Costa’s minimal surface equation and its applicability for $SPX year end projection

Costa’s minimal surface and its applicability for $SPX year end projection

math-minimal-surface

incase if you had forgotten the  equation from your physics classes .. ,the Costa’s minimal surface equation is below

The other day, we finally managed to apply Alfred Gray’s parametric equations  on how to use it for $SPX year end price target.

Here, \wp, \wp^\prime and \zeta are respectively the Weierstrass elliptic function, its derivative, and the Weierstrass zeta function, with invariants g_2=\left(\frac12\mathrm{B}\left(\frac14,\frac14\right)\right)^4=\frac{\Gamma(1/4)^8}{16\pi^2} and 0, and \mathrm{B}(x,y) and \Gamma(x) are the usual beta and gamma functions. The invariants are the ones corresponding to the semi-periods \omega_1=\frac12 and \omega_3=\frac{i}{2}. The parameter ranges are 0 < u < 1 and 0 < v < 1.

We may not be able to give the full details ( as they are proprietary of nature ) on how to manipulate the Weierstrass elliptic functions that show up in the equations, but below the details on how the equation fared against each year end’s actual $SPX close

Year Actual $SPX Close Equation Prediction Error in the Prediction
2016 ?? 3665 ??
2015 2044 2040 0.19
2014 2059 2076 0.82
2013 1848 1858 0.52
2012 1426 1414 0.86
2011 1258 1250 0.61
2010 1258 1248 0.77
2009 1115 1126 0.97
2008 903 901 0.25
2007 1468 1472 0.25
2006 1418 1406 0.87
2005 1248 1256 0.61
2004 1212 1206 0.49
2003 1112 1108 0.35
2002 880 885 0.59
2001 1148 1141 0.62
2000 1320 1330 0.73
1999 1469 1456 0.91
1998 1229 1232 0.22
1997 970 971 0.06
1996 741 742 0.17
1995 616 612 0.64
1994 459 462 0.59
1993 466 464 0.53
1992 436 434 0.39
1991 417 419 0.46
1990 330 329 0.37
1989 353 353 0.11
1988 278 278 0.10
1987 247 247 0.03
1986 242 241 0.49
1985 211 213 0.81
1984 167 167 0.14
1983 165 165 0.04
1982 141 140 0.46
1981 123 123 0.37
1980 136 135 0.56
1979 108 109 0.97
1978 96 97 0.92
1977 95 96 0.94
1976 107 107 0.43
1975 90 90 0.21
1974 69 69 0.64
1973 98 98 0.46
1972 118 118 0.04
1971 102 103 0.88
1970 92 93 0.91
1969 92 92 0.07
1968 104 103 0.83
1967 96 97 0.55
1966 80 80 0.41
1965 92 93 0.61
1964 85 85 0.29
1963 75 75 0.03
1962 63 63 0.16
1961 72 71 0.77
1960 58 58 0.19
1959 60 60 0.18
1958 55 55 0.38
1957 40 40 0.02
1956 47 47 0.70
1955 45 46 1.13
1954 36 36 0.06
1953 25 25 0.76
1952 27 27 1.59
1951 24 24 0.96
1950 20 21 2.71

ps: you might want to decode 3665 ( which is the year end target ) on your phone !!

$SPX Field guide to corrections since 1950

$SPX Field guide to corrections since 1950

1) click on the below image , 2) magnify it , 3) & take an A5 print out  4) & post it in-front of your desk , 5) & thank us later !!

spx corrections png

ps: ms.painted by son as an excercise , color code may or may not be proper for the reader to the feel

pps: would post some other stats later before Monday Open

you might want to consider subscribing to our daily quant rants email  !!

check out the new look of the paststat

 

$AAPL earning’s and historical price reaction since Y2k

$AAPL earning’s and historical price reaction

AAPL Earningswith almost $750 bn at stake , below various studies around $AAPL historical earnings ..

as $AAPL announces earnings , after market close , the change % on the  next day is considered as the ER day change

