/Contract Number:
HS0000031; 18-59
Resource Type:
Journal Article: Publisher's Accepted Manuscript
Journal Name:
Journal of the Royal Statistical Society: Series B (Statistical Methodology)
Additional Journal Information:
Journal Name: Journal of the Royal Statistical Society: Series B (Statistical Methodology); Journal Volume: 79; Journal Issue: 5; Related Information: CHORUS Timestamp: 2017-10-30 01:10:28; Journal ID: ISSN 1369-7412
Publisher:
Wiley-Blackwell
Country of Publication:
United Kingdom
Language:
English

Citation Formats

Wang, Ching-Yun, Cullings, Harry, Song, Xiao, and Kopecky, Kenneth J. Joint non-parametric correction estimator for excess relative risk regression in survival analysis with exposure measurement error. United Kingdom: N. p., 2017. Web. doi:10.1111/rssb.12230.
Wang, Ching-Yun, Cullings, Harry, Song, Xiao, & Kopecky, Kenneth J. Joint non-parametric correction estimator for excess relative risk regression in survival analysis with exposure measurement error. United Kingdom. doi:10.1111/rssb.12230.
Wang, Ching-Yun, Cullings, Harry, Song, Xiao, and Kopecky, Kenneth J. Mon . "Joint non-parametric correction estimator for excess relative risk regression in survival analysis with exposure measurement error". United Kingdom. doi:10.1111/rssb.12230.
@article{osti_1401054,
title = {Joint non-parametric correction estimator for excess relative risk regression in survival analysis with exposure measurement error},
author = {Wang, Ching-Yun and Cullings, Harry and Song, Xiao and Kopecky, Kenneth J.},
abstractNote = {},
doi = {10.1111/rssb.12230},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
number = 5,
volume = 79,
place = {United Kingdom},
year = {Mon Feb 27 00:00:00 EST 2017},
month = {Mon Feb 27 00:00:00 EST 2017}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1111/rssb.12230

Save / Share:
  • We describe the details of the binned bispectrum estimator as used for the official 2013 and 2015 analyses of the temperature and polarization CMB maps from the ESA Planck satellite. The defining aspect of this estimator is the determination of a map bispectrum (3-point correlation function) that has been binned in harmonic space. For a parametric determination of the non-Gaussianity in the map (the so-called f NL parameters), one takes the inner product of this binned bispectrum with theoretically motivated templates. However, as a complementary approach one can also smooth the binned bispectrum using a variable smoothing scale in ordermore » to suppress noise and make coherent features stand out above the noise. This allows one to look in a model-independent way for any statistically significant bispectral signal. This approach is useful for characterizing the bispectral shape of the galactic foreground emission, for which a theoretical prediction of the bispectral anisotropy is lacking, and for detecting a serendipitous primordial signal, for which a theoretical template has not yet been put forth. Both the template-based and the non-parametric approaches are described in this paper.« less
  • When assessing the impact of radiation exposure it is common practice to present the final conclusions in terms of excess lifetime cancer risk in a population exposed to a given dose. The present investigation is mainly a methodological study focusing on some of the major issues and uncertainties involved in calculating such excess lifetime risks and related risk projection methods. The age-constant relative risk model used in the recent analyses of the cancer mortality that was observed in the follow-up of the cohort of A-bomb survivors in Hiroshima and Nagasaki is used to describe the effect of the exposure onmore » the cancer mortality. In this type of model the excess relative risk is constant in age-at-risk, but depends on the age-at-exposure. Calculation of excess lifetime risks usually requires rather complicated life-table computations. In this paper we propose a simple approximation to the excess lifetime risk; the validity of the approximation for low levels of exposure is justified empirically as well as theoretically. This approximation provides important guidance in understanding the influence of the various factors involved in risk projections. Among the further topics considered are the influence of a latent period, the additional problems involved in calculations of site-specific excess lifetime cancer risks, the consequences of a leveling off or a plateau in the excess relative risk, and the uncertainties involved in transferring results from one population to another. The main part of this study relates to the situation with a single, instantaneous exposure, but a brief discussion is also given of the problem with a continuous exposure at a low-dose rate.« less
  • There are well-known associations of ionizing radiation with female breast cancer, and emerging evidence also for male breast cancer. In the UK, female breast cancer following occupational radiation exposure is among that set of cancers eligible for state compensation and consideration is currently being given to an extension to include male breast cancer. The objectives here, compare radiation-associated excess relative and absolute risks of male and female breast cancers. Breast cancer incidence and mortality data in the Japanese atomic-bomb survivors were analyzed using relative and absolute risk models via Poisson regression. As a result, we observed significant ( p≤ 0.01)more » dose-related excess risk for male breast cancer incidence and mortality. For incidence and mortality data, there are approximate 15-fold and 5- fold elevations, respectively, of relative risk for male compared with female breast cancer incidence, the former borderline significant (p = 0.050). In contrast, for incidence and mortality data there are approximate 20-fold and 10-fold elevations, respectively, of female absolute risk compared with male, both statistically significant (p < 0.001). There are no indications of differences between the sexes in age/time-since-exposure/age-at-exposure modifications to the relative or absolute excess risk. The probability of causation of male breast cancer following radiation exposure exceeds by at least 5-fold that of many other malignancies. In conclusion, there is evidence of much higher radiation-associated relative risk for male than for female breast cancer, although absolute excess risks for males are much less than for females. However, the small number of male cases and deaths suggests a degree of caution in interpretation of this finding.« less
  • There are well-known associations of ionizing radiation with female breast cancer, and emerging evidence also for male breast cancer. In the UK, female breast cancer following occupational radiation exposure is among that set of cancers eligible for state compensation and consideration is currently being given to an extension to include male breast cancer. The objectives here, compare radiation-associated excess relative and absolute risks of male and female breast cancers. Breast cancer incidence and mortality data in the Japanese atomic-bomb survivors were analyzed using relative and absolute risk models via Poisson regression. As a result, we observed significant ( p≤ 0.01)more » dose-related excess risk for male breast cancer incidence and mortality. For incidence and mortality data, there are approximate 15-fold and 5- fold elevations, respectively, of relative risk for male compared with female breast cancer incidence, the former borderline significant (p = 0.050). In contrast, for incidence and mortality data there are approximate 20-fold and 10-fold elevations, respectively, of female absolute risk compared with male, both statistically significant (p < 0.001). There are no indications of differences between the sexes in age/time-since-exposure/age-at-exposure modifications to the relative or absolute excess risk. The probability of causation of male breast cancer following radiation exposure exceeds by at least 5-fold that of many other malignancies. In conclusion, there is evidence of much higher radiation-associated relative risk for male than for female breast cancer, although absolute excess risks for males are much less than for females. However, the small number of male cases and deaths suggests a degree of caution in interpretation of this finding.« less