Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypotheses

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

That's a a theory - so is buy low sell high. Wahoo for profitable theories

But how goes the application? Made your millions yet?

Not yet, but would have made 10% on MTS this week though.

MTS is not of the quality I like - probably about half as good as WOW on some measure. But WOW is not yet at a bargain level I'm happy with at $27 last week - though at that price it is very reasonable.

Sometime luck just don't go your way for the price drop lower, but are you going to tell me I'll average losses over my investing career if I approach it as a business following Graham's advise like this?

I know I won't know everything, and luck might not be on my side with businesses I could come to know... but it's no rocket science and no master of the universe wisdom required.

 

[Value Collector]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

I’m not sure how Buffett or most of F/A in general fits into an evidence based thread. Assuming we are looking for evidence to a scientific standard.

Certainly Buffett & Co and there are long term successful T/A exponents as well provide enough evidence to nullify the efficient market hypothesis. But there is no evidence I have ever seen of what does work every time.

Most of the papers approach things from the perspective of showing the lowest deciles beat the highest deciles or such & such approach beats buy& hold – none of it is really aimed at testing hypotheses by looking for nullifying evidence. If you approached it this way every concept I know of would be nullified because none of it is underpinned by an ironclad law.

What the academic literature shows is “generalities” of things that tend to work on a probability basis. Some papers go to the level of confidence levels to try and ensure the observed generality is not a random occurrence but even a 95% confidence that an observation is not random is far different from collecting evidence to nullify a hypothesis.

The better generalities have appeared again & again over many papers, many markets and many timeframes, but how stable they will be into the future as people try to harvest them will be the big question. My suspicion is only the hardest (least cost effective or psychologically difficult) to harvest will survive.

Deciphering quantitative evidence in F/A is harder than T/A because you have the language of accounting defining a lot of the terms whereas price is pretty straight forward. So even if you get a confidence level that a F/A generality exists you have to be mindful of the underlying definition of the variable.

Here is a good summary of some generalities that have been persistent. (But none of it is sufficiently evidence based in my opinion – so not sure it fits this thread).

http://www.tweedy.com/resources/library_docs/papers/WhatHasWorkedFundOct14Web.pdf

My main interest around the concept of evidence based is how people cope once they see holes in the beliefs that used to fortify their involvement in the market. Do they look.

I guess it depends on what you are looking for to test

As I said, if you are looking to test some formula or ratio, I think you are missing the point.

But I think being a good investor is akin to being a good lawyer. can we scientifically prove some lawyers are better than others, or that some strategies employed by laywers are better than others, probably.

Does it mean it's easy to replicate the performance, probably not, does it mean that with the correct study to develop a knowledge base, combined with certain strategies for picking clients and using certain strategies to approach cases that you can become a good lawyer, I think you can.

Picking any one aspect of a good lawyer will not make you great, same with being an investor, it takes a lot of knowledge, as well as having practicle strategies.

Trying to find evidence to prove whether settleing out of court beats going to trail, or whether tax law beats criminal law etc seems pointless to me. As I said earlier, I think success in f/a comes from deep understanding of business and investment principles that can't be judged or employed in isolation.

 

[howardbandy]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Greetings --

Commenting on this paragraph --

As to coping with true, pervasive, uncertainty from a research perspective, you really can't. No margin for error is large enough to allow for it unless you know the bounds within which it is uncertain. Nothing can be proved conclusively or not if the idea under investigation is dominated by true uncertainty. Sure, you can get observational outcomes and some of these may produce stuff which meets some stats tests and have '*** (Significant at P = 0.01)' next to them. However, in a fully uncertain situation, you can't put too much weight on these outcomes. The more correct thing to say is "don't really know what this observation means" to any observation drawn from a fully uncertain situation. That would make for seriously boring copy...or otherwise be an excellent argument for indexing, in some ways.

---------

Evidence-based (read Bayesian) techniques provide measurable confidence given several criteria:

There are well defined rules for identifying the patterns that precede profitable trades.
Those rules are tuned using data mining techniques over in-sample data.
There are many examples of similar patterns in out-of-sample data.
The period of time spanned by the in-sample plus out-of-sample period provides a stationary distribution of patterns and trades.
The trades signaled in the out-of-sample period are profitable.

Read about it in "Quantitative Technical Analysis."

On the other hand, as several posters have pointed out, too much of what we hear as being evidence-based is seriously flawed. It suffers from too few examples, in-sample only analysis, selection bias, confusing a bull market with brains, etc.

In order to pass rigorous testing, there must be many confirming examples detected without bias in strictly out-of-sample data.