1) $AAPL trading odds for longs on the ER day , ( change from ER prior day’s close to next day’s close) , since Y2K 

# 62
Winners : 36
Losers : 26
% Winners : 58%
Average Change % : 1.24
Median Change % : 2.64
Maximum Gain % : 13.16
Maximum Loss % : -17.17
Average Gain %if Winner : 6.02
Average Loss % if Loser : -5.38
Payoff Ratio * 1.12
Average Absolute Change% 5.82

* Payoff Ratio is average winner (%) divided by average loser (%)

1-a) $AAPL trading odds for longs on the ER day night , ( change from ER prior day’s close to next day’s open) , since Y2K 

# 62
Winners : 39
Losers : 23
% Winners : 63%
Average Change % : 1.71
Median Change % : 2.19
Maximum Gain % : 12.68
Maximum Loss % : -13.23
Average Gain %if Winner : 5.82
Average Loss % if Loser : -5.26
Payoff Ratio 1.11
Average Absolute Change% 5.68

1-c) $AAPL trading odds for longs , from the open to close , after ER ( i’e the day session;s change , after the ER is out ) , since Y2K 

# 62
Winners : 21
Losers : 41
% Winners : 34%
Average Change % : -0.46
Median Change % : -0.64
Maximum Gain % : 8.74
Maximum Loss % : -5.30
Average Gain %if Winner : 2.25
Average Loss % if Loser : -1.89
Payoff Ratio 1.19
Average Absolute Change% 1.97

2) when $AAPL is trading with-in 10% to ATH ( like the case as is today) , ER full day trading odds for longs , since Y2K

# 24
Winners : 15
Losers : 9
% Winners : 63%
Average Change % : 1.10
Median Change % : 2.51
Maximum Gain % : 6.77
Maximum Loss % : -9.21
Average Gain %if Winner : 4.35
Average Loss % if Loser : -4.31
Payoff Ratio 1.01
Average Absolute Change% : 4.46

2-a) when $AAPL is trading with-in 10% to ATH , ER day over night trading odds for longs , since Y2K 

# 24
Winners : 17
Losers : 7
% Winners : 71%
Average Change % : 2.62
Median Change % : 3.47
Maximum Gain % : 12.60
Maximum Loss % : -5.70
Average Gain %if Winner : 5.43
Average Loss % if Loser : -4.23
Payoff Ratio 1.29
Average Absolute Change% : 5.24

2-b) when $AAPL is trading with-in 10% to ATH , ER day , regular session’s trading odds for longs , since Y2K 

# 24
Winners : 6
Losers : 18
% Winners : 25%
Average Change % : -1.44
Median Change % : -1.49
Maximum Gain % : 2.01
Maximum Loss % : -5.30
Average Gain %if Winner : 0.90
Average Loss % if Loser : -2.36
Payoff Ratio 0.38
Average Absolute Change% : 1.85

3) $AAPL full day change after ER , in the July / Q2 earnings , since Y2K

# 15
Winners : 10
Losers : 5
% Winners : 67%
Average Change % : 0.75
Median Change % : 2.67
Maximum Gain % : 11.83
Maximum Loss % : -17.17
Average Gain %if Winner : 5.58
Average Loss % if Loser : -8.90
Payoff Ratio 0.63
Average Absolute Change% : 6.68

conclusion –

1) “if  the setup of $AAPL trading within 10% to ATH closing , repeats itself , perhaps , a long into ER night and then reverse the trade in the morning ??”

