This paper presents a methodology to estimate solar irradiance using an empiric-stochastic approach, which is based on the computation of normalization parameters from the solar irradiance data. For this study, the solar irradiance data were collected in a weather station during a year. Posttreatment included a trimmed moving average to smooth the data, the performance of a fitting procedure using a simple model to recover normalization parameters, and the estimation of a probability density, which evolves along the daytime, by means of a kernel density estimation method. The normalization parameters correspond to characteristic physical variables that allow us to decouple the short- and long-term behaviors of solar irradiance and to describe their average trends with simple equations. The normalization parameters and the probability densities allowed us to build an empiric-stochastic methodology that generates an estimate of the solar irradiance. Finally, in order to validate our method, we had run simulations of solar irradiance and afterward computed the theoretical generation of solar power, which in turn had been compared with the experimental data retrieved from a commercial photovoltaic system. Since the simulation results show a good agreement with the experimental data, this simple methodology can generate the synthetic data of solar power production and may help to design and test a photovoltaic system before installation.