Analyzing dependence structure of thyroid hormones: a copula approach

Aim: To model the level and structure of the dependence between thyroid hormones by using the copula approach.Materials and methods: Dependence models were constructed with the help of copula functions explaining the relationships between thyroid hormones for the data supplied by Dokuz Eylül University’s Faculty of Medicine’s endocrine laboratory. For this purpose, 684 patients aged 0-85 were examined.Results: Results indicated that none of the pairs of thyroid hormones exhibited a tail dependence structure; however, valid models exhibited a symmetric dependence structure. The findings implied that both the T3 and T4 levels had a significant dependence structure with TSH levels. Furthermore, Gaussian and t-copula structures were appropriate for the pairs.Conclusion: Findings were compared with the results of conventional scalar measures to establish the importance of using copula models in analyzing thyroid hormone levels. Findings showed that the copula models revealed better indicators for health scientists for more accurate dependence modeling.