Have you tried synchronizing R processes? I did and it wasn’t straightforward. In fact, I ended up creating a new package – flock.
One of the improvements I did not too long ago to my R back-testing infrastructure was to start using a database to store the results. This way I can compute all interesting models (see the “ARMA Models for Trading” series for an example) once and store the relevant information (mean forecast, variance forecast, AIC, etc) into the database. Then, I can test whatever I want without further heavy lifting.
The volatility seems to be leaking quickly out of the stock market, and it seems to be back to its pre-dominantly bull-mode, which has been going on for a while now. So time to go long and wait for the next opportunity for more trading?
At the beginning of October, this strategy went heavily into treasuries (TLT), to the tune of 70%. The rest was SPY. With all the turbulence in October, this proved to be a good setup – yielding about 2.3% for the month.
For November, the strategy allocations deviate a little bit from the original strategy (which implementation was posted originally on the Systematic Investor Blog).
Time to stay out of the market for a bit, at least according to my system. With all the developments of late – I don’t blame it.:)
The last long position was quite painful, basically I held it throughout the correction, and I flipped it today (systematically) still at a loss (although a minor one), despite the massive recovery of late. Now let’s see how the short fares.:)
About a year ago, I moved my trading predominantly to futures. It has been a rich and beneficial learning experience, so I decided to share it in this post.
Was busy at the beginning of September and didn’t post the updates for that month. However, the allocations were pretty close to August’s. The performance for September was pretty bad – a loss of 3%, which sent us at a negative 1% for the year.
It seems that a correction might be starting, and the strategy (both the original and my modified version) is acting accordingly, allocating 71% to TLT (treasuries) and the rest to SPY (S&P 500).
This is the next post in the DVI indicator series. After the first two (here and here) analyzed in details the post-entry returns and the entry power of this indicator, it’s time to take a look at the trading performance.
Was short for a single day, and the system said to flip to long at the close. The position got cancelled out (I am out of the S&P 500), since another system of mine wanted to go short the same instrument. Go figure it …
Time to stay out of the market for a bit. This last short position went ugly – lost about 1.7% on it.