Experiments in Technical Analysis
- Thread starter karthikmarar
- Start date
Hello friends,
The thread has now entered a new and exciting phase. The points CV has brought out are very important. This has forced me to think again about the questions I was asking myself since beginning. When I started learning about TA about two years back I had two basic questions which are unanswered even today:
1. Is price a random variable?
2. If it is not then is it a dependent variable?
If the price is a random variable then it should follow the gaussian distribution. In that case we can apply the various statistical parameters like mean, standard deviation etc. to a small sample of data and draw conclusions about the whole data set. The sample values also should be selected randomly. This means that sample data should be such that each value in the data set has equal chance of getting included. What actually we are doing is selecting a portion of the data where the values are not randomly included. The sample is a continuous series of values. Therefore the sample set is not made of randomly selected values. Hence the conclusions drawn do not reflect the properties of the whole data set.
In TA we also talk of linear regression, coefficient of variation, regression coefficient etc. This means we are treating the prices as dependent variable and not a random value. If price is dependent variable then on what does it depend. In other words what is the independent variable. In price charts we plot the price on Y-axis which by convention is dependent variable and the X-axis is time. Does it mean price depends on time? But it is not. Time axis is just a convenience to plot the prices. So, price is independent variable. Then why do we try to fit a regression line to independent variable? Why do we plot it on Y-axis?
I do not have answers. I am not sure whether price is dependent variable or independent variable. Unless this is clear there is no meaning in fitting some lines, indicators etc.
What we are supposed to do is fit some relation/equation to the data to explain its behavior. But what we are actually doing is trying to fit the data to a particular relation/equation. We fit a small set of data points to whatever we want and try to interpret the results as the properties of the whole data set. The results of TA on a small portion of data would apply to only that set but not the whole data.
There are many more questions. But let us answer the basic question. What type of variable is price.
More later.
Regards
-Anant
The thread has now entered a new and exciting phase. The points CV has brought out are very important. This has forced me to think again about the questions I was asking myself since beginning. When I started learning about TA about two years back I had two basic questions which are unanswered even today:
1. Is price a random variable?
2. If it is not then is it a dependent variable?
If the price is a random variable then it should follow the gaussian distribution. In that case we can apply the various statistical parameters like mean, standard deviation etc. to a small sample of data and draw conclusions about the whole data set. The sample values also should be selected randomly. This means that sample data should be such that each value in the data set has equal chance of getting included. What actually we are doing is selecting a portion of the data where the values are not randomly included. The sample is a continuous series of values. Therefore the sample set is not made of randomly selected values. Hence the conclusions drawn do not reflect the properties of the whole data set.
In TA we also talk of linear regression, coefficient of variation, regression coefficient etc. This means we are treating the prices as dependent variable and not a random value. If price is dependent variable then on what does it depend. In other words what is the independent variable. In price charts we plot the price on Y-axis which by convention is dependent variable and the X-axis is time. Does it mean price depends on time? But it is not. Time axis is just a convenience to plot the prices. So, price is independent variable. Then why do we try to fit a regression line to independent variable? Why do we plot it on Y-axis?
I do not have answers. I am not sure whether price is dependent variable or independent variable. Unless this is clear there is no meaning in fitting some lines, indicators etc.
What we are supposed to do is fit some relation/equation to the data to explain its behavior. But what we are actually doing is trying to fit the data to a particular relation/equation. We fit a small set of data points to whatever we want and try to interpret the results as the properties of the whole data set. The results of TA on a small portion of data would apply to only that set but not the whole data.
There are many more questions. But let us answer the basic question. What type of variable is price.
More later.
Regards
-Anant
Dear Friends
I think Winston has a moot point.
As I had pointed out before that most indicators are built on the assumption that the prices have gaussian distribution. Ananth has also brought out this fact in his post.
(What I admire about ananth is his clarity of thought and expression. He has a great why of explaining complex things in a simpler way.. His posts make a great reading)
Ok, the question here is does approximation work? Assuming the prices to have a gaussian distribution is an approximation.. Is this approximation good enough for trading?
We can also approximate the prices to a gaussian distribution by applying Fisher transform? Will these Fisher transformed Indicators perform much better than the conventional Indicators which assume the prices to be gaussian distributed?
Many questionsgood for a lot of discussions
I am enclosing two charts here. One chart shows a fisher-transformed signal of a 10-day median price. Also shown in the chart is the conventional MACD.
Another chart shows a conventional stochastic D signal with a fisher transformed stochastic D.
