Abstract
The small sample likelihood inference method (Barndorff-Neilsen and Cox, 1994) is applied to Fieller’s problem for normal distributions with unknown unequal variances and extended to non-normal distributions. The proposed method is applied to a bioequivalence study of two formulations of a drug product. Examples and simulation studies show that the proposed method for the ratio of means demonstrates essentially exact coverage probabilities even for small samples.
Original language | English |
---|---|
Pages (from-to) | 181-190 |
Number of pages | 10 |
Journal | Computational Statistics and Data Analysis |
Volume | 38 |
Issue number | 2 |
DOIs | |
State | Published - Dec 28 2001 |
Keywords
- Ancillary
- Fieller’s interval
- Ratio of means
- Signed log-likelihood ratio statistic
- r*-formula
ASJC Scopus subject areas
- Statistics and Probability
- Computational Mathematics
- Computational Theory and Mathematics
- Applied Mathematics