Buffett, etal, have superb results, but they are not evidence-based. No fundamentally-based techniques can be. Out-of-sample tests are not practical -- there are too few examples. The problems with data granularity, delay between achieving a result and posting the result, bias introduced by the reporting agency, etc, cannot be overcome.

Belief, yes. Confidence, no.

Best regards,
Howard

 

[tech/a]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

That's a a theory - so is buy low sell high. Wahoo for profitable theories

But how goes the application? Made your millions yet?

Exactly

These are but two of 100s

It appears that people want to believe these theories and even defend them
Rather than investigate their veracity.

 

[wayneL]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Pick a company with a business you could understand.

Read its reports and account.

Read into its industry and competitors.

See if the company is going to go broke. See how it has been doing. See what are its assets and liabilities. See how its returns has been.

Estimate its position in relation to the industry. Have an idea of how its future would work out - will it still survive, will it go broke...

Then estimate its approximate value.

Buy below those estimates.

---


Not easy. Not effortless. Not always possible to find business you know and like and sell at a good price.

But not exactly Rocket Science either.

You think that's all there is to Buffets success?

 

[tech/a]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

You think that's all there is to Buffets success?

1 Buffett

Possibly 100s of Thousands of followers of the Buffett Principal.

Where are all the NEW Buffetts?

 

[satanoperca]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

1 Buffett

Possibly 100s of Thousands of followers of the Buffett Principal.

Where are all the NEW Buffetts?

Staying below the radar.

I always see successful people in two boats :
1. They want everyone to know their success and tell the world
2. They prefer to remain quiet and get on with business.

I am sure there are 100's of successful traders and investors to varying degrees, out there getting on with business.

 

[tech/a]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Staying below the radar.

I always see successful people in two boats :
1. They want everyone to know their success and tell the world
2. They prefer to remain quiet and get on with business.

I am sure there are 100's of successful traders and investors to varying degrees, out there getting on with business.

I'm sure there are
But New Buffets would be conspicuous particularly any number of them.

It appears Buffet principals are championed by budding Buffets rather than
New Buffets. Personally I think it's a tremendously logical principal.
Unfortunately logic regularly under performs expectation.

 

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

You think that's all there is to Buffets success?

It's not Buffett's. It's Graham's.

That was just one chart to show a straightforward application of Graham's formula - to put performance and estimates in perspective. So that's not all there is to it, but it work wonders for me.

----

Investing success is not a straight forward if this then that. It's a holistic understanding of the business and its environment - something that will take time to develop, and take a lot of hardwork to get to.

If you ask me, the "secret" to investing success has been out of the bag for at least 70 years. An investor's focus shouldn't be on what's the trade secret but on simply studying businesses and that's it. Everything else is just a bunch of highly placed people who doesn't know what they're doing, and geniuses who's paid to find new innovation and "scientific" evidence and make life easier and risk-free for established institutions to make money off of clients for no real work.

 

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

I'm sure there are
But New Buffets would be conspicuous particularly any number of them.

It appears Buffet principals are championed by budding Buffets rather than
New Buffets. Personally I think it's a tremendously logical principal.
Unfortunately logic regularly under performs expectation.

Mate, aren't you the one who ask for evidence if FA or TA works?

When it's shown, you then say people are showing off?

Have I say how much money I have made or how much I got at the bank?
When asked how's the application of this works for me, didn't I just show it have and would work pretty well. That's not another piece of evidence?


Proof is quite simple. Why not just pick any 8 or 9 Technical Analysis investor or fund manager with the same kind of performance records as the 9 Buffett show and that's it.

 

[sinner]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Maybe I read into what people are saying. That I know what they're implying.

I guess that is the problem here, we have all been respectful enough to listen and take on your comments as would be appropriate when holding discussion with other adults, while you have an argument with yourself about the things you think others are implying.

I guess it's over for me once the thread devolves from luutzu arguing with successful investors about why they can't estimate the value of a firm, into luutzu explaining to wayneL how easy it is to invest by estimating the value of a firm..sorry tech. Another thread bites the dust!

Then estimate its approximate value.

 

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

I guess that is the problem here, we have all been respectful enough to listen and take on your comments as would be appropriate when holding discussion with other adults, while you have an argument with yourself about the things you think others are implying.

I guess it's over for me once the thread devolves from luutzu arguing with successful investors about why they can't estimate the value of a firm, into luutzu explaining to wayneL how easy it is to invest by estimating the value of a firm..sorry tech. Another thread bites the dust!

When did I ever say it's easy?

I probably have said it's simple, but simple does not mean simplistic or easy.

How in the world do you think it's easy to understand a multi-disciplined, multi-million, billion dollar national and international corporation?

How could I anyone imply it's easy to be so certain that the entire market is wrong and I am right?

