Realized volatility measures are imperfect tools to predict risk.
Low r-squared highlights idiosyncratic risk. Will check for time dependence.
Durbin-Watson indicates no significant autocorrelation. More here.
You're not supposed to time the market, I know.
Total return3 vs the S&P and a 40/20/40 blend4, and portfolio allocation5
| year | TR | S&P 500 | 40/20/40 | nonUS/eq/bd/cs |
| 1999 | 12.3% | 21.0% | 13.9% | 15/14/18/54 |
| 2000 | 9.6% | -9.1% | -1.5% | 41/23/31/4 |
| 2001 | 0.6% | -11.9% | -5.0% | 41/21/32/5 |
| 2002 | 3.0% | -22.1% | -6.0% | 40/23/30/7 |
| 2003 | 36.3% | 28.7% | 25.9% | 43/20/24/13 |
| 99-03 | 11.7% | -0.6% | 4.7% | 39/21/28/12 |
Diversification is the only free lunch.
Tracking errors and information ratios6
| year | TES&P | IRS&P | TEblend | IRblend |
| 1999 | 11% | -0.8 | 6% | -0.3 |
| 2000 | 21% | 0.9 | 10% | 1.1 |
| 2001 | 13% | 1.0 | 9% | 0.6 |
| 2002 | 18% | 1.4 | 7% | 1.2 |
| 2003 | 11% | 0.7 | 9% | 1.1 |
| 99-03 | 15% | 0.8 | 8% | 0.8 |
Lots of relative risk versus indexes.
Average risk premiums and Sharpe ratios7
| year | RP | RPS&P | RPblend | SR | SRS&P | SRblend |
| 1999 | 0.6% | 1.3% | 0.7% | 0.2 | 0.3 | 0.3 |
| 2000 | 0.4% | -1.2% | -0.6% | 0.1 | -0.2 | -0.2 |
| 2001 | -0.1% | -1.2% | -0.7% | -0.0 | -0.2 | -0.2 |
| 2002 | 0.2% | -2.0% | -0.6% | 0.0 | -0.3 | -0.2 |
| 2003 | 2.6% | 2.1% | 1.9% | 0.8 | 0.6 | 0.7 |
| 99-03 | 0.7% | -0.2% | 0.2% | 0.18 | -0.04 | 0.05 |
Risk premiums are unannualized arithmetic monthly averages.
Total return3, correlation with the index and average net long8
| year | TR | SPX TR | corr | net long |
| 1999 | -5.3% | 21.0% | -0.1 | 12% |
| 2000 | 8.3% | -9.1% | -0.6 | 21% |
| 2001 | 15.1% | -11.9% | 0.3 | 26% |
| 2002 | -25.7% | -22.1% | 0.1 | 30% |
| 2003 | 35.3% | 28.7% | 0.3 | 36% |
| 99-03 | 3.5% | -0.6% | -0.1 | 25% |
With correlations this low, there is no point to running a regression.
Standard deviation, tracking error and information ratio6
| year | stdev | SPX stdev | TE | IR |
| 1999 | 25% | 13% | 29% | -0.9 |
| 2000 | 43% | 17% | 55% | 0.3 |
| 2001 | 16% | 20% | 21% | 1.3 |
| 2002 | 17% | 21% | 25% | -0.1 |
| 2003 | 17% | 11% | 17% | 0.4 |
| 99-03 | 26% | 17% | 32% | 0.1 |
High volatility, huge tracking errors. Not an enhanced-index portfolio.
Average risk premium and Sharpe ratio7
| year | RP | SPX RP | Sharpe | SPX Sharpe |
| 1999 | -0.6% | 1.3% | -0.1 | 0.3 |
| 2000 | 0.9% | -1.2% | 0.1 | -0.2 |
| 2001 | 1.0% | -1.2% | 0.2 | -0.2 |
| 2002 | -2.5% | -2.0% | -0.5 | -0.3 |
| 2003 | 2.6% | 2.1% | 0.5 | 0.6 |
| 99-03 | 0.3% | -0.2% | 0.04 | -0.04 |
Better to be lucky than good.
1This page is not a formal presentation or an advertisment of any kind. I am not an investment firm. I have no composite. This page is for illustrative purposes only and comes with no guarantees of any sort. I am missing balances for no-activity months in my trading account (March 2002 and February 2003). Otherwise, I endeavored to follow calculations standards and have tried to make "every reasonable effort to assure that [my] performance information is a fair, accurate, and complete presentation of [my] performance." That said, I very explicitly have not prepared or presented this information in compliance with the Performance Presentation Standards of the Association for Investment Management and Research (AIMR-PPS®), the U.S. and Canadian version of the Global Investment Performance Standards (GIPS®). AIMR has not been involved in the preparation or review of my performance calculation or presentation in any way.
In re the size and density of that footnote, better safe than sorry.
2 Growth of $100 represents the hypothetical return to $100 using monthly total returns of portfolios and indexes. Return vs volatility is annualized five-year total returns vs annualized five-year standard deviations of the returns. Regression shows an ordinary least-squares fit to monthly portfolio risk premium versus 40/20/40 blend index RP. Timing index represents each previous-month-end net long exposure times the current month's S&P 500 return. Market exposure shows the portfolio's net long position month-by-month.
3 Total return calculated using the hoary old modified Dietz method.
4 40/20/40 index blend represents a monthly total return blend of 40% GFD World Ex-US, 20% Russell 2000 and 40% Merrill Lynch Corporate/Government Bond indexes.
5 Allocation format is non-US equity/US equity/bonds/cash. Numbers may not add to 100 due to rounding. Exchange-traded funds and mutual funds are classified according to their mandates.
6 Tracking error (TE) is the standard deviation of monthly out-/underperformance versus a benchmark index. Information ratio (IR) is the out-/underperformance versus the index divided by the tracking error.
7 Risk premium (RP) is the simple arithmetic average of monthly total return in excess of monthly T-Bill return. Sharpe ratio (Sharpe) is this average risk premium divided by its standard deviation, the original [1966, 1975] version of Sharpe's differential ratio. Cf his updated 1994 paper in the Journal of Portfolio Management.
8 The net long calculation is squirrely. Rather than recalculate options deltas, I took a dollar in a call or a put to be fifty cents long or short, respectively. This is a poor approximation for all but at-the-money options.
