In this talk, an introduction of classical Extreme Value Theory (EVT)
is presented as a tool to understand the properties of the tail of the
probability distribution of a stochastic variable. First, we take a
look at the statistical behavior of \(M_n=\max \{X_1, X_2, \cdots,
X_n\}\) where \(X_1, X_2, \cdots, X_n\) is a sequence of i.i.d. RV's
having common distribution function \(F\). The result of classical EVT
for independent processes was extended to apply to a wide class of
dependent (stationary) sequences satisfying the \(D(u_n)\) and
\(D'(u_n)\) conditions. Finally, I will mention one of the examples
for EVT on a dynamical system such as the Arnold Cat Map.
|