Explore poverty with statistical modeling: The bivariate polynomial binary logit regression (BPBLR)

Logit regression (or logistic regression) is a statistical analysis of categorical data. The binary responses have two categories. We present the Bivariate Polynomial Binary Logit Regression (BPBLR), which extends logit regression by modeling two correlated binary response variables. This model uses a polynomial pattern to capture the association between the logit and predictor variables. The maximum likelihood estimation (MLE) method is used for parameter estimation, and the maximum likelihood ratio test (MLRT) method is used for the statistical testing of the proposed model. The distribution of the test statistics asymptotically is the Chi-square distribution. Selection of the optimal polynomial degree and the best model is based on the minimum Deviance value. Some highlights of the proposed method are:•Statistical modeling innovation on categorical data with two correlated binary response variables, namely Bivariate Polynomial Binary Logit Regression (BPBLR).•The statistical test is obtained using MLRT method.•The BPBLR model is applied to actual datasets regarding the depth and severity of poverty to capture poverty problems SDGs 1.