Hocus Press Release 2.0

Can retiring early make you crazy? Get the latest news from the world of Hoco-mania. Surprising insights on arithmetic, imagined 'death threats', message board administration, and the merits of leaving a high-paying job only to pursue sub-minimum wage work in retirement to make ends meet. For more on Hocomania see Rob Bennett, author of Passion Saving.

Re: Hocus Press Release 2.0

Postby Schroeder » 07/06/06 at 18:16:07

**LINK**
45. The Kiyosaki Effect
mattwright| 07-06-06 | 04:17 PM
I will give Rob credit where it is do. He is apparently a very good salesman. Despite the complete lack of substance of anything he says, he has managed to get himself quoted in numerous publications as an "expert".

<snip>

And we know that hocus is paying $99 a month to get himself quoted.

http://www.s152957355.onlinehome.us/cgi ... 1151456871

tashina wrote:
- SGoon wrote:$99 a month. ? :-/



Two childen's tickets for one day at Disney World - $104 :cry:

Yet, hocus makes a joke of it . . .

47. Crosses to Carry
hocus| 07-06-06 | 04:21 PM
He is at this time a junior Kiyasaki

One big difference between Kiyosaki and me is that he has enough money to take his kids to DisneyWorld. I have told my boys that they need to settle for Sesame Place Water Park until daddy sells more books. Oh, the humanity! Oh, the horror!

Rob
Proud Member of the Financial Freedom Community!
User avatar
Schroeder
***** God Member
 
Posts: 3892
Joined: 10/11/05 at 19:53:13

Re: Hocus Press Release 2.0

Postby M._Kaleko » 07/06/06 at 18:52:17

47. Crosses to Carry
hocus| 07-06-06 | 04:21 PM
He is at this time a junior Kiyasaki

One big difference between Kiyosaki and me is that he has enough money to take his kids to DisneyWorld. I have told my boys that they need to settle for Sesame Place Water Park until daddy sells more books. Oh, the humanity! Oh, the horror!

Rob


He's already entered the phase where he pleads for lenience and pity, if not for him then at least his wife and poor kids. I've seen the exact same message before with minimal rearrangements in word choice.

Predictably, the next phase will bring out some valiant defenders of the poor guy. I know I feel a lot of compassion right now, and if I didn't know better, I'd jump in and help hocus to at least save face. :oops:

?
M._Kaleko
*** Full Member
 
Posts: 138
Joined: 04/09/06 at 17:19:34

Re: Hocus Press Release 2.0

Postby Schroeder » 07/06/06 at 19:43:50

In the July 6 blog, hocus talks about the comments made at Diehards. Here's an excerpt . . .

**LINK**
An odd note I hear in a number of comments on the calculator is a stress on the possible risk in taking the numbers generated by the calculator too seriously. There is such a risk, of course. But is it not more than a little curious that most of the posters who refer to the risk of taking what the historical data says too seriously rarely raise concerns about the risks that follow from not taking note at all of what the historical data says about how valuations affect long-term returns?

It's obvious that hocus misses the point people are making when they caution not to take the numbers generated by the hoco-calculator seriously.

As an example, the "Most Likely" 10-year real return for the S&P 500 according to the calculator is 1.31%. Why should the 10-year return on the S&P 500 be lower than the 10-year real return on TIPS (currently at 2.4%)? That makes no sense.

Schroeder
Proud Member of the Financial Freedom Community!
User avatar
Schroeder
***** God Member
 
Posts: 3892
Joined: 10/11/05 at 19:53:13

Re: Hocus Press Release 2.0

Postby syke-- » 07/06/06 at 20:27:41

orion wrote:
So JWR has produced something crude that produces some output that hasn't had to be reviewed or to jump any hurdles except for fitting the notions of a self-described "non-numbers" guy. ?Yep there's another fact for ya. ?:D


Excellent observation.  

