### Abstract

In randomized cancer screening trials, mortality rates for the screened group relative to those of the control group are not likely to be constant as a function of years from randomization due to the inherent lag between initiation of screening and any putative effects of screening on mortality. In this situation, a log rank test for differences in mortality between the randomization groups will not be optimal. Although optimality could potentially be recovered by use of a weighted log rank statistic, the optimal weights are difficult to specify a priori and the potential loss of power by use of poorly specified weights is great. We describe a likelihood ratio test with two degrees of freedom for use in this situation which is based on a fit of a weakly structured full model. Computation of an approximate significance level for this test is described and a large sample justification for this approximation is given. Size and power properties of the proposed statistic are compared to that of several other statistics in a small simulation study and the statistic is applied to data from the HIP Breast Cancer Screening Trial.

Original language | English (US) |
---|---|

Pages (from-to) | 44-50 |

Number of pages | 7 |

Journal | Biometrics |

Volume | 51 |

Issue number | 1 |

DOIs | |

State | Published - May 30 1995 |

Externally published | Yes |

### Fingerprint

### Keywords

- Cancer
- Likelihood ratio
- Screening Trial

### ASJC Scopus subject areas

- Agricultural and Biological Sciences(all)
- Public Health, Environmental and Occupational Health
- Agricultural and Biological Sciences (miscellaneous)
- Applied Mathematics
- Statistics and Probability

### Cite this

*Biometrics*,

*51*(1), 44-50. https://doi.org/10.2307/2533313

**A likelihood ratio test for cancer screening trials.** / Self, S. G.; Etzioni, Ruth.

Research output: Contribution to journal › Article

*Biometrics*, vol. 51, no. 1, pp. 44-50. https://doi.org/10.2307/2533313

}

TY - JOUR

T1 - A likelihood ratio test for cancer screening trials

AU - Self, S. G.

AU - Etzioni, Ruth

PY - 1995/5/30

Y1 - 1995/5/30

N2 - In randomized cancer screening trials, mortality rates for the screened group relative to those of the control group are not likely to be constant as a function of years from randomization due to the inherent lag between initiation of screening and any putative effects of screening on mortality. In this situation, a log rank test for differences in mortality between the randomization groups will not be optimal. Although optimality could potentially be recovered by use of a weighted log rank statistic, the optimal weights are difficult to specify a priori and the potential loss of power by use of poorly specified weights is great. We describe a likelihood ratio test with two degrees of freedom for use in this situation which is based on a fit of a weakly structured full model. Computation of an approximate significance level for this test is described and a large sample justification for this approximation is given. Size and power properties of the proposed statistic are compared to that of several other statistics in a small simulation study and the statistic is applied to data from the HIP Breast Cancer Screening Trial.

AB - In randomized cancer screening trials, mortality rates for the screened group relative to those of the control group are not likely to be constant as a function of years from randomization due to the inherent lag between initiation of screening and any putative effects of screening on mortality. In this situation, a log rank test for differences in mortality between the randomization groups will not be optimal. Although optimality could potentially be recovered by use of a weighted log rank statistic, the optimal weights are difficult to specify a priori and the potential loss of power by use of poorly specified weights is great. We describe a likelihood ratio test with two degrees of freedom for use in this situation which is based on a fit of a weakly structured full model. Computation of an approximate significance level for this test is described and a large sample justification for this approximation is given. Size and power properties of the proposed statistic are compared to that of several other statistics in a small simulation study and the statistic is applied to data from the HIP Breast Cancer Screening Trial.

KW - Cancer

KW - Likelihood ratio

KW - Screening Trial

UR - http://www.scopus.com/inward/record.url?scp=0029005031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029005031&partnerID=8YFLogxK

U2 - 10.2307/2533313

DO - 10.2307/2533313

M3 - Article

C2 - 7766795

AN - SCOPUS:0029005031

VL - 51

SP - 44

EP - 50

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 1

ER -