Probability distributions are commonly used for describing and modeling data in several different areas. There are a lot of well-known statistical distributions however they are inefficient for modeling data in many applied areas such as lifetime analysis, finance and insurance. The selection of the appropriate probability density distribution reduces the estimation error and also allows obtaining characteristics. Hence, there is a clear need for more flexible distributions. In this study, we propose a new probability distribution to model different data sets. After defining the new probability distribution named Poisson-Lindley (PL) distribution, an application to real data demonstrates that the new distribution can provide a better fit than other classical models.