2007 | OriginalPaper | Buchkapitel
Extreme Returns in Asset Prices
Erschienen in: Statistical Analysis of Extreme Values
Verlag: Birkhäuser Basel
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Throughout this chapter, we assume that speculative prices
s
t
like those pertaining to stocks, foreign currencies, futures etc. are evaluated at discrete times
t
= 0, 1, 2, . . ., where the periods can be days or weeks. Thus, if
s
0
is the price of an investment at time
t
= 0, then the return—the difference of prices taken relatively to the initial price—at time
T
is (
s
T
−
s
0
)/
s
0
. Our primary interest concerns daily returns under discrete compounding (arithmetic returns)
$$ \tilde r_t = \frac{{s_t - s_{t - 1} }} {{s_{t - 1} }}$$
or the daily returns under continuous compounding (log-returns)
(16.1)
$$ r_t = \log (s_t ) - \log (s_{t - 1} ).$$
These quantities are close to each other if the ratio
s
t
/
s
t
−1
is close to 1. We will focus on the latter concept. Log-returns are also called geometric returns in the financial literature.