|
PureBytes Links
Trading Reference Links
|
Steve,
Since the TIMESERIES calc method of a moving average is the
moving average x the slope, give this a whirl:
T1:=Input("Time Periods",2,250,13);P1:=Input("Data: 1=C
2=Median 3=Typical 4=Wt.
Close",1,4,1);P2:=If(P1=1,C,If(P1=2,MP(),If(P1=3,Typ(),If(P1=4,WC(),C))));T2:=Input("Signal
Periods",1,200,3);V1:=Input("Threshold",0,10,3);A2:=((P2-Ref(Mov(P2,T1,TIMESERIES),-1))*100)/P2;A2;Mov(A2,T2,E);V1;-V1
Maybe yaa, maybe nah...
-Corey.
<BLOCKQUOTE dir=ltr
style="PADDING-RIGHT: 0px; PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #000000 2px solid; MARGIN-RIGHT: 0px">
----- Original Message -----
<DIV
style="BACKGROUND: #e4e4e4; FONT: 10pt arial; font-color: black">From:
Steve
Karnish
To: <A title=metastock@xxxxxxxxxxxxx
href="mailto:metastock@xxxxxxxxxxxxx";>metastock@xxxxxxxxxxxxx
Sent: Thursday, January 10, 2002 7:59
PM
Subject: Re: Forecast Oscillator
Sorry Nick,
I don't have an "expert". The picture can
be duplicated by selecting the Forecast Oscillator and setting it to 13
periods. The system tester is simply:
Enter long:
Cross(-3.4,ForecastOsc(CLOSE,13))
Enter
short: Cross(ForecastOsc(CLOSE,13),3.4)
I always trade the following day's opening (you
must set the tester to delay "1"...to represent entry on the "next" day.
Also, due to the nature of this oscillator, any testing/optimizing of trigger
levels must take in consideration that each issue can develop a range from 2
to about 15 percent. This makes optimizing levels for individual issues
a bit of a pain.
Take care,
Steve
<BLOCKQUOTE dir=ltr
style="PADDING-RIGHT: 0px; PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #000000 2px solid; MARGIN-RIGHT: 0px">
----- Original Message -----
<DIV
style="BACKGROUND: #e4e4e4; FONT: 10pt arial; font-color: black">From:
<A title=nick.channon@xxxxxxxxxxxxx
href="mailto:nick.channon@xxxxxxxxxxxxx";>Nick Channon
To: <A title=metastock@xxxxxxxxxxxxx
href="mailto:metastock@xxxxxxxxxxxxx";>metastock@xxxxxxxxxxxxx
Sent: Thursday, January 10, 2002 7:03
PM
Subject: Re: Forecast Oscillator
Steve, that looks very good. Could you kindly
save me time by posting the expert?
Many thanks,
Nick
<BLOCKQUOTE dir=ltr
style="PADDING-RIGHT: 0px; PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #000000 2px solid; MARGIN-RIGHT: 0px">
----- Original Message -----
<DIV
style="BACKGROUND: #e4e4e4; FONT: 10pt arial; font-color: black">From:
Steve
Karnish
To: <A title=metastock@xxxxxxxxxxxxx
href="mailto:metastock@xxxxxxxxxxxxx";>metastock@xxxxxxxxxxxxx
Sent: Friday, January 11, 2002 6:56
AM
Subject: Re: Forecast
Oscillator
Thanks Peter,
I use this formula much differently than
Chande suggests. I've had a lot of success with a 13 period
FO. I plot the formula and establish equidistant levels (from
zero) that trigger buy and sell signals. Simple, but
effective. This approach is graphically displayed in the
attachment. I like the FO because it can be somewhat "adaptive" (and
it can pull twenty bucks out of crude).
Thanks again, Equis doesn't "trust" us with
the formula. If you "click" on the little "arrow&?", on the
task bar, in MetaStock and drop it on the Forecast Oscillator you get the
following blurb:
"The oscillator is above zero when the
forecast price is greater than the actual price. Conversely, it's
less than zero if its below."
Of course, this is totally false (the
opposite is true). Which of edition of MetaStock do you believe
they might correct their mistake?
