Flexible modeling of longitudinal highly skewed outcomes.
Flexible modeling of longitudinal highly skewed outcomes.
复制标题
DOI：
10.1002/sim.3754
复制
发表时间：
2009-12-30
影响因子：
2
通讯作者：
Marcus, Michele
中科院分区：
文献类型：
--
作者：
Chen, Huichao;Manatunga, Amita K.;Lyles, Robert H.;Peng, Limin;Marcus, Michele
The analysis of data from epidemiologic and environmental studies present challenges such as skewness of distribution, rounding and multiple measurements over time. To model trends over time based on repeated measurements, we propose a general latent model suitable for highly skewed data. The model assumes that the observed outcome is determined by an unobservable outcome which follows a Weibull distribution. To accommodate correlations among repeated responses over time, we introduce a general random effect from the power variance function (PVF) family of distributions, including the gamma distribution often employed in the literature. The resulting marginal likelihood has a closed form without resorting to numerical or approximation methods. We study estimation and hypothesis testing under these models, with different choices of random effect distributions. Simulation studies are conducted to evaluate their performance. Finally, we apply the proposed method to exposure data collected from the Michigan polybrominated biphenyl (MIPBB) study.
登录
查看更多内容
影响因子：
3.7
作者：
FOLLMANN, DA;LAMBERT, D
通讯作者：
LAMBERT, D
影响因子：
2.7
作者：
HOUGAARD, P
通讯作者：
HOUGAARD, P
影响因子：
2.5
作者：
BECKMAN, RJ;JOHNSON, ME
通讯作者：
JOHNSON, ME
DOI：
10.1111/j.1467-985x.2004.00337.x
发表时间：
2005-01-01
影响因子：
2
作者：
Grilli, L
通讯作者：
Grilli, L
影响因子：
1.9
作者：
HEITJAN, DF
通讯作者：
HEITJAN, DF