Abstract
Combining p-values from independent statistical tests is a popular approach to meta-analysis, particularly when the data underlying the tests are either no longer available or are difficult to combine. Numerous p-value combination methods appear in the literature, each with different statistical properties, yet often the final choice used in a meta-analysis can seem arbitrary, as if all effort has been expended in building the models that gave rise to the p-values. Birnbaum (1954) showed that any reasonable p-value combiner must be optimal against some alternative hypothesis. Starting from this perspective and recasting each method of combining p-values as a likelihood ratio test, we present theoretical results for some standard combiners that provide guidance on how a powerful combiner might be chosen in practice.
Original language | English |
---|---|
Pages (from-to) | 239-246 |
Number of pages | 8 |
Journal | Biometrika |
Volume | 105 |
Issue number | 1 |
Early online date | 4 Jan 2018 |
DOIs | |
Publication status | Published - Mar 2018 |
Keywords
- Edgington's method
- Fisher's method
- George's method
- Meta-analysis
- Pearson's method
- Stouffer's method
- Tippett's method
Fingerprint Dive into the research topics of 'Choosing between methods of combining <sub><i>p</i></sub>-values'. Together they form a unique fingerprint.
Profiles
-
Dr Patrick Rubin-Delanchy
- School of Mathematics - Associate Professor in Statistical Science
Person: Academic