Recurrent events occur in many scientific areas: engineering, reliability, biomedicine, public health, industry, and economics. Examples of recurrent events are failure of electronic and mechanical systems, nuclear power plant accidents, occurrence of shocks, hospitalization of a person with a chronic disease, re-occurrence of a tumor, outbreak of a disease, and the Dow Jones Industrial Average decreasing by at least 200 points during a trading day. The stochastic modeling and the appropriate statistical inference for such models are therefore of utmost importance. In this talk I will discuss several classes of models for recurrent events and discuss methods of inference for such models. Focus will be in the semi-parametric inference for such models. The statistical analysis of recurrent event models requires care and caution because in the monitoring of such events, informative censoring occurs because of a sum-quota accrual scheme, which also leads to the number of events observed per experimental unit to be informative. Some concrete applications will be also be illustrated.