Statistical physics is a scientific field dealing with mathematical description of nature.
Statistical physics can describe a wide variety of fields which are treated statistically due to their inherently probabilistic nature. Some examples would include many problems in quantum physics such as nuclear reactions, and various events in the fields of biology, chemistry, neurology and even sociology.
Another set of problems in statistical physics are classical systems which have so many variables, or degrees of freedom, that an exact solution is not possible or not really useful. A statistical approach works very well, since the number of degrees of freedom is extremely large. This is also often called Statistical mechanics and can describe work in non-linear dynamics, Chaos theory, thermal physics, fluid dynamics, or plasma physics.
Although there are some problems in statistical physics which can be solved analytically using approximations and expansions, most current research utilizes the large processing power of modern computers to simulate or approximate solutions. A very common approach to statistical problems is to use a monte-carlo simulation, to yield insight into the dynamics of a complex system.