http://www.google.com/url?sa=t&rct=j&q= ... FK-H4wDear all, in the above articale I found a sentence:The Day of the Week Effect in Stock Index FuturesA great deal of evidence shows that returns on stocks differ depending on the day of the week. In particular, Friday returns are generally high. It is true ? Any one has such experience ?

That stopped being true in 2000, which tells you how old that document is: approximately 12 years.

Yes, exactly. I have been looking for a good board question to illustrate the new built-in FinancialData in Mathematica.This is a good one. Some code that sorts returns by day of the week:Results: decade of the '90's:-------------------------------------------------------WeekdayStats["SP500",{1990,1,1},{1999,12,31}]Monday: mean(%) = 0.118567 std dev = 0.971239Tuesday: mean(%) = 0.0624191 std dev = 0.913289Wednesday: mean(%) = 0.0877446 std dev = 0.759541Thursday: mean(%) = -0.0294375 std dev = 0.896667Friday: mean(%) = 0.061481 std dev = 0.886581ndays=2527 daycounts={482,518,516,508,503}Overall mean=0.0596475 overall mean check=0.0596475Results: turn of the century to date:--------------------------------------------------------------WeekdayStats["SP500",{2000,1,1},{2012,8,30}]Monday: mean(%) = -0.00623899 std dev = 1.50773Tuesday: mean(%) = 0.052273 std dev = 1.41775Wednesday: mean(%) = -0.00468118 std dev = 1.32218Thursday: mean(%) = 0.043123 std dev = 1.36286Friday: mean(%) = -0.0461352 std dev = 1.18871ndays=3186 daycounts={597,653,655,643,638}Overall mean=0.00804684 overall mean check=0.00804684

why it been stopped in 2000 ?any explanation ?QuoteOriginally posted by: acastaldoThat stopped being true in 2000, which tells you how old that document is: approximately 12 years.

There are lots of papers on this sort of thing, so if googling turns up a convincing, country-by-country story, please let us know. BTW, running my code by various decades:

Here you go (Scale: 1 means: std dev of daily returns = 1%) ...

Yeah, same thought here re Black Monday.The 2000's are back to the 60's pattern for vols, except twice as big!

Well, I haven't plotted the 1930's!

to what extent has expiry of options/futures (witching-day) influence on stocks?could there be kindda saisonality of friday session volatility?

I think the last vol. chart I posted shows it correctly: Fridays (in the US) are relatively quiet.Probably trumping any putative increased vol. due to options expiration is the lesser amt of corp news: see Table 1 in https://aeaweb.org/assa/2005/0107_0800_0903.pdf

Quiet fridays are observed in all sorts of data. I've seen it in electricity prices (cheaper on friday than any other weekday) and also if you plot visitors to websites, friday is lower than every other weekday.Interestingly I found the "friday afternoon effect" in electricity prices to be more pronounced in the UK than in France. So it's us Brits that slack off early, so much for stereotypes!