2) ” the max gain on ER day is 13.2 % , so forget about 150 weeklies :)

 

below the historical ER dates and $AAPL , over night gap , next day open to change  & full day change details , in percentage , since Y2K

ER-Date Over Night Gap % Next Day Open to Close % Full Day Change % Absoulte Change %
21-Jul-15 ?? ?? ?? ??
27-Apr-15 1.36 -2.90 -1.58 1.58
27-Jan-15 7.78 -1.97 5.65 5.65
20-Oct-14 3.27 -0.53 2.72 2.72
22-Jul-14 0.74 1.85 2.61 2.61
23-Apr-14 8.28 -0.08 8.20 8.20
27-Jan-14 -7.58 -0.44 -7.99 7.99
28-Oct-13 1.21 -3.65 -2.49 2.49
23-Jul-13 4.76 0.36 5.14 5.14
23-Apr-13 -3.10 3.03 -0.16 0.16
23-Jan-13 -10.51 -2.07 -12.36 12.36
25-Oct-12 -0.02 -0.89 -0.91 0.91
24-Jul-12 -4.40 0.09 -4.32 4.32
24-Apr-12 9.88 -0.92 8.87 8.87
24-Jan-12 8.09 -1.71 6.24 6.24
18-Oct-11 -4.95 -0.68 -5.59 5.59
19-Jul-11 5.11 -2.33 2.67 2.67
20-Apr-11 3.68 -1.21 2.42 2.42
18-Jan-11 2.26 -2.73 -0.53 0.53
18-Oct-10 -4.59 2.01 -2.68 2.68
20-Jul-10 5.24 -4.09 0.93 0.93
20-Apr-10 5.81 0.16 5.98 5.98
25-Jan-10 1.42 0.00 1.41 1.41
19-Oct-09 5.66 -0.92 4.69 4.69
21-Jul-09 4.14 -0.67 3.45 3.45
22-Apr-09 4.21 -0.96 3.20 3.20
21-Jan-09 6.29 0.36 6.68 6.68
21-Oct-08 6.43 -0.51 5.88 5.88
21-Jul-08 -10.40 8.74 -2.57 2.57
23-Apr-08 1.50 2.18 3.71 3.71
22-Jan-08 -12.50 2.11 -10.65 10.65
22-Oct-07 8.14 -1.27 6.77 6.77
25-Jul-07 6.30 0.06 6.37 6.37
25-Apr-07 6.53 -2.70 3.66 3.66
17-Jan-07 -3.00 -3.29 -6.19 6.19
18-Oct-06 6.35 -0.34 5.98 5.98
19-Jul-06 12.68 -0.75 11.83 11.83
19-Apr-06 5.88 -2.70 3.02 3.02
18-Jan-06 -1.50 -2.72 -4.18 4.18
11-Oct-05 -5.70 1.23 -4.54 4.54
13-Jul-05 6.36 -0.10 6.26 6.26
13-Apr-05 -5.43 -3.99 -9.21 9.21
12-Jan-05 12.60 -5.30 6.63 6.63
13-Oct-04 8.65 4.14 13.16 13.16
14-Jul-04 10.41 0.83 11.32 11.32
14-Apr-04 8.18 1.67 9.98 9.98
14-Jan-04 -5.33 -0.26 -5.58 5.58
15-Oct-03 -4.11 -2.31 -6.33 6.33
16-Jul-03 1.61 3.52 5.18 5.18
16-Apr-03 -0.30 -0.61 -0.91 0.91
15-Jan-03 -1.52 2.89 1.32 1.32
16-Oct-02 -2.40 -0.70 -3.09 3.09
16-Jul-02 -9.69 -3.10 -12.49 12.49
17-Apr-02 -2.34 -0.35 -2.68 2.68
16-Jan-02 5.68 2.37 8.18 8.18
17-Oct-01 1.77 4.11 5.94 5.94
17-Jul-01 -13.23 -4.55 -17.17 17.17
18-Apr-01 12.11 0.67 12.86 12.86
17-Jan-01 5.95 4.91 11.15 11.15
18-Oct-00 -4.81 -1.14 -5.90 5.90
18-Jul-00 -3.60 -4.53 -7.97 7.97
19-Apr-00 2.12 -3.89 -1.86 1.86
19-Jan-00 8.39 -1.73 6.51 6.51

you might want to consider subscribing to our daily quant rants email  !!

check out the new look of the paststat

RIP Nelson Fraser Freeburg Jr.

