This is what happens when science is used for PR purposes. The ME is full of holes.
--- dhamiltony2k5 <[EMAIL PROTECTED]> wrote: > Om, hey, New.Morning; do you ever interact with the > FF TM university > about > this? On their radio broadcasts they (Drs. Hagelin > and > Morris) and other PhD's are saying the ME is an > absolute scientific > certainty. A fact. Their method it seems is that if > they say this > enough > times and their ME studies get published in > newsprint and broadcast > enough times then > hence, > it might be true then. It is pretty dramatic the > way they say it. Of > course, it is being said to a packed jury. > > What do any of them say to you about your analysis > of their work > though? > That thing also that you mention about 'peer > review', which allows > for others to demonstrate a > repeatability and then they have 'substance'? Is > their public > relations certainty anywhere near the > point where they have substance? > > They seem pretty certain the way they present, and > it sounds really > neat and convincing the way they say it. > > -Doug in Iowa > > > Flaw in the ME studies: > > > http://groups.yahoo.com/group/FairfieldLife/message/124066 > > > > More at: > > http://2006-course-effects.blogspot.com/ > > > --- In [email protected], new.morning > <[EMAIL PROTECTED]> > wrote: > > > > I have corrected and updated some recent posts on > the flawed MUM > > analysis of the IA experiment. > > > > A 13% Gain over 17 weeks in NOT a Rare Event > > > > A recent IA experiment press release states the > "advanced > econometric > > models" show a 3/10,000 chance for normal > occurance of recent market > > increases since the start of IA. Thus the > so-called rarity of the > > event opens the door for claims of some special > new effect. > > > > Lets actually look at the data. > > > > The current IA experiment has run 17 full weeks, > and the S&P 500 has > > risen 12.9% in that period. Good show. > > > > But what is the naturally occurring frequency of a > 12.9% or better > > gain in any 17 weeks period. Going back to 1960, > it has occurred on > > average 4.98 times / year. That is, for any given > start week, there > is > > a about a 10% (4.98/52) chance, historically over > almost 50 years, > > that there will be a 12.9% or better gain in the > S&P500. > > > > And if you allow 20 weeks to realize the same > 12.9% gains, that is, > > same returns, albeit gained slightly more slowly, > it has occured on > > average 7.1 times per year. About a 15% > probability that any week > will > > be the start of a 12.9+ gain over the next 20 > weeks. > > > > And there is a 20% probability that you will get a > 10% or better > > return on the S&P 500 within 20 weeks. > > > > For the IA experiement claim the current rise in > the financial > markets > > since July 21, 2006, the start of the IA > experiment, is a very rare > > event, of the magnitude of 3/10,000 probability is > preposterous, and > > indicative of very naive or slanted research. > > > > 12 times there has been double or greater that > approximate 13% gain, > > that is greater or equal to 26% gain in 17 weeks > periods -- going > back > > to 1960. It has occurred on average once every > four years. > > > > So if the IA produced that rate of growth, they > might begin to be > able > > to claim something fairly unique is occuring. Or > best, if the S&P > 500 > > yielded a 35% gain in 17 weeks -- which has never > occurred in the > > period since 1960. > > > > ..... > > > > > > IA Analysis Goofs: Assuming Normality, or > Overspecification of the > Event? > > > > The enourmous goof, cited in the last post, by IA > researchers is > > astonishing. How could such mistakes occur -- in > the face of real > > data. (claiming a 3/10,000 chance for normal > occurance of recent > > market increases since the start of IA -- when > such an event -- a > 13% > > run-up in 17 weeks -- has occurred over 220 times > since 1960. > > > > One possibility for the goof is a well-known issue > that can be made > in > > studies of financial markets is to using analysis > and models that > > assume a normal distribution. Distributions of the > returns for most > > financial markets, certainly the S&P 500 -- the > proxy for all US > > markets -- has "fat tails" and a lower peak than a > normal > > distribution. More like the top half of a somewhat > flattened > circle -- > > aka an elipse, than the classic "bell" shape of a > normal (aka > > guassian) distribution. > > > > For some analysis, in the main body of the > distriubtion, the > > difference is not to substantial. However, when > analyzing the tails, > > the extreme events, the normal distribution > extremely underestimates > > the occurence of extreme gains or losses, that is > the top or bottom > 1% > > or more accutely, the top .1% of the distribution. > > > > ... > > > > A second possibility of where the IA analysis flaw > lies is > > overspecification of the event. For example, > instead of testing for > > 13% rises in the S&P 500 over 17 weeks, one could > have tested 13% > > rises in the S&P 500 over 17 weeks where there is > a pattern that > there > > are weekly declines in the 3rd, 5th and 7th weeks > of the series. > That > > is the pattern of the recent rise, but is > absolutely unimportant to > > the premise being tested: if the 13% rises in the > S&P 500 over 17 > > weeks is "rare" or if it naturally occurs > periodically. The > occurence > > of 13% rises in the S&P 500 over 17 weeks with > weekly declines in > the > > 3rd, 5th and 7th weeks of the series is indeed > much rarer than the > === message truncated === __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com
