On the exact null-distribution of a test for homogeneity of the risk ratio in meta-analysis of studies with rare events
On the exact null-distribution of a test for homogeneity of the risk ratio in meta-analysis of studies with rare events
This paper focuses on the test for homogeneity of relative risk in meta-analysisof count outcomes. Meta-analysis of studies with rare events faces particular chal-lenges, since the number of studies are low and the frequency of events may besmall in some or all treatment arms. In such a case, the conventional chi-square testfor homogeneity becomes undefined and we suggest a new chi-square test which isalways defined. However, the chi-square approximation is poor. We therefore intro-duce methodology to obtain its exact distribution which is based on the productbinomial likelihood. The exact p-value is then derived and the performance of themethod is investigated using simulations. The results show that the type I error ofthe proposed method satisfies the nominal significance level in rare events situations.Also, the exact distribution behaves very similar to the simulated distribution. Areal data example of a meta-analysis with an extreme form of rare event studies isused to illustrate the new test.
420-434
Bohning, Dankmar
1df635d4-e3dc-44d0-b61d-5fd11f6434e1
Sangnawakij, Patarawan
e821a2a7-a89f-4172-9006-8a6c2db9add6
Holling, Heinz
88d46f56-77ca-4d0e-b035-a51aff735435
Bohning, Dankmar
1df635d4-e3dc-44d0-b61d-5fd11f6434e1
Sangnawakij, Patarawan
e821a2a7-a89f-4172-9006-8a6c2db9add6
Holling, Heinz
88d46f56-77ca-4d0e-b035-a51aff735435
Bohning, Dankmar, Sangnawakij, Patarawan and Holling, Heinz
(2020)
On the exact null-distribution of a test for homogeneity of the risk ratio in meta-analysis of studies with rare events.
Journal of Statistical Computation and Simulation, 91 (2), .
(doi:10.1080/00949655.2020.1815200).
Abstract
This paper focuses on the test for homogeneity of relative risk in meta-analysisof count outcomes. Meta-analysis of studies with rare events faces particular chal-lenges, since the number of studies are low and the frequency of events may besmall in some or all treatment arms. In such a case, the conventional chi-square testfor homogeneity becomes undefined and we suggest a new chi-square test which isalways defined. However, the chi-square approximation is poor. We therefore intro-duce methodology to obtain its exact distribution which is based on the productbinomial likelihood. The exact p-value is then derived and the performance of themethod is investigated using simulations. The results show that the type I error ofthe proposed method satisfies the nominal significance level in rare events situations.Also, the exact distribution behaves very similar to the simulated distribution. Areal data example of a meta-analysis with an extreme form of rare event studies isused to illustrate the new test.
Text
Exact_Q_Revise01
- Accepted Manuscript
More information
Accepted/In Press date: 22 August 2020
e-pub ahead of print date: 8 October 2020
Identifiers
Local EPrints ID: 443631
URI: http://eprints.soton.ac.uk/id/eprint/443631
ISSN: 0094-9655
PURE UUID: f989f4ee-d989-4b7a-84ce-c8a0b9640f93
Catalogue record
Date deposited: 07 Sep 2020 16:30
Last modified: 28 Apr 2022 06:14
Export record
Altmetrics
Contributors
Author:
Patarawan Sangnawakij
Author:
Heinz Holling
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