RIP Nelson Fraser Freeburg Jr.

Nelson-Freeburg-1435595124

 

link to Nelson Fraser Freeburg Jr. Obituary to share your memories ..

below few public links of his work

I’ve read his newsletter Formula Research , and benefited a lot .

I’d like to present few simple tweaks of his models in his memory

1) yearly $SPX market timing based on PMI 

PMI data source FRED 

a) below the trading odds for buying $SPX ( minus dividends) , at the end of Dec ( i.e last trading day of the year and exiting at next year’s Dec end , data since 1950

Winners : 47
Losers : 17
% Winners : 73%
Average Change % : 8.86
Median Change % : 11.60
Maximum Gain % : 45.00
Maximum Loss % : -38.50
Average Gain %if Winner : 16.78
Average Loss % if Loser : -13.85
Payoff Ratio 1.21

b) buy $SPX , if the PMI reading at the current year’s Dec is greater then the last year’s Dec

Winners : 21
Losers : 11
% Winners : 66%
Average Change % : 5.37
Median Change % : 7.40
Maximum Gain % : 34.10
Maximum Loss % : -23.40
Average Gain %if Winner : 13.73
Average Loss % if Loser : -11.65
Payoff Ratio 1.18

c) buy $SPX , if the PMI reading at the current year’s Dec is less then the last year’s Dec

Winners : 26
Losers : 6
% Winners : 81%
Average Change % : 12.35
Median Change % : 14.20
Maximum Gain % : 45.00
Maximum Loss % : -38.50
Average Gain %if Winner : 19.24
Average Loss % if Loser : -17.52
Payoff Ratio 1.10

conclusion : it is better to buy $SPX in those years , when there is a PMI contraction 

ps: Dec 2014 PMI reading was 55.1 , which was less than that of Dec 2013 reading of 56.1 , and $SPX closed at 2058.9 as on Dec 2014.

2) quarterly  $SPX market timing  based on composite ROC 

ROC is the rate of the change over certain look period , for ex: ROC(3) , is the change in percent , from current monthly close to 3 months ago , for ex: for Jun end , it is the change % from Mar close to Jun close .

a) trading odds for buying at any quarter end and exiting at the next quarter end , data since 1950

Winners : 170
Losers : 91
% Winners : 65%
Average Change % : 2.15
Median Change % : 2.80
Maximum Gain % : 21.60
Maximum Loss % : -26.10
Average Gain %if Winner : 6.49
Average Loss % if Loser : -5.96
Payoff Ratio 1.09

let’s define composite ROC on monthly , as the average of ROC(3), ROC(6) & ROC(12)

for the quarter ending Jun 2015 , the composite ROC , is

ROC(3) = -1.2, ROC(6) = 0.2 , an ROC(12) = 5.2 and the average of those three which is composite ROC is 1.7

b) buy  $SPX at Qtr end , when the composite ROC is +’ve and exit at next Qtr end , data since 1950

Winners : 127
Losers : 60
% Winners : 68%
Average Change % : 2.36
Median Change % : 2.50
Maximum Gain % : 20.50
Maximum Loss % : -23.20
Average Gain %if Winner : 5.84
Average Loss % if Loser : -4.99
Payoff Ratio 1.17

c) buy  $SPX at Qtr end , when the composite ROC is -‘ve and exit at next Qtr end , data since 1950

Winners : 39
Losers : 31
% Winners : 56%
Average Change % : 1.39
Median Change % : 2.90
Maximum Gain % : 21.60
Maximum Loss % : -26.10
Average Gain %if Winner : 8.72
Average Loss % if Loser : -7.84
Payoff Ratio 1.11

conclusion : you see there is that slight edge of going long , when the composite ROC is +’ve

 

 