---
With regard to the application of Graham's formula:

Craft was being smug and ask how well have I apply that simplistic formula - and I showed him that simple idea in action. It does look like it work pretty well if you can read it. And that's just a straight forward, mechanical application - no adjustment, no analysis or thinking involved in that chart.

Did I say that is all, that's all you need to do? Read my reply to Wayne again.

But it does put all the market and the investor's thinking in perspective, doesn't it?

----

Let's take a look at DCF and see if it's designed to create jobs for academics and consultants and other prophets or design to be useful to otherwise intelligent adults not trained in fancy maths.




To the definitions:
Definitions of Terms


V0= Value of Equity (if cash flows to equity are discounted) or Firm (if cash flows to firm are discounted)

CFt = Cash Flow in period t; Dividends or FCFE if valuing equity or FCFF if valuing firm.

r = Cost of Equity (if discounting Dividends or FCFE) or Cost of Capital (if discounting FCFF)

g = Expected growth rate in Cash Flow being discounted

ga= Expected growth in Cash Flow being discounted in first stage of three stage growth model

gn= Expected growth in Cash Flow being discounted in stable period

n = Length of the high growth period in two-stage model

n1 = Length of the first high growth period in three-stage model

n2 - n1 = Transition period in three-stage model
WHICH MODEL SHOULD I USE?

Use the growth model only if cash flows are positive
Use the stable growth model, if
the firm is growing at a rate which is below or close (within 1-2% ) to the growth rate of the economy
Use the two-stage growth model if
the firm is growing at a moderate rate (... within 8% of the stable growth rate)
Use the three-stage growth model if
the firm is growing at a high rate (... more than 8% higher than the stable growth rate)
SUMMARIZING THE MODEL CHOICES...

more here: http://pages.stern.nyu.edu/~adamodar/New_Home_Page/lectures/basics.html

----

Sure looks like a lot of work.
Let's bring a few of them in and advise us of changes, all of the time.

 

[tech/a]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Sinner

Luutzu
Demonstrates brilliantly the lack of ability to understand what is needed to
Determine if your method that you adopt to trade can be profitable----when you trade it.

Roger Federa wins tennis tournaments
So do Andy Murray

And Rafael Nadal
---- so then can I ---- what more proof do you/I need!

Again I'm not looking for proof I'm looking for method used to demonstrate an evidence based result.

The exact opposite to that being offered up here.
It's this sort of logic that Joe Public Gobbles up and why 90 % fail.

 

[History Repeats]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

There's a free summary of this book available (180pages)

http://www.cfapubs.org/doi/pdf/10.2470/rf.v2012.n1.1

You can get it online but i think worth the money to get the book.

 

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Sinner

Luutzu
Demonstrates brilliantly the lack of ability to understand what is needed to
Determine if your method that you adopt to trade can be profitable----when you trade it.

Roger Federa wins tennis tournaments
So do Andy Murray

And Rafael Nadal
---- so then can I ---- what more proof do you/I need!

Again I'm not looking for proof I'm looking for method used to demonstrate an evidence based result.

The exact opposite to that being offered up here.
It's this sort of logic that Joe Public Gobbles up and why 90 % fail.

So why do you do your work the way it's done Tech? Did you learn it from somebody or it's all your own discoveries? How did you first make heads or tails of the charts?

Why do people, in general, go to school and university and just generally read and study? Just because someone else have done it, have discovered it, and now wrote it and it makes sense and it's what you want to do and pursue...why bother right? Just do what you were born to do, follow your endowment.

Come on man, you're much smarter than that. Trying to talk like that just to laugh at me ain't going to help your case.

---

Anyway, you are after a system right? A magic formula? One that you can plug numbers in or read the direction and reach El Dorado yea?

Get real man.

Think about it. Could there really be such a map, such formula where you plug in a few numbers neatly prepared for you, then sit back and watch it rain gold.

Lest I get accused of putting words in your mouth - saying "looking for papers on evidence based results..." - is looking for a proven system that works right?

And again, just in case I get accused of throwing up Graham's one shorthand approximation formula - note the word "shorthand", note the word "approximation" - that I am saying there is a magic formula and that's all there is to it... In case I am accuse of saying that, I do not.

anyway, let's do this again next year. It's going to be an annual thing.

 

[cynic]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

...Lest I get accused of putting words in your mouth - saying "looking for papers on evidence based results..." - is looking for a proven system that works right?
...

Not necessarily.

The motivation for asking could be to demonstrate to others that there is a distinct lack of evidentiary support for deeply entrenched beliefs.

 

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Not necessarily.

The motivation for asking could be to demonstrate to others that there is a distinct lack of evidentiary support for deeply entrenched beliefs.

