REGRESI LOGISTIK UNIVARIAT DENGAN DATA RESPON TIDAK SEIMBANG

In binary logistic regression problem it is common for the two classes to be imbalanced. One case is very rare compared to the other. This paper focus on determining Maximum Likelihood Estimator on univariate logistic regression for infinitely unbalanced data response. By finding the differential of log-likelihood equation that is resulted, its maximum depend on points given through their average . Thus we can substitute each given with or substituting all given with one . If we use normal distribution for given then the slope can be determined by simple formula where and each an average and variance for which .Keywords : Logistic Regression, MLE, Infinitely Unbalanced Data Respons