$IWM from Russel Re-balance Day – Sorry There is No Edge

$IWM from Russel Re-balance Day – No Edge

rebalancebelow the trading odds for $IWM for a 1/2/3/4/5/10/20 trading day holding period from the last Friday of the June ( annual Russel re-balancing date ) , data since Y2K

Exit # Wins % Wins Avg% Med% Avg Win % Avg Loss % Pay Off Max Loss % OAPF T-Test
t+1 15 8 53.3 0.12 0.26 1.02 -0.91 1.12 -2.26 1.51 0.40
t+2 15 9 60.0 -0.06 0.37 1.40 -2.26 0.62 -4.99 1.18 -0.11
t+3 15 10 66.7 -0.02 1.25 1.93 -3.93 0.49 -6.12 1.06 -0.03
t+4 15 8 53.3 -0.36 1.22 2.30 -3.41 0.67 -6.11 0.82 -0.44
t+5 15 7 46.7 -0.42 -0.10 3.08 -3.48 0.88 -7.14 0.68 -0.43
t+10 15 6 40.0 -0.39 -1.86 5.58 -4.37 1.28 -10.05 0.66 -0.28
t+20 15 7 46.7 -0.45 -0.64 5.17 -5.37 0.96 -12.24 0.63 -0.29
1st +’ve exit in 5 days 15 11 73.3 -0.81 0.63 0.95 -5.65 0.17 -7.14 0.46 -1.06
1st -‘ve exit in 5 days 15 9 60.0 -0.70 -0.21 -0.78 2.90 0.27 5.19 0.19 -1.30

PF: Profit Factor, and OAPF is the outlier adjusted profit factor ( which is profit factor recalculated after removing the maximum winner )

conclusion : we don’t see any major edge to go long or short from the close of Russel  re-balancing day ,

below the historical returns of $IWM from the  Russel  re-balancing day ,  since Y2K

Date $IWM t+1% t+2% t+3% t+4% t+5% t+10% t+20%
27-Jun-14 116.77 0.40 1.42 1.03 1.64 -0.10 -1.86 -4.12
28-Jun-13 94.44 1.63 1.56 1.76 3.20 3.62 7.25 7.05
29-Jun-12 76.28 1.16 2.48 2.36 1.22 0.83 -0.14 -0.64
24-Jun-11 75.14 0.78 2.34 2.83 3.58 5.19 4.54 4.22
25-Jun-10 60.00 -0.57 -4.33 -5.43 -6.11 -7.14 -3.40 3.17
26-Jun-09 46.98 0.00 -0.29 1.25 -2.24 -3.10 -3.51 7.91
27-Jun-08 62.88 -0.98 -0.90 -3.71 -4.23 -5.44 -4.77 0.01
29-Jun-07 74.21 1.29 1.77 1.94 2.29 2.20 1.91 -5.96
30-Jun-06 63.49 1.25 -0.22 -0.25 -1.73 -1.71 -5.98 -2.86
24-Jun-05 54.48 0.26 1.82 2.62 2.40 2.85 7.35 7.51
25-Jun-04 50.43 -0.21 0.63 1.19 -0.65 -0.34 -3.95 -8.89
27-Jun-03 38.09 -0.31 0.37 2.88 2.00 4.12 6.99 6.30
28-Jun-02 38.26 -2.04 -4.99 -6.12 -3.01 -5.02 -10.05 -12.24
29-Jun-01 42.56 -2.26 -2.85 -4.12 -5.89 -5.00 -5.64 -5.45
30-Jun-00 42.62 1.41 0.26 1.44 2.07 2.74 5.46 -2.77

you might want to consider subscribing to our daily quant rants email  !!

check out the new look of the paststat

 

Prior Much Awaited All Time High Closings

Prior Much Awaited All Time High Closings

Finally! Nasdaq tops its March 2000 record

 

with Nasdaq ( IXIC) closing at an All Time High after 3801 trading days , below $STUDY

there were 13 much awaited ( defined as , i.e 1000 ++ trade days of waiting between prior ATH and the current ATH ) ATH closes ( on DJIA , SPX , IXIC & RUT from the DB that i operate) goes back to 1900 on DJIA , 1950 on SPX , 1979 on IXIC and only till 1987 on RUT