I will leave it to you to draw the conclusions
Regards
Karthik
I think Winston has a moot point.
As I had pointed out before that most indicators are built on the assumption that the prices have gaussian distribution. Ananth has also brought out this fact in his post.
(What I admire about ananth is his clarity of thought and expression. He has a great why of explaining complex things in a simpler way.. His posts make a great reading)
Ok, the question here is does approximation work? Assuming the prices to have a gaussian distribution is an approximation.. Is this approximation good enough for trading?
We can also approximate the prices to a gaussian distribution by applying Fisher transform? Will these Fisher transformed Indicators perform much better than the conventional Indicators which assume the prices to be gaussian distributed?
Many questionsgood for a lot of discussions
I am enclosing two charts here. One chart shows a fisher-transformed signal of a 10-day median price. Also shown in the chart is the conventional MACD.
Another chart shows a conventional stochastic D signal with a fisher transformed stochastic D.
I will leave it to you to draw the conclusions
Regards
Karthik
Last edited:
Thanks Karthik, for the charts.
Just one clarification. Is the IFT for the Stoch or RSI? You have mentioned Stoch but the label on the graph shows RSI.
Assuming they are both for the Stoch %D, i see a definite advantage in gaging the turning points. (Less ambiguity)
And why have you excluded %K?
Regards,
Kalyan.
Just one clarification. Is the IFT for the Stoch or RSI? You have mentioned Stoch but the label on the graph shows RSI.
Assuming they are both for the Stoch %D, i see a definite advantage in gaging the turning points. (Less ambiguity)
And why have you excluded %K?
Regards,
Kalyan.
U
Hi,
Revolutionary thinker Mr Naseem Taleib has HIT us like Mail Train & all our beliefs
are under serious introspection.
1st CV's post := Is Data Sationary ?
My understanding till now YES it is Stationary in Broader Relativity.{Proved by my
analogy of "Photo Finish" in Horse Racing}
Next Are we Overemphasizing RANDOMNESS ?
The out come of my Trade may be predominantly "LUCKY STREAK" ,YES it may be so or
it IS so.This belief will make me SKEPTICAL & relentlessly drive me towards garnering
the 'O D D S' in favour of the Trade. More Money Mgmt(Position Size etc) ,more Risk Mgmt.
(% Risk model,Optimal "F" etc etc ) OK so far so good.
Now acceptance & acknowlegment of this Randomness is 100 % OK ,which means the
Chance of tommorrow's close > open is Random or a little extension today's Close
being Highest or Lowest in coming 10 days is Random,absolutely OK till now.
But the event which has happened ,that is today's close after 3.31pm is a CERTAINITY.
yesterday's Close is also a certainity.Plz accept & acknowlege this.The TIME in
"Y" axis of a chart is not ,can not be ever ,now or never in FUTURE WILL EVER BE
R A N D O M.
We know if now is 10.52 am(before posting this) than at the time of posting this
it NEVER EVER will have a Time stamp < 10.52.
ONLY THE RIGHT SIDE OF THE CHART'S "X" AXIS CAN BE R A N D O M. I repeat only
the extreme Right side.
The eliptical path Earth traverses around Sun is FINITE ,measurable but it can
BOOM & disintregate is possible ,like the Black Swan.That possibility that i may
die just now is there but the moment i lived from 10.53 to now 11.04 is Certain.
Acknowlegment of Draw Down / Loss is TRUE event,it is not FALSE that I was Lucky
or Unlucky only in all my trades in last 280 days for 9 yrs.( Basically unlucky
is certainity in my case)
Now coming to data ,sample data (whether true representative of whole).
We may have to take recourse of
" The Axiomatic Theory of Probability " In simple words a Theory to MEASURE :=
SS:= Sample Space ;{Means Set of all possible/concievable outcomes }
Sigma:= Sigma Field; { Means set of all combination outcomes }
PF := Probability Function { Means Any damn set function ,whose domain/ boundary is SS}
SS * Sigma * PF
Here we also have few FIXED Mathematical RULE as following;
PF[SS]=1;
if "A" is an event in Sigma then,
PF [A] >= 0
I am seriously considering this presently,only to tackle future uncertanities.All my TA tools
till date is absolutely OK,to guide me in taking positions.
By the by the mathameticks in constructing a "Linear Regression Line " is itself a satistical
tool to predict future values from past datas & all statical tools are 100% applicable on
past data ,simply because it is representing a "Certain event".
Very interesting excersise going on & good to find All members i Respect in this forum has
participated ,waiting for all your guidance.
