Statistical Learning Models :
Neural Net Daily Trend Identifier : UP [0.42 confidence : Low ]
Daily Short-Term Overreaction : UP [confidence : High]
Filtering Model (4-hour frequency):
Main Trend : UP
Momentum : UP [increasing]
Mean Reversion (4-trading hours frequency) :
4 periods accumulated return (16 hours) : 0.6%
percentile : 59%
9 periods Return (36 hours) : 1.3%
percentile : 68.2%
10 period Volatility (40 hours) : 7.8% annualized
percentile : 22%
Relative Volatility (10 per / 50 per)
percentile : 69%
Markov Regime Switching identifier ( daily close ):
Probability of a strong uptrend regime : 2.4
Probability of a weak uptrend regime : 29.5
Probability of a sideways / weak uptrend regime : 54.8
Probability of a downtrend / volatile regime : 13.3
SPY - VIX statistical relationship ( daily close ):
zone : uptrend
percentile : 45.2% [ normal ]
Wavelet Discontinuity Watch (daily close ) :
Risk of a correction / crash increasing.
High volatility regime pattern emerging.
Overall commentary for Jan/10/2011:
Neuralnet trend model still in uptrend zone, but confidence dropped to low levels.
Main trend up, with increasing momentum.
Volatility is now stable, but volatility trend is up.
MatLab´s Markov model updated the regime probabilities, downtrend regime increased for third consecutive day from 10.4% to 13.3%. The dangerous zone is around 20% . We will keep a close eye on it today. A major down day could trigger a snowball.
Wavelet model probability of a discontinuity is increasing, and beginning to show similarities with April 2010 highs.
Model suggested positioning did not change : small short with stops at SPY highs around 127.8.
Lacking enough Flying-Hours in Quantitative Thinking ? Then try Understanding Daily Reports first.