Carroll Rachel, Lawson Andrew B, Faes Christel, Kirby Russell S, Aregay Mehreteab, Watjou Kevin
Department of Public Health Sciences, Medical University of South Carolina, 135 Cannon St, Charleston, SC 29425, USA.
Interuniversity Institute for Statistics and Statistical Bioinformatics, Hasselt University, 3500 Hasselt, Belgium.
Int J Environ Res Public Health. 2017 May 9;14(5):503. doi: 10.3390/ijerph14050503.
Oral cavity and pharynx cancer, even when considered together, is a fairly rare disease. Implementation of multivariate modeling with lung and bronchus cancer, as well as melanoma cancer of the skin, could lead to better inference for oral cavity and pharynx cancer. The multivariate structure of these models is accomplished via the use of shared random effects, as well as other multivariate prior distributions. The results in this paper indicate that care should be taken when executing these types of models, and that multivariate mixture models may not always be the ideal option, depending on the data of interest.
口腔和咽癌，即便合在一起考虑，也是一种相当罕见的疾病。对肺癌、支气管癌以及皮肤黑素瘤实施多变量建模，可能会对口腔和咽癌得出更好的推断。这些模型的多变量结构是通过使用共享随机效应以及其他多变量先验分布来实现的。本文的结果表明，在执行这类模型时应谨慎，并且根据所关注的数据，多变量混合模型可能并不总是理想的选择。
