2018/04/03 by Kengo Nagashima, Hisashi Noma, Nagashima, Kengo +3 · 6 citations
Agricultural and Biological Sciences · Decision Sciences · #Agriculture, Soil, Plant Science #Meta-analysis and systematic reviews #Optimal Experimental Design Methods
paper · doi:10.1177/0962280218773520
openalex created_date 2018/04/13 · openalex publication_date 2018/05/10 · openalex updated_date 2026/07/31
Prediction intervals are commonly used in meta-analysis with random-effects models. One widely used method, the Higgins-Thompson-Spiegelhalter prediction interval, replaces the heterogeneity parameter with its point estimate, but its validity strongly depends on a large sample approximation. This is a weakness in meta-analyses with few studies. We propose an alternative based on bootstrap and show by simulations that its coverage is close to the nominal level, unlike the Higgins-Thompson-Spiegelhalter method and its extensions. The proposed method was applied in three meta-analyses.