JWR wrote:

A lot of academics are outstanding researchers. But they have to meet ridiculous hurdles. They can't get away with observing the obvious. They can't get away with a crude, Gaussian (bell curve, normal) approximation. They have to be wrong in exactly the precise, acceptable manner.

Written by a person predicting future stock market returns out to 0.1 percent.  

The thing that kills models is bad assumptions.  Let's start with his first one:  A Gaussian distribution is a crude approximation.  Obviously, that's not true.  Stock returns are clearly not distributed normally, they are much more variable (fat tails), and tend to trend upward (to the right of the graph).

If you look at a graph of stock returns, those observations are blindingly obvious.  So why assume they are normal when everyone with two eyes knows they aren't?  
User avatar
syke--
***** God Member
 
Posts: 610
Joined: 02/10/04 at 21:18:26
Location: Seattle, WA

Re: Hocus Press Release 2.0

Postby hocus » 07/07/06 at 05:26:05

You are a sick, sick man, hocus.

I acknowledge once breaking down and buying a Cat Stevens album.

"Wild World" is a good song, I don't care what anybody says.

I'm not so sure about "Peace Train" anymore.

Rob
Lying and sliming since May 12, 2002 --  Don't understand why intercst allows me to post here. Learn more about Rob Bennett, see link: http://retireearlyhomepage.com/bennett.html
User avatar
hocus
***** God Member
 
Posts: 5847
Joined: 02/11/04 at 12:31:16

Re: Hocus Press Release 2.0

Postby Schroeder » 07/07/06 at 10:24:46

Johnd "I'm outta Here" Craig has made a reappearance on that Diehards thread. Here, we see his infatuation with hocus burst through . . .

**LINK**
Post #55
<snip>

Rob's views of "valuations matter" are IMO no more radical than those of Bogle, Bernstein, Swedroe or Shiller as discussed at #29. All of them do "economic forecasting" in a manner similar to Rob's. I take it you're not suggesting that they also take their views elsewhere. So please do give us your substantive views rather than simply supplying fuel for the flamers.

John

To elevate hocus' "forecasting" on par with Bogle, Bernstein, Swedroe and Shiller is, well . . . Craigomania! :D

Schroeder
Proud Member of the Financial Freedom Community!
User avatar
Schroeder
***** God Member
 
Posts: 3892
Joined: 10/11/05 at 19:53:13

Re: Hocus Press Release 2.0

Postby M._Kaleko » 07/07/06 at 11:12:15

Behold, the hocus defender has arrived (fanfares etc.)!

And who could it be?
None other than Johnny d Craig, chewing on mild-mannered Michael LeBoeuf (a "Bogleheads Guide to Investing" co-author), for his allegedly "flaming" writing style.

Quite a comeback, after being eaten alive in the last round.

I'm popping a cork  [smiley=beer.gif]
?
M._Kaleko
*** Full Member
 
Posts: 138
Joined: 04/09/06 at 17:19:34

Re: Hocus Press Release 2.0

Postby gw » 07/07/06 at 11:39:38

There have been many people who have looked at John's work, including well-recognized experts like Scott Burns. Never have I heard a single criticism from any reasonably informed person.


Flat-out lie.  There have been many informed people who criticized JWR's work - you just re-write history.

I'm "reasonably informed" regarding statistics (although I claim no expertise in economics) and use statistics almost every day.  On the old NFB, I asked JWR some simple questions, such as...

1.  How did he justify deleting data from his analyses?  Competent, honest analysts always have objective criteria for deleting data and publically describe them.  That's one of the most fundamental ways to keep statistical analyses honest.

2.  Is it valid to "eyeball fit" confidence intervals?   Confidence intervals are well-defined statistical parameters that are calculated.  His guesses are, quite simply, meaningless.

3.  The r2 values of his correlations were so low (0.2 - 0.4) that I questioned the useful of predictions from his equations.

4.  When I calculated the r2 values, I got even lower values than he reported - even though I used the same data set that JWR used.  I asked  him about this.

