## Abstract

Diagnostic odds ratio (DOR) is defined as the ratio of the odds of the positivity of a diagnostic test results in the disease population relative to that in the non-diseased population. It is a function of sensitivity and specificity and hence considered as an indicator of diagnostic accuracy. The naïve estimator functions of DOR fails when either sensitivity or specificity is close to 1. We propose several methods to adjust for such situation. Agresti and Coull (AC) adjustment is a common and straightforward way for extreme binomial proportions. Another way is to apply Moving extreme ranked set sampling (MERSS) = which estimates the odds by sum of indicators and thus avoid the situation of dividing by 0. For a more complete comparison of methods, we also include the estimation method based on the basic ranked set sampling (RSS) The asymptotic mean and variance of the proposed estimators are derived, hence all methods readily apply for the confidence interval estimating and hypothesis testing of DOR. An intensive simulation study is conducted to compare the efficiency of the proposed methods. The proposed methods are illustrated using a real data set.

Original language | American English |
---|---|

State | Published - Aug 12 2015 |

Event | Joint Statistical Meeting (JSM) - Duration: Aug 11 2015 → … |

### Conference

Conference | Joint Statistical Meeting (JSM) |
---|---|

Period | 08/11/15 → … |

## Keywords

- Moving extreme ranked set sampling
- Diagnostic odds ratio
- AC adjustment
- Nonparametric test

## DC Disciplines

- Biostatistics
- Public Health