Subsampling method is one method that can be used to solve big data problems. In this paper focus on estimation in Poisson Regression using Maximum Likelihood Estimation (MLE). In this study will be discussed about the implementation of the Subsampling method of The Demand for Medical Care data. In the subsampling, some subsamples will be taken with different number which will be searched for the best model among the subsamples. The results of this study obtained parameter estimates and Poisson regression models on each subsample. In the subsample with the highest number has the better model among other subsamples due to obtaining the smaller value of AIC (Akaike Information Criterion).