Asish
Revolutionary thinker Mr Naseem Taleib has HIT us like Mail Train & all our beliefs
are under serious introspection.
1st CV's post := Is Data Sationary ?
My understanding till now YES it is Stationary in Broader Relativity.{Proved by my
analogy of "Photo Finish" in Horse Racing}
Next Are we Overemphasizing RANDOMNESS ?
The out come of my Trade may be predominantly "LUCKY STREAK" ,YES it may be so or
it IS so.This belief will make me SKEPTICAL & relentlessly drive me towards garnering
the 'O D D S' in favour of the Trade. More Money Mgmt(Position Size etc) ,more Risk Mgmt.
(% Risk model,Optimal "F" etc etc ) OK so far so good.
Now acceptance & acknowlegment of this Randomness is 100 % OK ,which means the
Chance of tommorrow's close > open is Random or a little extension today's Close
being Highest or Lowest in coming 10 days is Random,absolutely OK till now.
But the event which has happened ,that is today's close after 3.31pm is a CERTAINITY.
yesterday's Close is also a certainity.Plz accept & acknowlege this.The TIME in
"Y" axis of a chart is not ,can not be ever ,now or never in FUTURE WILL EVER BE
R A N D O M.
We know if now is 10.52 am(before posting this) than at the time of posting this
it NEVER EVER will have a Time stamp < 10.52.
ONLY THE RIGHT SIDE OF THE CHART'S "X" AXIS CAN BE R A N D O M. I repeat only
the extreme Right side.
The eliptical path Earth traverses around Sun is FINITE ,measurable but it can
BOOM & disintregate is possible ,like the Black Swan.That possibility that i may
die just now is there but the moment i lived from 10.53 to now 11.04 is Certain.
Acknowlegment of Draw Down / Loss is TRUE event,it is not FALSE that I was Lucky
or Unlucky only in all my trades in last 280 days for 9 yrs.( Basically unlucky
is certainity in my case)
Now coming to data ,sample data (whether true representative of whole).
We may have to take recourse of
" The Axiomatic Theory of Probability " In simple words a Theory to MEASURE :=
SS:= Sample Space ;{Means Set of all possible/concievable outcomes }
Sigma:= Sigma Field; { Means set of all combination outcomes }
PF := Probability Function { Means Any damn set function ,whose domain/ boundary is SS}
SS * Sigma * PF
Here we also have few FIXED Mathematical RULE as following;
PF[SS]=1;
if "A" is an event in Sigma then,
PF [A] >= 0
I am seriously considering this presently,only to tackle future uncertanities.All my TA tools
till date is absolutely OK,to guide me in taking positions.
By the by the mathameticks in constructing a "Linear Regression Line " is itself a satistical
tool to predict future values from past datas & all statical tools are 100% applicable on
past data ,simply because it is representing a "Certain event".
Very interesting excersise going on & good to find All members i Respect in this forum has
participated ,waiting for all your guidance.
Asish
Last edited by a moderator:
Hi Winston,
Yes, it does not matter what is the means with which you achieve the end. "End justifies the Means". Here I quote an example of one of my friends. He does not do any TA for trading. He just observes the price for a few days. If it is going up buys the stock. When it starts going down or after a certain amount of gain he sells. If he finds a second stock rising faster, he simply sells the first one and buys the second. He almost always wins. ('almost' because there are a few occasions where the trades go into loss but he quickly gets out). You may call this MM. But it is not based firmly on MM rules. His entry-exit are not based on any set principles. When he 'feels' that the time is right for entry or exit he just does it. It is a just a thumb rule he uses. So his technique is simpler than the simple ones we are searching. But if we base our 'simple system' on some rules then we get better results, even better than the 'simpler' system. We are trying to find such a system based on some simple rules. Unfortunately, in searching for simple rules and systems we are complicating the things. This happens because we try to force the data to 'FIT OUR RULES' instead of finding the rules which fit or explain the data. There are many other issues I want to discuss. I would do it one by one. Till then let us think about making the simple simpler.
regards
-Anant
| Thread starter | Similar threads | Forum | Replies | Date |
|---|---|---|---|---|
|
My experiments with MFs | Mutual Funds Discussion Forum | 93 | |
| R | Experiments with Market Profile | Advanced Trading Strategies | 53 | |
| G | Trading logs/experiments | Commodities | 8 | |
|
My Experiments with Charts | Members Discussion Forums | 1 | |
|
Experiments with OBV | Advanced Trading Strategies | 199 |