Details
| Original language | English |
|---|---|
| Pages (from-to) | 1704-1717 |
| Number of pages | 14 |
| Journal | Communications in Statistics: Simulation and Computation |
| Volume | 45 |
| Issue number | 5 |
| Early online date | 23 Apr 2016 |
| Publication status | Published - 27 May 2016 |
Abstract
In multiple comparisons of fixed effect parameters in linear mixed models, treatment effects can be reported as relative changes or ratios. Simultaneous confidence intervals for such ratios had been previously proposed based on Bonferroni adjustments or multivariate normal quantiles accounting for the correlation among the multiple contrasts. We propose Fieller-type intervals using multivariate t quantiles and the application of Markov chain Monte Carlo techniques to sample from the joint posterior distribution and construct percentile-based simultaneous intervals. The methods are compared in a simulation study including bioassay problems with random intercepts and slopes, repeated measurements designs, and multicenter clinical trials.
Keywords
- Coverage probability, Fieller, Gibbs Sampler, Multiple comparisons
ASJC Scopus subject areas
- Mathematics(all)
- Statistics and Probability
- Mathematics(all)
- Modelling and Simulation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Communications in Statistics: Simulation and Computation, Vol. 45, No. 5, 27.05.2016, p. 1704-1717.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Simultaneous Confidence Intervals for Ratios of Fixed Effect Parameters in Linear Mixed Models
AU - Schaarschmidt, Frank
AU - Djira, Gemechis D.
N1 - Publisher Copyright: Copyright © Taylor & Francis Group, LLC.
PY - 2016/5/27
Y1 - 2016/5/27
N2 - In multiple comparisons of fixed effect parameters in linear mixed models, treatment effects can be reported as relative changes or ratios. Simultaneous confidence intervals for such ratios had been previously proposed based on Bonferroni adjustments or multivariate normal quantiles accounting for the correlation among the multiple contrasts. We propose Fieller-type intervals using multivariate t quantiles and the application of Markov chain Monte Carlo techniques to sample from the joint posterior distribution and construct percentile-based simultaneous intervals. The methods are compared in a simulation study including bioassay problems with random intercepts and slopes, repeated measurements designs, and multicenter clinical trials.
AB - In multiple comparisons of fixed effect parameters in linear mixed models, treatment effects can be reported as relative changes or ratios. Simultaneous confidence intervals for such ratios had been previously proposed based on Bonferroni adjustments or multivariate normal quantiles accounting for the correlation among the multiple contrasts. We propose Fieller-type intervals using multivariate t quantiles and the application of Markov chain Monte Carlo techniques to sample from the joint posterior distribution and construct percentile-based simultaneous intervals. The methods are compared in a simulation study including bioassay problems with random intercepts and slopes, repeated measurements designs, and multicenter clinical trials.
KW - Coverage probability
KW - Fieller
KW - Gibbs Sampler
KW - Multiple comparisons
UR - http://www.scopus.com/inward/record.url?scp=84964623375&partnerID=8YFLogxK
U2 - 10.1080/03610918.2013.849741
DO - 10.1080/03610918.2013.849741
M3 - Article
AN - SCOPUS:84964623375
VL - 45
SP - 1704
EP - 1717
JO - Communications in Statistics: Simulation and Computation
JF - Communications in Statistics: Simulation and Computation
SN - 0361-0918
IS - 5
ER -