This paper documents a new 'time-of-the-month' pattern in the daily returns
of the Standard & Poor's and the NASDAQ indices. Splitting a month into th
ree time segments, the results show that the returns are highest during the
'first third', experience a drop during the 'second third', and are lowest
, and in most cases negative, during the 'last third' of a month. This patt
ern remained remarkably consistent for the two indices examined. It also he
ld up well over business cycles and many different subperiods tested. Thus,
the results of this study provide convincing evidence of a new monthly ano
maly which displays a remarkable degree of robustness.