Abstract
Background and Objective: Meta-analysis may produce estimates that are unrepresentative of a test’s performance in practice. Tailored meta-analysis (TMA) circumvents this by deriving an applicable region for the practice and selecting the studies compatible with the region. It requires the test positive rate, r and prevalence, p being estimated for the setting but previous studies have assumed their independence. The aim is to investigate the effects a correlation between r and p has on estimating the applicable region and how this affects TMA.
Methods: Six methods for estimating 99% confidence intervals (CI) for r and p were investigated: Wilson’s 6 Bonferroni correction, Clopper-Pearson’s 6 Bonferroni correction, and Hotelling’s T2 statistic 6 continuity correction. These were analyzed in terms of the coverage probability using simulation trials over different correlations, sample sizes, and values for r and p. The methods were then applied to two published meta-analyses with associated practice data, and the effects on the applicable region, studies selected, and summary estimates were evaluated.
Results: Hotelling’s T2 statistic with a continuity correction had the highest median coverage (0.9971). This and the Clopper-Pearson method with a Bonferroni correction both had coverage consistently above 0.99. The coverage of Hotelling’s CI’s varied the least across different correlations. For both meta-analyses, the number of studies selected was largest when Hotelling’s T2 statistic was used to derive the applicable region. In one instance, this increased the sensitivity by over 4% compared with TMA estimates using other methods.
Conclusion: TMA returns estimates that are tailored to practice providing the applicable region is accurately defined. This is most likely when the CI for r and p are estimated using Hotelling’s T2 statistic with a continuity correction. Potentially, the applicable region may be obtained using routine electronic health data.
Methods: Six methods for estimating 99% confidence intervals (CI) for r and p were investigated: Wilson’s 6 Bonferroni correction, Clopper-Pearson’s 6 Bonferroni correction, and Hotelling’s T2 statistic 6 continuity correction. These were analyzed in terms of the coverage probability using simulation trials over different correlations, sample sizes, and values for r and p. The methods were then applied to two published meta-analyses with associated practice data, and the effects on the applicable region, studies selected, and summary estimates were evaluated.
Results: Hotelling’s T2 statistic with a continuity correction had the highest median coverage (0.9971). This and the Clopper-Pearson method with a Bonferroni correction both had coverage consistently above 0.99. The coverage of Hotelling’s CI’s varied the least across different correlations. For both meta-analyses, the number of studies selected was largest when Hotelling’s T2 statistic was used to derive the applicable region. In one instance, this increased the sensitivity by over 4% compared with TMA estimates using other methods.
Conclusion: TMA returns estimates that are tailored to practice providing the applicable region is accurately defined. This is most likely when the CI for r and p are estimated using Hotelling’s T2 statistic with a continuity correction. Potentially, the applicable region may be obtained using routine electronic health data.
| Original language | English |
|---|---|
| Pages (from-to) | 1-9 |
| Number of pages | 9 |
| Journal | Journal of Clinical Epidemiology |
| Volume | 106 |
| Early online date | 29 Sept 2018 |
| DOIs | |
| Publication status | Published - Feb 2019 |
Bibliographical note
Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.Keywords
- Data interpretation
- Statistical
- Decision making
- Diagnosis tests
- Routine
- Mass screening
- Meta-analysis
- Models
- Statistical 1. Introduction It is of interest to policy makers and clinicians to ensure that the
ASJC Scopus subject areas
- Epidemiology