Nasdaq Index Arbitrage

Quote from cdcaveman:

http://blog.quanttrader.org/tag/cointegration/

Code already written....
More...

Caveman,

You are a lifesaver! Defiantly have my hands full for a project this weekend thanks to this link!

This is going to sound kind of naive but when it comes to programming and coding i often see Excel/VBA, R/Matlab, and C/Python

I was wondering if you could bridge the gap between those 3 subsets and how they interconnect. I essentially store all of my data in Excel and right now do all of my Stat Anal in Excel but will shortly be moving to R/Matlab. I'm not sure how and why VBA/C/Python comes into the whole picture. This is a little off topic from the original thread but we seem to be on the same wavelength so I thought I would ask

etfarb
 
what you want to do is easier done with the dow futures, those weights are public... nasdaq are only available for sale... and guarded quite a bit... and it is a good idea to have a clue how the constituents influence the index future, after all... they are the true underlying...
 
Quote from etfarb:

Caveman,

You are a lifesaver! Defiantly have my hands full for a project this weekend thanks to this link!

This is going to sound kind of naive but when it comes to programming and coding i often see Excel/VBA, R/Matlab, and C/Python

I was wondering if you could bridge the gap between those 3 subsets and how they interconnect. I essentially store all of my data in Excel and right now do all of my Stat Anal in Excel but will shortly be moving to R/Matlab. I'm not sure how and why VBA/C/Python comes into the whole picture. This is a little off topic from the original thread but we seem to be on the same wavelength so I thought I would ask

etfarb
More...

MATLAB I don't know much about... but its not open source I don't think. You can save as CSV and work in RStudio with your data. C/python are lower level languages then VBA ...VB is what you would use to automate common routines in excel...

you can load quantmod into R and get quotes very simply from yahoo...
 
Quote from ofthomas:

what you want to do is easier done with the dow futures, those weights are public... nasdaq are only available for sale... and guarded quite a bit... and it is a good idea to have a clue how the constituents influence the index future, after all... they are the true underlying...
More...

ofthomas,

Interesting you brought that up because thats why i posted here in the first place. I understand that the nasdaq universe is a total of 3000 issues. I have not been able to find the total weight of the index in comparison to its weightings hence why I am going to go with assumptions from developing a basket of the 10-15 largest weightings from the nasdaq 100. It doesn't take a rocket scientist to figure out that the QQQ basket is pretty much what moves the entire index. I'm targeting the Nasdaq due to its vulnerability to its handful of components that move it. I havn't given the dow much thought but I may since you've brought it up. However, as I've mentioned in my past posts on this thread. The last few drops on the NQ my system pretty much gave a layup to go short, I just don't feel comfortable trading when I don't fully understand the mechanics inside and out
 
Quote from cdcaveman:

MATLAB I don't know much about... but its not open source I don't think. You can save as CSV and work in RStudio with your data. C/python are lower level languages then VBA ...VB is what you would use to automate common routines in excel...

you can load quantmod into R and get quotes very simply from yahoo...
More...

I guess its best to do 1 thing at a time rather then try to learn everything at once. CDcaveman, thank again man, I really appreciate this!
 
Quote from etfarb:

ofthomas,

Interesting you brought that up because thats why i posted here in the first place. I understand that the nasdaq universe is a total of 3000 issues. I have not been able to find the total weight of the index in comparison to its weightings hence why I am going to go with assumptions from developing a basket of the 10-15 largest weightings from the nasdaq 100. It doesn't take a rocket scientist to figure out that the QQQ basket is pretty much what moves the entire index. I'm targeting the Nasdaq due to its vulnerability to its handful of components that move it. I havn't given the dow much thought but I may since you've brought it up. However, as I've mentioned in my past posts on this thread. The last few drops on the NQ my system pretty much gave a layup to go short, I just don't feel comfortable trading when I don't fully understand the mechanics inside and out
More...

careful, without knowing the actual weights and how they are calculated, you run the risk of guessing the wrong way....that is why APPL can be red and NQ still move higher... in any event... NQ will lead/lag depending on the type of economic cycle we are in... which is what you are seeing... just my two cents, for whatever they are worth....
 
Quote from etfarb:

I guess its best to do 1 thing at a time rather then try to learn everything at once. CDcaveman, thank again man, I really appreciate this!
More...

I was on my phone earlier.. but generally... i think the best thing to do is not be distracted by to many different technologies..

i did some research to find out what in the long run would be the most powerful thing to get involved in... you don't wanna be restricted at how you look at reality by the tools that are available to you just through your broker and or trading platform defaults..

Anyone in higher level statistical work would agree R is very very good.. i can say that with confidence.. there is a big community behind it to help you.. work on something.. post your work , get help , learn .. and soon you will be on your way to being proficient..

i'm not good with plot() or ggplot() in R yet.. but some more fooling around and i'm sure i'll get it ..

get a irc client like Xchat.. thats my favorite.. freenode is the server # R-Finance is the channel.. lots of help there.. LOTS.

alot of the guys in there are very proficient... and very helpful.. paste your code in pastebin.com post it in the chat.. someone will help you..
i also joined the google group for ggplot2 and get emails respectively..

stuff i think is cool..
http://algorithmzoo.com/
http://spatialanalysis.co.uk/2012/10/londons-twitter-languages/


resources
http://cran.r-project.org/other-docs.html
http://cran.r-project.org/doc/contrib/Lam-IntroductionToR_LHL.pdf
http://cran.r-project.org/doc/manuals/R-intro.pdf
 
Quote from etfarb:

I;m not looking to do HFT arb.

I'm simply looking to make a basket from the 10-15 largest weightings in the nasdaq to help me decide when I should go long or short the index.

I swing trade so i use EOD data to backtest. I read an article that basically says you need to figure out what assets cointegrate with the index in order to figure out the weightings. I was wondering if there was an easier way to do this since i don't know R and don't own matlab

is there a way to test for cointegration in excel?
More...

Dude you're making this WAY to hard.
 
You must log in or register to reply here.
Back
Top