PeakTrader.com Forum Index PeakTrader.com
Economics, Portfolio Optimization, and Technical Analysis
 
 FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups   RegisterRegister 
 ProfileProfile   Log in to check your private messagesLog in to check your private messages   Log inLog in 
Log inFast Charts

Letter to the Editor-Follow Up

 
Post new topic   Reply to topic     PeakTrader.com Forum Index -> Portfolio Optimization
View previous topic :: View next topic  
Author Message
administrator
Site Admin


Joined: 28 Dec 2005
Posts: 11966

PostPosted: Mon Aug 20, 2007 1:45 am    Post subject: Letter to the Editor-Follow Up Reply with quote

Lou, in the short-run, the stock market (or stocks) is
a random walk, i.e. there's a equal chance it'll rise
or fall. In the long-run, the stock market is mean
reverting, i.e. you can bet the farm the stock market
will rise about 10% a year on average. To create a
sound general equilibrium model, you don't want serial
correlation, because you want each variable to
independently explain the stock market. Two big
problems in a short-run stock market model are omitted
variable bias and stochastics (i.e. a large error
term). There are variables in a "black box" (i.e.
unknown forces). Also, the variables and the weights
of those variables change over time. So, what explains
the stock market in one period may not explain it in
another. The stock market is less random and more mean
reverting in the intermediate-run than in the
short-run. One of my professors (a Ph.D from
UC-Berkeley in Macro 6000) described random walk as a
drunk person, i.e. the movements, or which way the
drunk will fall, are unpredictable. However, I
disagree with his definition, because there are
physical forces (that are predictable), rather than
only alcohol, that influence the drunk's movements.
Nonetheless, it's generally very difficult to predict
short-run movements in the stock market. However, some
are better at predicting the intermediate-run, while
the long-run is predictable. The links below show the
type of model you want to achieve. Art

http://en.wikipedia.org/wiki/Unit_root

http://en.wikipedia.org/wiki/Omitted-variable_bias

> Hi Art.
>
> Your comments below are interesting because they are
> simply ever investor's
> problem!
> Your a brilliant guy so don't get me wrong, but your
> not only consistent
> with most brilliant
> guys but consistent with most human beings.
>
> In my quest to be a better investor I've been
> reading up on behavioral
> fiance.
> The more you know, the more likely you are to
> overestimate your ability to
> predict the future.
> They have found that geniuses were usually wrong
> even when they were most
> confident.
> e.g. when 80% confident on an issue,. they were
> right 45% of time in
> studies.
>
> We make many cognitive errors.
> Many considerations like: myopic loss aversion,
> order prference, regret
> shunning, confirmation bias, hindsight bias,
> overconfidence etc.
>
> You have much more mastery of stats than me but
> isn't it true that stocks
> aren't
> serially correlated???????
> (e.g. odds are 50/50 it can continue to move in same
> direction etc.
>
> Many things to consider.
>
> I'm much happier and more successful now that I
> concentrate on intermediate
> trends
> in big indices and sectors vs. short-term trading.
>
> Don't be afraid of self-examination or your inferior
> autoworker friend will
> outperform
> you! lol (just kidding......hehehe)
>
> Have a good weekend.
> Thanks for your response.
>
> Lou
> p.s.
> Check out 20 ema on SPX on monthly chart.
> I'm watching that very closely.
Back to top
View user's profile Send private message
Display posts from previous:   
Post new topic   Reply to topic     PeakTrader.com Forum Index -> Portfolio Optimization All times are GMT - 8 Hours
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by PeakTrader 2.0.8 © 2001, 2002