Network estimation of multi-dimensional binary variables with application to divorce data

The cross-integration of statistics with social and scientific applications is one the most popular topics in past decade. Motivated by divorce data collected from rural areas Sichuan Province, China, we propose a new method to estimate network multiple binary variables, which specifies dependence structures variables through Gaussian copula model. Method moments employed latent correlation matrix variables. Alternating direction multipliers algorithm then used corresponding empirical matrix. This modifies traditional estimation perspectives computational efficiency positive definite guarantee. Analysis conducted for illustration.