Photo from archive.org
Abstract In this study, we reformulate pairwise comparisons as penalized likelihood estimation problems based on the L 1 penalties on the pairwise differences. The proposed approach offers a natural way… Click to show full abstract
Abstract In this study, we reformulate pairwise comparisons as penalized likelihood estimation problems based on the L 1 penalties on the pairwise differences. The proposed approach offers a natural way to avoid logically contradictory conclusions resulting from pairwise comparisons. Moreover, we show that under appropriate conditions, all nulls are not rejected and all alternatives are rejected with probability going to one. Two examples based on real data are used to illustrate the proposed method.
Keywords:
multiple comparisons;
pairwise;
test consistency;
pairwise multiple;
consistency pairwise;
logical test
Journal Title: Journal of Statistical Planning and Inference
Year Published: 2020
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!
Journal Title: Journal of Statistical Planning and Inference
Year Published: 2020
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!