Take Care,
Steve
----- Original Message -----
<BLOCKQUOTE dir=ltr
style="PADDING-RIGHT: 0px; PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #000000 2px solid; MARGIN-RIGHT: 0px">
<DIV
style="BACKGROUND: #e4e4e4; FONT: 10pt arial; font-color: black">From:
<A title=investor@xxxxxxxxxxxxx
href="mailto:investor@xxxxxxxxxxxxx";>Peter Gialames
To: <A
title=metastock@xxxxxxxxxxxxx
href="mailto:metastock@xxxxxxxxxxxxx";>metastock@xxxxxxxxxxxxx
Cc: <A title=kernish@xxxxxxxxxxxx
href="mailto:kernish@xxxxxxxxxxxx";>kernish@xxxxxxxxxxxx
Sent: Thursday, January 10, 2002
9:45 AM
Subject: RE: Forecast
Oscillator
<FONT face=Arial color=#0000ff
size=2>Not sure if this is what you are looking for but
...
<FONT face=Arial color=#0000ff
size=2>
<FONT face=Arial color=#0000ff
size=2>Peter Gialames
<FONT face=Arial color=#0000ff
size=2>
Here is the text from
S&C V. 10:5 (220-224): Forecasting Tomorrow's Trading Day by Tushar
S. Chande, Ph.D.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Using linear regression as a crystal ball for forecasting the
market? After all, if you were to be able to
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>determine tomorrow's high, low and close for trend changes and
placement of stop points, it would
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>simplify your life immeasurably. Can it work? Tushar Chande
explains how it can be done.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Wouldn't you trade better It you could "see" the future? A simple
linear regression can provide an
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>objective forecast for the next day's high, low and close. These
ingredients are essential for a trading
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>game plan, which can help you trade more mechanically and less
emotionally. Best of all, a regression
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>forecast oscillator, %F, gives early warning of impending trend
changes. The linear regression method is
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>well known for finding a "best-fit" straight line for a given set
of data. The output of the regression are
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>the slope (m) and constant (c) of the
equation
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>(1)Y = mX + c
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Here, m and c are derived from a known set of
values of the independent variable X and dependent
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>variable Y. The relative strength of the linear relationship
between X and Y is measured by the
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>coefficient of determination r <SPAN
style="FONT-SIZE: 10pt">2 , which is the ratio of
the variation explained by the regression line to the
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>total variation in Y. Here is a table to help interpret the
values of r 2 ,
which range from 0 to 1:
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>The coining of the term "regression" can be attributed to Sir
Francis Galton, who observed in the late
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>1800s that tall fathers appeared to have as a rule short sons,
while short fathers appeared to have as a rule
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>tall sons. Galton suggested that the heights of the sons
"regressed" or reverted to the average. Technician
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Arthur Merrill also had a good explanation in a recent issue of
STOCKS &
COMMODITIES, and
Patrick
Lafferty
recently wrote on an application of multiple regression to gold trading.
Virtually all introductory
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>books on statistics have a detailed discussion of the linear
regression method.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Successful professional traders emphasize the importance of
having a trading plan. A trading game plan,
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>much like that of a football team, clearly defines specific
actions under different conditions. The linear
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>regression method is very useful in developing a forecast for the
next trading day's high, low and close
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>based on the last five trading sessions. The method is general
and broad-based enough so that it can be
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>used with stocks, indices or commodities. The forecast is the
basis of my trading plan: I can define what I
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>should do if the market rises above the forecast high, falls
below the forecast low or stays within the
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>forecast range. This way, I can avoid being emotional and trade
as mechanically as possible by having a
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>plan to rely on.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 9pt">FORECASTING WITH LINEAR
REGRESSION
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">I
like to use at least 10 days of data and develop a forecast for the
high, low and close. The five-day
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>regression is a good choice for short-term trading. You can use
any length of regression you like. Here
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>are the calculations with the daily close in a spreadsheet
format:
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">1
Perform a linear regression with the first five days of data to obtain
the slope m and constant c such
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>that
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">X
Value Daily Close
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
1 Day
1
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
2 Day
2
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3> ....
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
5
Day 5
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">2
Forecast the next day's close with the slope m and constant c
from step 1:
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>(2) Forecast close (Day 6) = 6m + c
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">3
Record m, c and r 2 on the same line as Day 5. Record the
forecast from step 2 one day ahead, with
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Day 6. Note when we are using five days' data, the first forecast
is for Day 6.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">4
Step the calculation ahead one day such that
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">5
Record m, c and r 2 as in step 3.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">6
Calculate the regression forecast oscillator, %F, as
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>(3)
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 10pt">%F = ((Y-Yforecast)/Y)*100
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>where Y is the close for Day 6 and Y(Forecast) is the forecast
for Day 6 from step 2 (from Day 5).