Maybe. Just I doubt that's the case here.

I mean, the world's most successful investor have all along said this book, this approach, provide me with the principles and foundation and completely changed my life and my investing... and it also made great successes out of all the investors that I know and worked with... and we just listen and shrugged it off as them being real geniuses and only suckers would believe they too could learn the "secret".

What's the secret? Treat stock as ownership in an entire business man; Study the business man; Invest in what you know man; Work really hard and be really careful in case you're wrong man.

Seriously, when's the last time any one got rich by working hard to know what they're doing, and only does it if it is safe and won't kill them if it fail.



When you see and hear that and you're not satisfy with it, you're not looking for reason and understanding, you're looking for a system.

 

[cynic]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

Maybe. Just I doubt that's the case here.
...

It's interesting that you say that.

I actually thought that my alternative was likely to be the case here, however, knowing that there certainly are other possibilities, I'd prefer not to make the error of automatically presuming the correctness of my opinions on the thoughts and/or motivations of others.

...
When you see and hear that and you're not satisfy with it, you're not looking for reason and understanding, you're looking for a system.

Are systems and reason/understanding mutually exclusive?

If not, how could one arrive at such a conclusion?

 

[luutzu]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

It's interesting that you say that.

I actually thought that my alternative was likely to be the case here, however, knowing that there certainly are other possibilities, I'd prefer not to make the error of automatically presuming the correctness of my opinions on the thoughts and/or motivations of others.


Are systems and reason/understanding mutually exclusive?

If not, how could one arrive at such a conclusion?

If system is defined as a set of principles, as an approach, then it's not mutually exclusive.

But 'system' is not reason/understanding if it's simply a formula with variables to plug into.

Example. Say we turn on Google GPS maps to go somewhere. if we simply follow the direction as directed no matter what - then that's just a mechanical system with formula to follow - this case being that if they say left we turn left; if right turn right; if go straight we go straight even if there are no signs and road blocks warning of danger.

But if we follow a general principle approach, we would adapt, would input our own knowledge of main roads and short cuts to get to our destination.


---
I guess people just either take to it or they don't.

I think the problem with investing still being debated is because it's been transformed into some secondary and tertiary entity, and the focus is on understanding the new set of entities rather than the original form - yet studying the new form but thinking all form are the one and the same.

If you bring stocks down to its basic, its original form - that of a share in the business - it's then just a matter of studying the business and knowing how to read financial statements.

If stocks are seen as pieces of stocks sold on exchanges... then there's the share price movement, the market sentiment, volumes and trends to look into. Then if stocks are into an index, classified into groups based on market cap, industry and sector, into different markets etc... Then you start to have to look at alpha and beta, come up with precise measure of diversification and risk and return etc.

Pretty soon you focus on things of no real relation to the actual living and breathing business these instruments all ought to represent.


Like most investors, I have looked at Technical Analysis; I have been to university and formally study Applied Finance and took Master of Commerce (Fund Management)... So OK I drop out of the Master degree, but seriously, it's not like I just never look at these stuff and follow the first book some rich guy recommend.


Anyhoo... Unless a person's job depends on believing in something, they won't believe or open to ideas they do not already currently follow.

 

[cynic]

Re: Looking for papers on Evidence Based Results for T/A and F/A methods/ideas/hypoth

If system is defined as a set of principles, as an approach, then it's not mutually exclusive.

Whilst that's not quite how I would define a system, I am otherwise largely agreeable.

But 'system' is not reason/understanding if it's simply a formula with variables to plug into.

I'm not quite sure that I correctly understand the point you're trying to make here.

A formula/system/algorithm/model may lack the self awareness and capacity for independent reasoning, however, its creator and subscribers will have their reasons (irrespective of validity or lack thereof) for their decision to create/operate it.

...
But if we follow a general principle approach, we would adapt, would input our own knowledge of main roads and short cuts to get to our destination.

Couldn't this simply be seen as a rational enhancement of a valid system pursuant to an appreciation of that system's scope and intent?

---
I think the problem with investing still being debated is because it's been transformed into some secondary and tertiary entity, and the focus is on understanding the new set of entities rather than the original form - yet studying the new form but thinking all form are the one and the same.
...

I'd agree that sometimes when additional layers of complexity evolve, the inner workings can become more deeply obscured.

I'd also agree that many(but certainly not all) do operate with an (at best) limited understanding of those inner workings.

However, the failure of some, to appreciate those inner workings, needn't necessarily invalidate those additional layers.

...
Anyhoo... Unless a person's job depends on believing in something, they won't believe or open to ideas they do not already currently follow.

That may well be true of some people, but I sincerely doubt it could be true of all people.