JWR's response to this and other questions, of course, was to simply run away and refuse to respond.  

Now, hocus, tell us.  In this stock market predictor of yours, how have you and JWR validated the fundamental assumptions of linear regression that determine whether any of your predictions have value.

1.  Linearity of the relationship between dependent and independent variables.
2.  Normality of the distribution.
3.  Homoscedasticity of errors
4.  Absence of serial correlation.

After that, you could address details such as r2 values, "eyeball" estimates of correlation coefficients, etc.

Naw...never mind.   You're incapable of responding honestly even if you or JWR knew the answers.  
Bennett's May '02 post: "I am deeply sorry for falsely criticizing the study"
http://boards.fool.com/the-differences-between-how-dory36s-online-17225279.aspx
Read about Rob; google "Narcisstic Personality Disorder".
gw
***** God Member
 
Posts: 3071
Joined: 03/19/05 at 18:04:07

Re: Hocus Press Release 2.0

Postby hocus » 07/07/06 at 11:57:59

You have a long history as a ?Greaney defender, GW. A review of the Post Archives will confirm that for any community members who cares to check it out.

Rob
Lying and sliming since May 12, 2002 --  Don't understand why intercst allows me to post here. Learn more about Rob Bennett, see link: http://retireearlyhomepage.com/bennett.html
User avatar
hocus
***** God Member
 
Posts: 5847
Joined: 02/11/04 at 12:31:16

Re: Hocus Press Release 2.0

Postby sgeeeee » 07/07/06 at 12:00:20

hocus wrote:You have a long history as a ?Greaney defender, GW. A review of the Post Archives will confirm that for any community members who cares to check it out.

Rob

A review of the Post Archives (why is that capitalized?) will confirm that hocus is a green and purple tree frog for any commuity members who care to check it out.   :) :) :)
-sgeeeee
User avatar
sgeeeee
***** God Member
 
Posts: 719
Joined: 02/10/04 at 22:48:31
Location: Mesa, AZ

Re: Hocus Press Release 2.0

Postby syke-- » 07/07/06 at 12:09:22

hocus wrote:You have a long history as a ?Greaney defender, GW. A review of the Post Archives will confirm that for any community members who cares to check it out.

Rob


While they are busy doing that, why don't you explain the poor r-squared value?  
User avatar
syke--
***** God Member
 
Posts: 610
Joined: 02/10/04 at 21:18:26
Location: Seattle, WA

Re: Hocus Press Release 2.0

Postby gw » 07/07/06 at 12:31:39

You have a long history as a  Greaney defender, GW.


Irrelevant and a transparent dodge of simple questions...but we already knew you were incapable of answering them.
Bennett's May '02 post: "I am deeply sorry for falsely criticizing the study"
http://boards.fool.com/the-differences-between-how-dory36s-online-17225279.aspx
Read about Rob; google "Narcisstic Personality Disorder".
gw
***** God Member
 
Posts: 3071
Joined: 03/19/05 at 18:04:07

Re: Hocus Press Release 2.0

Postby tmeri » 07/07/06 at 13:16:37

gw wrote:
There have been many people who have looked at John's work, including well-recognized experts like Scott Burns. Never have I heard a single criticism from any reasonably informed person.


Flat-out lie. ?There have been many informed people who criticized JWR's work - you just re-write history.

I'm "reasonably informed" regarding statistics (although I claim no expertise in economics) and use statistics almost every day. ?On the old NFB, I asked JWR some simple questions, such as...

1. ?How did he justify deleting data from his analyses? ?Competent, honest analysts always have objective criteria for deleting data and publically describe them. ?That's one of the most fundamental ways to keep statistical analyses honest.

2. ?Is it valid to "eyeball fit" confidence intervals? ? Confidence intervals are well-defined statistical parameters that are calculated. ?His guesses are, quite simply, meaningless.

3. ?The r2 values of his correlations were so low (0.2 - 0.4) that I questioned the useful of predictions from his equations.

