Analysis of economic data relating to the level of poverty in Indonesia is conducted to determine the factors that affect the poverty index. This needs to be done as a material for the government's consideration in planning national development. Model analysis was performed using a logistic regression model. Logistic regression analysis is a statistical analysis method that describes the relationship between the dependent variable (response) which has two or more categories with one or more independent variables (predictors) on the category scale or interval scale, with the dependent variable coded zero if the province has a poverty percentage below percentage of poverty in Indonesia, and coded if the province has a poverty percentage above or equal to the percentage of poverty in Indonesia. This study aims to analyze the level of poverty in Indonesia using a logistic regression model. Parameter estimation is done using the Stochastic Restricted Maximum Likelihood Estimator (SRMLE), where this method can only be used on data containing multicollinearity. Multicollinearity data often appears in economic data because an increase in the value of one variable will affect the increase in other variables. Four independent variables were taken, namely the unemployment percentage, the underemployment percentage, the poverty depth index and the poverty severity index. Of the four variables, the Poverty Depth Index and Poverty Severity Index are variables that contain multicollinearity. The results of the analysis with a significance level of 0.05 indicate that the percentage of unemployment and depth of the poverty Index are significant variables for the poverty rate in Indonesia.