1) only ATH ( All Time High) closings were considered and not the Intra-day-high’s
2) # days between prior ATH , is the distance in trading days between the current and prior ATH closing
3) below the long awaited ATH of the four indices .. and the forward one year returns
Date DJIA # days between prior ATH t-252 % t+252 %
05-Mar-13 14253.77 1358 9.81 14.78
03-Oct-06 11727.34 1699 11.31 19.94
03-Nov-82 1065.49 2478 22.92 15.37
10-Nov-72 995.26 1676 22.43 -10.47
23-Nov-54 382.74 7308 38.97 25.91
31-Dec-24 120.51 1545 23.61 29.16
28-Sep-16 103.11 3098 6.62 -9.93
24-Mar-05 79.27 1122 67.06 29.30
avg% for any 252 days 6.61
Date SPX
28-Mar-13 1569.19 1375 10.78 18.38
30-May-07 1530.23 1802 19.53 -8.62
17-Jul-80 121.44 1897 19.52 7.67
avg% for any 252 days 8.86
Date IXIC
23-Apr-15 5056.06 3801 22.51 ??
07-Sep-78 137.09 1424 35.36 7.13
avg% for any 252 days 12.02
Date RUT
05-Apr-04 606.39 1021 62.45 1.62
avg% for any 252 days 10.08
below the trading odds for buying the First All Time High Closing after 1000 or more trading days and holding for an year
Winners : 10
Losers : 3
% Winners : 77%
Average Change % : 10.79
Median Change % : 14.78
Maximum Gain % : 29.30
Maximum Loss % : -10.47
Average Gain %if Winner : 16.93
Average Loss % if Loser : -9.67
Payoff Ratio 1.75
do note that it’s tiny sample of 13 from an aprox of 65K++ !!
ps: difficult to operate an excel with one hand only ( as the other hand bruised badly in freakish biking incident while on a holiday) , prior experience from others in such situations would be of help :)

you might want to consider subscribing to our daily quant rants email  !!

contact us for your quant trading programming needs in python and or R 

check out Quant-Ideas  to aid the short term trader to find high probability winning trades

 

S&P 500 Stocks Apr-Jun 2015 Quarter Seasonality

S&P 500 Stocks Apr-Jun 2015 Quarter Seasonality 

Stocks Seasonality

 “Just as the seasons change, so does investment sentiment toward various stocks and industries. The patterns and trends, which would seemingly be widely known and acted upon, repeat over and over and can be exploited by confident investors willing to research when stocks tend to rally and falter.”

 S&P 500 Stocks Apr-Jun 2015 Quarter Seasonality Excel Sheet 

Contains Apr-Jun , Quarterly Seasonality for all the S&P 500 Stocks since 1990 , with the following columns as shown below

Sample First 10 Columns ( in alphabetical order)  in the S&P  500 Stocks Apr-Jun , Quarterly Seasonality Excel Sheet

Symbol # Wins % Wins Avg % Med % Avg Win % Avg loss % Pay Off STDEVP Avg % for any Qtr T-test
A 15 9 60 1.95 3.19 15.88 -18.96 0.84 21.31 2.53 -0.11
AA 25 13 52 4.60 2.58 18.09 -10.00 1.81 18.21 2.42 0.60
AAL 9 5 56 2.90 2.31 27.75 -28.17 0.99 38.38 11.18 -0.65
AAPL 25 12 48 1.23 -2.60 20.84 -16.87 1.23 21.51 8.28 -1.64
ABBV 2 2 100 6.56 6.56 6.56 4.25 5.87 0.23
ABC 19 14 74 11.28 9.30 18.69 -9.45 1.98 25.58 6.32 0.85
ABT 25 16 64 5.33 6.07 11.54 -5.70 2.02 11.27 3.60 0.77
ACE 22 16 73 4.07 3.38 8.17 -6.86 1.19 9.77 4.18 -0.05
ACN 13 7 54 2.45 2.62 12.83 -9.66 1.33 13.29 5.48 -0.82
ACT 22 14 64 9.89 13.22 22.87 -12.84 1.78 20.19 5.65 0.99