4. ?When I calculated the r2 values, I got even lower values than he reported - even though I used the same data set that JWR used. ?I asked ?him about this.


JWR's response to this and other questions, of course, was to simply run away and refuse to respond.



I think the issues of eyeballing the confidence interval and why his r2 values are higher than they ought to be have been answered, though perhaps the trolls don't remember how that was done. [link=http://gummy-stuff.org/JWR.htm]Gummy claims[/link] that a 90% confidence interval can be approximated by removing 10% of the values that lie farthest from the line fitted through the data. He does this by "eyeballing" the graph to pick out the 10% that are farthest away.

Unless I'm mistaken, if you remove the outliers, you are going to get a higher r2 value. It's one of those "mathematical cetainties" I think.

Corrections welcome. I'm too lazy any more to actually do arithmetic to verify my claims here.

I think the thing that keeps tripping me up is that a confidence interval says nothing about individual values but rather about the true mean of the entire population. It would seem that when you calculate a confidence interval for the mean, it isn't especially useful for predicting the certainty of the value of the next population element to be "drawn."

But if you think that a confidence interval has meaning, and you believe that the previous values of PE10 or whatever were randomly generated (heh), then why not just calculate the standard error of the sample and generate a real confidence interval? And why throw out some of the data? As n increase, the confidence interval grows smaller. I'm still struggling to understand the "logic" behind this mess, though there may be some. I know that most of you believe that Gummy has the right stuff. I'm too ignorant to judge, I suppose.
Claim to fame -- first ever to win hocus bingo.

Hocus does not have my permission to use my words or stories anywhere, ever.

We have MOVIES!  Financial Freedom Movies
User avatar
tmeri
***** God Member
 
Posts: 997
Joined: 02/11/04 at 17:51:03

Re: Hocus Press Release 2.0

Postby hocus » 07/07/06 at 13:51:09

"Morning is Broken" has a good melody. I don't believe he wrote that one, though. It was a hymm or something like that, wasn't it?

Rob
Lying and sliming since May 12, 2002 --  Don't understand why intercst allows me to post here. Learn more about Rob Bennett, see link: http://retireearlyhomepage.com/bennett.html
User avatar
hocus
***** God Member
 
Posts: 5847
Joined: 02/11/04 at 12:31:16

Re: Hocus Press Release 2.0

Postby Schroeder » 07/07/06 at 14:09:56

OK. This question is destined to have an honored place as one that hocus will not provide an honest and informed answer.

In post #69 in Diehards conversation 51714, hocus writes . . .

**LINK**
The most likely return for stocks over the next 10 years is 1.3 percent real. TIPS offer a higher real return.

And yesterday, I asked the following question . . .

Schroeder wrote:In the July 6 blog, hocus talks about the comments made at Diehards. Here's an excerpt . . .

**LINK**
An odd note I hear in a number of comments on the calculator is a stress on the possible risk in taking the numbers generated by the calculator too seriously. There is such a risk, of course. But is it not more than a little curious that most of the posters who refer to the risk of taking what the historical data says too seriously rarely raise concerns about the risks that follow from not taking note at all of what the historical data says about how valuations affect long-term returns?

It's obvious that hocus misses the point people are making when they caution not to take the numbers generated by the hoco-calculator seriously.

As an example, the "Most Likely" 10-year real return for the S&P 500 according to the calculator is 1.31%. [highlight]Why should the 10-year return on the S&P 500 be lower than the 10-year real return on TIPS (currently at 2.4%)?[/highlight] That makes no sense.

Schroeder

Do you have an answer hocus?

Schroeder
Proud Member of the Financial Freedom Community!
User avatar
Schroeder
***** God Member
 
Posts: 3892
Joined: 10/11/05 at 19:53:13

PreviousNext

Return to The Best of Hoco-mania

Who is online

Users browsing this forum: No registered users and 9 guests

cron