Statistical Arbitrage Market Neutral Strategy

[sinner]

Hi Sinner,

Your equity and future chart looks quite interesting. Can you explain what you mean by your last line? Where on the chart will you go long/short the correlation? Actually, is there a correlation if you are just going long/short straddle on a single stock?

SR

I think you don't understand what I wrote.

I don't go long or short "the correlation" and the chart is not a chart of correlation, it is a pair of instruments (each chart is a different pair of instruments) which form the basis for a trading model, long or short of which depends on implied correlation (and a few other factors).

What I "meant" is that I prefer to place the same trade as the OP on models which make much more sense to place those sorts of trades on, because then you really are betting on only one thing (correlation returning) rather than two things (correlation returning and cointegration remaining high).

 

[SilverRanger]

I think you don't understand what I wrote.

I don't go long or short "the correlation" and the chart is not a chart of correlation, it is a pair of instruments (each chart is a different pair of instruments) which form the basis for a trading model, long or short of which depends on implied correlation (and a few other factors).

What I "meant" is that I prefer to place the same trade as the OP on models which make much more sense to place those sorts of trades on, because then you really are betting on only one thing (correlation returning) rather than two things (correlation returning and cointegration remaining high).

Hi Sinner,

Yes, I am a bit confused here as I thought you were doing volatility dispersion trading (something I've been reading lately and keen to paper trade on).

What do you do that other pair traders don't so that you can "bet on only correlation returning, but not cointegration remain high"? Is it by going long/short stock/index straddles?

SR

 

[sinner]

What do you do that other pair traders don't so that you can "bet on only correlation returning, but not cointegration remain high"? Is it by going long/short stock/index straddles?

SR

Without being too specific (and giving it away), I constrain my models to instruments where the edge is derived from market inefficiency rather than simply hoping based on a statistical model that the cointegration is "real".

You can see it plain as day in the charts, BHP/RIO pair looks completely different to my pairs. If you compare the bollinger bands on the equities charts vs the futs it gives you a clue. That's it from me, holidays!

 

[SilverRanger]

Without being too specific (and giving it away), I constrain my models to instruments where the edge is derived from market inefficiency rather than simply hoping based on a statistical model that the cointegration is "real".

You can see it plain as day in the charts, BHP/RIO pair looks completely different to my pairs. If you compare the bollinger bands on the equities charts vs the futs it gives you a clue. That's it from me, holidays!

Sinner,

Thanks for your answer, I think that will keep me busy over the weekend to work something out. Have fun in your holidays

SR