Wang Jiali, Westveld Anton H, Welsh A H, Parker Melissa, Loong Bronwyn
Research School of Finance, Actuarial Studies and Statistics, College of Business and Economics, The Australian National University, Canberra, ACT, Australia.
Canberra Endometriosis Centre, Centenary Hospital for Women and Children, ACT Health, Canberra, ACT, Australia.
PLoS One. 2021 Mar 18;16(3):e0248340. doi: 10.1371/journal.pone.0248340. eCollection 2021.
A high prevalence of menstrual disturbance has been reported among teenage girls, and research shows that there are delays in diagnosis of endometriosis among young girls. Using data from the Menstrual Disorder of Teenagers Survey (administered in 2005 and 2016), we propose a Gaussian copula model with graphical lasso prior to identify cohort differences in menstrual characteristics and to predict endometriosis. The model includes random effects to account for clustering by school, and we use the extended rank likelihood copula model to handle variables of mixed-type. The graphical lasso prior shrinks the elements in the precision matrix of a Gaussian distribution to encourage a sparse graphical structure, where the level of shrinkage is adaptable based on the strength of the conditional associations among questions in the survey. Applying our proposed model to the menstrual disorder data set, we found that menstrual disturbance was more pronouncedly reported over a decade, and we found some empirical differences between those girls with higher risk of developing endometriosis and the general population.
据报道，青少年女孩月经紊乱的患病率很高，而且研究表明，年轻女孩中子宫内膜异位症的诊断存在延迟。利用青少年月经紊乱调查（于2005年和2016年进行）的数据，我们提出了一种带有图形拉索先验的高斯Copula模型，以识别月经特征的队列差异并预测子宫内膜异位症。该模型包括随机效应以考虑学校层面的聚类情况，并且我们使用扩展秩似然Copula模型来处理混合型变量。图形拉索先验会收缩高斯分布精度矩阵中的元素，以鼓励形成稀疏的图形结构，其中收缩程度可根据调查中问题之间条件关联的强度进行调整。将我们提出的模型应用于月经紊乱数据集后，我们发现十年来月经紊乱的报告更为明显，并且我们发现患子宫内膜异位症风险较高的女孩与一般人群之间存在一些经验差异。