Definitions

  • # Total number of instances
  • Wins Number of winning Months ( i’e number of months when returns are positive)
  • % Wins Percentage winning Months ( i’e number of months when returns are positive)
  • Avg % Average Monthly Returns in percentage
  • Med % Median Monthly Returns in percentage
  • Avg Win % Average % change if the returns in month are positive
  • Avg Loss % Average % change if the returns in month are negative
  • Pay Off Ratio of Average Win % divided by Average Loss% , A.k.a Pay-off Ratio.
  • STDEVP Standard deviation of the Monthly percentage returns , ( the lower the the better)
  • Avg for any Month Average percentage returns for any month
  • T-test Sqrt(number of instance) * (Avg for the month – Average for any month )/ Standard Deviation of Monthly returns look for a value above 1.8 or below -1.8 for a sample size of more than 20 , for the seasonal returns to be statistically significant
  • Monthly returns are calculated from the close of the last trading day of the previous month to the last trading of the current month
  • Quarterly returns are calculated from the close of the last trading day of the previous quarter to the last trading of the current quarter

Sample First 10 Columns ( in alphabetical order)  in the S&P  500 Stocks Apr Monthly Seasonality Excel Sheet 

Symbol # Wins % Wins Avg % Med % Avg Win % Avg loss % Pay Off STDEVP Avg for any Month T-test
A 15 8 53 2.03 1.31 11.27 -8.52 1.32 12.59 1.15 0.27
AA 25 13 52 4.45 2.57 13.04 -4.86 2.69 12.96 0.79 1.41
AAL 9 4 44 7.41 -0.42 24.38 -6.17 3.95 20.29 3.35 0.60
AAPL 25 14 56 2.89 0.47 10.11 -6.30 1.60 10.90 2.40 0.22
ABBV 2 2 100 8.10 8.10 8.10 5.87 2.38 1.38
ABC 20 12 60 2.56 2.86 9.09 -7.24 1.26 10.75 2.03 0.22
ABT 25 20 80 3.59 3.64 5.54 -4.21 1.32 5.13 1.20 2.33
ACE 22 17 77 3.62 3.86 5.55 -2.95 1.88 5.19 1.37 2.03
ACN 13 9 69 0.24 1.84 4.49 -9.33 0.48 7.60 1.50 -0.60
ACT 22 12 55 2.41 1.78 9.39 -5.97 1.57 9.75 1.94 0.22

Similarly the excel sheet contains seasonality for the months of May and June as well .

warning ! Seasonality alone never justifies a trade all by itself, but it deserves as yet another tool in trader’s toolbox for market timing .

price : Pay What You Want ( all the donations goes to Autism Charity cause ) 

( you might to do us a favor by click to tweet  pls) 

you might want to consider subscribing to our daily quant rants email  !!

contact us for your quant trading programming needs in python and or R 

check out Quant-Ideas  to aid the short term trader to find high probability winning trades

Bearish $IWM seasonal pattern as on 7th Apr 2015

Bearish $IWM seasonal pattern as on 7th Apr 2015

Bearish Seasonal Pattern

Below the trading odds for $IWM for going long on the 4th trading of April , ( i.e 7th Apr 2015 close) and exiting after 1/2/3/4/5/10/20 trading days , since 2001( since $IWM IPO )

