We develop a scale-invariant truncated Levy (STL) process to describe physi
cal systems characterized by correlated stochastic variables. The STL proce
ss exhibits Levy stability for the probability density, and hence shows sca
ling properties (as observed in empirical data); it has the advantage that
all moments are finite (and so accounts for the empirical scaling of the mo
ments). To test the potential utility of the STL process, we analyze financ
ial data. (C) 2001 Elsevier Science B.V. All rights reserved.