REVISITING THE PERFORMANCE OF CONTINUITY CORRECTION METHODS IN META-ANALYSIS OF SPARSE DATA
Author(s)
Parks DC1, Bhattacharyya A2
1GSK, Phoenixville, PA, USA, 2GSK, King of Prussia, PA, USA
OBJECTIVES: Meta-analysis with binary data often requires combining results from multiple studies with zero cell events. Combining such data can be problematic, as continuity corrections are needed, which can influence results and conclusions. The “treatment arm” continuity correction (TACC, M. Sweeting et al
Conference/Value in Health Info
2016-05, ISPOR 2016, Washington DC, USA
Value in Health, Vol. 19, No. 3 (May 2016)
Code
PRM159
Topic
Methodological & Statistical Research
Topic Subcategory
Confounding, Selection Bias Correction, Causal Inference
Disease
Multiple Diseases