Abstract
In this article we consider the problem of sample size determination for two-level mixed-effects logistic regression models for the analysis of longitudinal data. In this case, level 1 represents measurement occasion and level 2 represents subject. We provide an algorithm for sample size requirements (i.e., power characteristics) for a test of the treatment-by-time interaction and overall time trend that strictly maintains the type I error rate close to the nominal level. The methodology is illustrated both via simulation and an example from a now classic psychiatric randomized clinical trial.
| Original language | English |
|---|---|
| Title of host publication | Research in Applied Statistical Science |
| Publisher | Nova Science Publishers, Inc. |
| Pages | 11-21 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781633218192 |
| ISBN (Print) | 9781633218185 |
| State | Published - 1 Oct 2014 |
Fingerprint
Keywords
- Hierarchical models
- Marginal maximum likelihood
- Power analysis
- Type I error rate
Cite this
}
Sample size determination for between group comparisons in mixed-effects logistic regression models for analysis of longitudinal data. / Bhaumik, Dulal K.; Aryal, Subhash; Amatya, Anup; Kapur, Kush.
Research in Applied Statistical Science. Nova Science Publishers, Inc., 2014. p. 11-21.Research output: Chapter in Book/Report/Conference proceeding › Chapter
TY - CHAP
T1 - Sample size determination for between group comparisons in mixed-effects logistic regression models for analysis of longitudinal data
AU - Bhaumik, Dulal K.
AU - Aryal, Subhash
AU - Amatya, Anup
AU - Kapur, Kush
PY - 2014/10/1
Y1 - 2014/10/1
N2 - In this article we consider the problem of sample size determination for two-level mixed-effects logistic regression models for the analysis of longitudinal data. In this case, level 1 represents measurement occasion and level 2 represents subject. We provide an algorithm for sample size requirements (i.e., power characteristics) for a test of the treatment-by-time interaction and overall time trend that strictly maintains the type I error rate close to the nominal level. The methodology is illustrated both via simulation and an example from a now classic psychiatric randomized clinical trial.
AB - In this article we consider the problem of sample size determination for two-level mixed-effects logistic regression models for the analysis of longitudinal data. In this case, level 1 represents measurement occasion and level 2 represents subject. We provide an algorithm for sample size requirements (i.e., power characteristics) for a test of the treatment-by-time interaction and overall time trend that strictly maintains the type I error rate close to the nominal level. The methodology is illustrated both via simulation and an example from a now classic psychiatric randomized clinical trial.
KW - Hierarchical models
KW - Marginal maximum likelihood
KW - Power analysis
KW - Type I error rate
UR - http://www.scopus.com/inward/record.url?scp=84954159982&partnerID=8YFLogxK
M3 - Chapter
AN - SCOPUS:84954159982
SN - 9781633218185
SP - 11
EP - 21
BT - Research in Applied Statistical Science
PB - Nova Science Publishers, Inc.
ER -