Stop-losses on Stock Positions in Depth

Do stop-losses usefully mitigate downside risk in realistic scenarios? In their November 2015 paper entitled “Stop-Loss Strategies with Serial Correlation, Regime Switching, and Transactions Costs”, Andrew Lo and Alexander Remorov analyze the value of stop-losses when asset returns are autocorrelated (trending), regime switching (bull and bear) and subject to trading costs. They consider daily and 10-day measurement intervals, with respective stop-loss ranges of 0% to -6% and 0% to -14%. If at any daily close the cumulative return on the risky asset over the measurement interval falls below a specified threshold, they immediately switch to the risk-free asset (U.S. Treasury bills). They consider two ways to execute stop-loss signals: (1) assume it is possible to estimate signals just before the close and sell at the same close; or, (2) use a signal from the prior close to trigger a market-on-close sell order the next day (delayed execution). They re-enter the risky asset when its cumulative return over a specified interval exceeds a specified threshold. They employ both simulations and empirical tests. For simulations, they estimate trading cost as 0.2%, the average half bid-ask spread of all sampled stocks during 2013-2014. For empirical tests, they use actual half bid-ask spreads as available and estimates otherwise. Empirical findings are most relevant to short-term traders who employ tight stop-losses. Using daily returns and bid-ask spreads as available for a broad sample of U.S. common stocks during 1964 through 2014, they find that:

• From simulations:
  • The performance of a tight stop-loss relates about linearly to risky asset return volatility
    and autocorrelation. When these metrics are high enough, stop-losses improve risk-adjusted returns compared to buy-and-hold.
  • Wide stop-losses are attractive compared to buy-and-hold for assets that switch between bull and bear regimes if (1) volatility is low (high) in the bull (bear) regime and (2) regime switches are infrequent. Attractiveness comes from downside volatility reduction.
  • The 10-day stop-loss signal consistently increases return skewness and reduces maximum drawdown.
• From empirical tests:
  • Stock return autocorrelations tend to be positive over the first half of the sample but significantly negative over the second half, so the past two decades are unfavorable for tight stop-losses.
  • Very large bid-ask spreads commonly accompany stock price crashes, working against stop-loss net profitability.
  • Due mostly to high trading costs, tight stop-losses significantly lower returns compared to buy-and-hold. Wide stop-losses work better but still have lower raw returns than buy-and-hold.
  • Based on risk-adjusted performance, wide 10-day stop-losses generally perform about as well as buy-and-hold due to downside volatility reduction.
  • The delayed stop-loss scheme works marginally better than immediate execution for most stop-loss settings and significantly better for tight stop-losses because of return reversion during the one-day delay.
• Quick re-entry is usually beneficial for tight stop-losses.
• The level of the risk-free rate has a significant impact on the effectiveness of stop-losses.

In summary, evidence indicates that actual behavior of individual U.S. stocks in recent decades is not conducive to use of tight stop-losses, but wide stop losses applied over 10-day intervals may be attractive for downside risk reduction.

Cautions regarding findings include:

• Estimated trading costs ignore broker fees and impact of trading and may therefore be materially low for some traders.
• Testing many different stop-loss/re-entry settings on the same data introduces snooping bias, such that the best-performing settings tend to be lucky and overstate expected performance.
• The assumption of immediate switching between stocks and the risk-free rate, ignoring settlement delays, may be material to findings, especially for tight stops (frequent trading).

See also “Do Stop Losses Work?”, “Using Trailing Stop Losses to Reduce Risk”, “Higher Measurement Frequency and Stop-losses for Trend Followers?”, “Stop-losses to Avoid Stock Momentum Crashes?” and “Add Stop-loss to Asset Class Momentum Strategy?”.