Estimation of Binary Logistic Regression Using the Maximum Likelihood Method

This study discusses parameter estimation in binary logistic regression using maximumlikelihood. Binary logistic regression is a logistic regression with the dependent variablebeing dichotomous or consisting of 2 categories. The parameter estimation method usedis maximum likelihood estimation. The model parameters were simultaneously tested by thelikelihood ratio test and the model parameters were partially tested by the wald test. Logittransformation was performed to obtain a binary logistic regression model. Based on the results obtained, there are 3 independent variables that significantly affect chronic obstructive pulmonary disease, namely FEV1, FVC, and FEF 25-75. From the likelihood ratio test obtained a significance value of α ≤ 0.05 so it can be concluded that the model is significant. From the Wald test the independent variables that affect chronic obstructive pulmonary disease are FEV1, FVC, and FEF 25-75. The logistic regression model obtained is g(x) = -0.488 + 0.083 x1 - 0.182 x2 + 0.143 x3 - 0.036 x4