Exit # Wins % Wins Avg% Med% Avg Win % Avg Loss % Pay Off Max Loss % PF OAPF STDEV T-Test
t+1 14 4 28.6 -0.78 -0.18 0.34 -1.23 0.28 -3.55 0.10 0.04 1.21 -2.41
t+2 14 5 35.7 -0.66 -0.47 0.57 -1.34 0.42 -3.96 0.21 0.14 1.28 -1.93
t+3 14 7 50.0 -0.30 -0.03 1.20 -1.81 0.67 -3.44 0.49 0.30 1.90 -0.59
t+4 14 6 42.9 -0.16 -0.55 1.92 -1.73 1.11 -3.80 0.60 0.41 2.13 -0.29
t+5 14 6 42.9 -0.73 -1.56 1.84 -2.65 0.69 -3.66 0.43 0.29 2.38 -1.15
t+10 14 8 57.1 0.67 0.66 2.98 -2.41 1.24 -5.09 1.12 0.88 3.03 0.83
t+20 14 9 64.3 1.92 1.59 4.83 -3.32 1.46 -4.68 1.64 1.21 5.23 1.37
1st +’ve exit in 5 days 14 10 71.4 -0.13 0.44 0.99 -2.94 0.34 -3.66 0.59 0.40 2.03 -0.25
1st -‘ve exit in 5 days 14 14 100.0 1.01 -0.51 -1.01 NA NA NA NA INF 1.05 3.58

1st -‘ve exit in 5 days assumes , one goes short at current close and exits at lower close than the entry in the next 5 trading days , otherwise buy to cover with a loss at the end of the 5th trading day ..

14/14 times $IWM closed lower than the entry at some point of time in the next 5 trading days , with an average loss of 101 bps at the 1st -‘ve close ..

PF: Profit Factor, and OAPF is the outlier adjusted profit factor ( which is profit factor recalculated after removing the maximum winner )

below the historical returns of $IWM from the close of  4th trading day of April 

Date $IWM t+1% t+2% t+3% t+4% t+5% t+10% t+20% 1st +’ve cls % 1st -‘ve cls%
07-Apr-15 * 125.35 ?? ?? ?? ?? ?? ?? ?? ?? ??
04-Apr-14 112.97 -1.46 -0.77 0.66 -2.20 -3.56 -0.90 -2.27 0.66 -1.46
04-Apr-13 89.48 -0.20 0.63 0.34 2.16 2.29 -2.54 1.49 0.63 -0.20
05-Apr-12 77.83 -1.64 -3.96 -2.60 -1.21 -2.51 -1.68 -3.06 -2.51 -1.64
06-Apr-11 80.26 -0.60 -1.64 -2.52 -3.80 -3.66 -1.82 -2.99 -3.66 -0.60
07-Apr-10 64.90 -0.11 0.49 0.91 1.14 3.30 3.82 0.03 0.49 -0.11
06-Apr-09 41.13 -3.55 -1.77 3.99 4.04 1.02 4.50 12.25 3.99 -3.55
04-Apr-08 64.17 -0.16 -0.26 -1.89 -0.86 -3.40 0.72 1.96 -3.40 -0.16
05-Apr-07 71.87 0.14 0.45 -0.18 0.50 1.14 2.32 2.96 0.14 -0.18
06-Apr-06 67.37 -1.60 -1.71 -3.44 -2.43 -2.20 0.59 1.69 -2.20 -1.60
06-Apr-05 53.60 0.39 -1.14 -1.62 -0.71 -2.48 -5.09 -3.58 0.39 -1.14
06-Apr-04 51.45 0.76 -0.14 0.12 -2.22 -2.51 -2.41 -4.68 0.76 -0.14
04-Apr-03 31.78 0.06 0.16 -0.41 -0.38 -0.91 3.15 9.60 0.06 -0.41
04-Apr-02 41.77 -0.14 1.10 0.74 2.68 1.03 3.76 3.14 1.10 -0.14
05-Apr-01 37.03 -2.81 -0.68 1.67 1.00 2.24 4.94 10.34 1.67 -2.81

* 125.35 – at the time of writing 

you might want to consider subscribing to our daily quant rants email  !!

contact us for your quant trading programming needs in python and or R 

check out Quant-Ideas  to aid the short term trader to find high probability winning trades