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">7
Record the oscillator on the same line as Day 6.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">8
Step the calculations ahead one day at a time until the most recent
day.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Technically, we can use the linear regression to develop a point
forecast (single value) for the next day
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>(as in step 2) or a range (interval) of values with a certain
confidence level. The interval widens, greater
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>the variation in the data and greater the desired confidence
level.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">I
use the forecast oscillator, %F, to determine if my forecast is above or
below the actual market data.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Since
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 10pt">%F = ((Y-Yforecast)/Y)*100
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 10pt">
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 10pt">where Y can be any market
variable for stocks, indices or commodities, %F measures the
percent
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>deviation of the actual value from its forecast. In a trading
market, %F changes its sign before a
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>significant trend change. In trending markets, %F tends to change
sign early in the trend. I interpret %F in
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>the context of the r 2
Of the regression. A low value of r <SPAN
style="FONT-SIZE: 10pt">2 plus a change in sign of
%F is a good signal of a
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>change in trend. Market extremes and periodicity can also be
observed on the %F charts.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 9pt">DEVELOPING A TRADING
PLAN
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>You can use the forecasts to develop a specific trading plan to
suit your trading style. I use the forecasts
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">in
several ways.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Forecasts as stops. I use the high and the low as
action points. If the market exceeds the forecast high, it
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>wants to go up. To trade with the trend, I put a buy stop a few
ticks above the high. If the market falls
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>below the forecast low, it wants to go down. Hence, I set a sell
stop a few ticks below the forecast low. If
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>you want to trade against the trend, sell short near the forecast
high and buy near the forecast low.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Forecasts as intraday range scale. The forecasts
provide a scale for evaluating the trading day. The
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>market can stay within the expected range or go outside. On a
down day, the intraday high is well below
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>the forecast high and may be below the forecast close. On an up
day, the market stays well above the
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>forecast low and often above the forecast close.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>General rules for trading with forecasts. Here are
some general rules:
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">•
Use the forecasts only if r 2 is greater than 0.1. Higher the value of r
2 , the greater the confidence in the
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>forecasts.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">•
A trend change is imminent when r 2 falls below 0.1. Prepare to close
longs.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">•
A trend is in place if r 2 is greater than 0.6. As a trend follower, you
could wait for this value to be
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>exceeded before opening positions. This would keep you out of
short-term fluctuations.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">•
An early warning of a trend change is provided by a zero-crossing of %F,
the forecast oscillator.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Prepare to tighten stops and look for changes in slope and
coefficient of determination for
<FONT
size=3>confirmation.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">•A
change in trend is confirmed by a change in slope of the regression.
Open positions in direction of
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>trend change. To trade against the trend, look for peaks in slope
and strength of the linear trend.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>•The trend will usually change in the direction of %F.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>•Always be prepared for a market move against the forecast. Use
stops!
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>A SAMPLE TRADING
PLAN
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">I
have developed a forecast for the high, low and close for January 20,
1992, from the previous five
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>trading days, seen in Figure 1. The market was making new highs
the previous week. Was a downward
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>movement imminent? Let's look at the data from Friday, January
17, 1992:
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>The market was trending moderately (0.4<= r <SPAN
style="FONT-SIZE: 10pt">2 <0.6), but the forecast
oscillator %F was negative for
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>high, low and close, warning of a possible change in trend. The
relatively small slope of the regression
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>for the high meant the market was meeting resistance. The slope
of the regression for the close had turned
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>down from the high values during the recent strong uptrend. The
forecast, however, called for a strong
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>close near the highs of the day, but that seemed doubtful, given
the low slopes in a moderating trend. The
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>plan was to watch for a change in trend. If the market opened
weak, a bearish strategy was called for. For
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>example, I would consider buying the Standard & Poor's 100
Index OEX <FONT
size=3>January 390 puts, or selling
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>short the S&P 500 March futures contract.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 16pt; FONT-FAMILY: Arial">The high daily volume of
OEX
<SPAN
style="FONT-SIZE: 16pt; FONT-FAMILY: Arial">index options traded makes
the S&P
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 16pt; FONT-FAMILY: Arial">100 index an interesting
application of me regression forecast
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 16pt; FONT-FAMILY: Arial">approach.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>The market opened at the Friday close and weakness was evident at
the open, as the S&P 500 futures
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>opened lower. It was clear in early trading that the trend would
be down, as the market traded well below
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>the forecast high and close. Clearly, the forecast range provided
a good scale, since it reinforced the
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>concept that the market was weaker than the trend of the prior
five days. A bearish stance would have
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>been profitable.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 9pt">THE NATURE OF REGRESSION
FORECASTS
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>The high daily volume of OEX
index options traded makes the S&P 100 index an
interesting application
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">of
the regression forecast approach. I have examined a time period from
early October 1991 to
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>mid-January 1992. The OEX
close and its forecast are in Figure 2; the r
2 values in
Figure 3; %F in Figure
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">4,
and Figure 5 has %F around the mid-November plunge.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Several observations can be made from the <SPAN
style="FONT-SIZE: 9pt">OEX analysis. First, the
forecast lags the OEX <FONT
size=3>in an uptrend
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">or
in a downtrend. Second, the close and the forecast cross over several
days before a trend change. This
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>crossover can be seen as a zero crossing in the %F chart.
