Comment: Fuzzy and Randomized Confidence Intervals and P-Values

Brown, Lawrence D.; Cai, T. Tony; Dasgupta, Anirban

doi:10.1214/088342305000000395

Search citation statements

Order By: Relevance

Paper Sections

Select...

Randomization Mid-p and Continuity Correction1

Comparative Studies1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2010

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another commonly used device in dealing with discrete distributions is called (somewhat optimistically) a continuity correction, for example adding or subtracting 1/2 (or more generally another constant) from the observed number of successes. Although there is some advocacy of continuity corrections with respect to the binomial problem in the literature, it appears that there are better-performing ways to deal with the discreteness [2,36].…”

Section: Randomization Mid-p and Continuity Correctionmentioning

confidence: 99%

“…Vollset [53] reviews in detail thirteen methods, recommending a continuitycorrected Wilson score method (strongly disfavored by Refs. [2,36]), but describing as "safe" the C-P intervals, mid-P intervals, and Wilson score intervals without the continuity correction. He finds likelihood-ratio intervals to be too narrow for boundary outcomes.…”

Section: Comparative Studiesmentioning

confidence: 99%

See 1 more Smart Citation