Power-law tail behavior and the summation scheme of Levy-stable distributio
ns is the basis for their frequent use as models when fat tails above a Gau
ssian distribution are observed. However, recent studies suggest that finan
cial asset returns exhibit tail exponents well above the Levy-stable regime
(0 < alpha < 2). In this paper, we illustrate that widely used tail index
estimates (log-log linear regression and Hill) can give exponents well abov
e the asymptotic limit for alpha close to 2, resulting in overestimation of
the tail exponent in finite samples. The reported value of the tail expone
nt alpha around 3 may very well indicate a Levy-stable distribution with al
pha approximate to 1.8.