Significant trend changes are preceded by
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>trendless periods with values of r <SPAN
style="FONT-SIZE: 10pt">2 near zero. Strong trends
are accompanied by high values of r <SPAN
style="FONT-SIZE: 10pt">2 and
regression
slope. These observations support the general rules of interpretation
noted above. As Figure 5
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>shows, %F provided a timely warning of an impending trend change
just before the OEX <FONT
size=3>fell 15.68 points.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">I
have included data for wheat (cash) from 1989 to indicate the use of
this approach with commodities.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>The market showed significant trends during this period with good
periodicity, as shown in Figures 6, 7
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>and 8. The %F zero crossings were timely indicators of trend
change. Features observed with OEX
charts
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>are also seen here; note in particular how %F can be used to
identify extremes in the market from Figures
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">4
and 8.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Simple linear regression yields forecasts of the high, low and
close for stocks, indices or commodities.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>these forecasts can be used to develop a trading plan. You can
trade with the trend, against the trend,
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>intraday or interday. The forecast oscillator, %F, provides early
warning of trend changes taken together
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>with the regression slope and coefficient of determination. This
approach works best in trending markets
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none">or
trading range markets; it is only moderately useful in volatile markets
with choppy price action. These
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>objective forecasts will let you trade less emotionally and more
mechanically. Profits will look up when
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>you can look ahead.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>Tushar Chande holds a doctorate in engineering from the
University of Illinois and a master's degree
in
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><FONT
size=3>business administration from the University of
Pittsburgh.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 8pt; FONT-FAMILY: Arial">REFERENCES
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">Lafferty, Patrick [ 1991 ].
"A regression-based oscillator," <SPAN
style="FONT-SIZE: 11.5pt; FONT-FAMILY: Arial">Technical Analysis of
STOCKS
&
<SPAN
style="FONT-SIZE: 8pt; FONT-FAMILY: Arial">COMMODITIE<SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">S,
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">Volume 9:
September.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">Merrill, Arthur [1991].
"Fitting a trendline by least squares," <SPAN
style="FONT-SIZE: 11.5pt; FONT-FAMILY: Arial">Technical Analysis of
STOCKS
&
<SPAN
style="FONT-SIZE: 8pt; FONT-FAMILY: Arial">COMMODITIE<SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">S,
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">Volume 9:
December.
<P class=MsoNormal
style="MARGIN: 0in 0in 0pt; mso-layout-grid-align: none"><SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">Pfaffenberger, Roger, and
James Patterson [1987]. <SPAN
style="FONT-SIZE: 11.5pt; FONT-FAMILY: Arial">Statistical Methods for
Business and Economic<SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">s,
<SPAN
style="FONT-SIZE: 11pt; FONT-FAMILY: Arial">Irwin.
<FONT face=Tahoma
size=2>-----Original Message-----From:
owner-metastock@xxxxxxxxxxxxx
[mailto:owner-metastock@xxxxxxxxxxxxx]On Behalf Of Steve
KarnishSent: Thursday, January 10, 2002 10:34
AMTo: metastock@xxxxxxxxxxxxxSubject: Forecast
Oscillator
List,
Does anyone have the math formula for
Chande's Forecast Oscillator?
Thanks,
<FONT face=Arial
size=2>Steve
|