Survivorship Bias

Survivorship Bias

Survivorship bias is a logical error that focuses on things that *succeeded* in a particular process, overlooking those that did *not*. This leads to distorted conclusions because the failures, which often hold critical information, are not considered. It's a pervasive issue in many fields, from finance and investing to medicine, history, and even everyday life. Understanding survivorship bias is crucial for making informed decisions and avoiding flawed reasoning. This article will delve deep into the concept, its various manifestations, examples, and how to mitigate its effects, especially within the context of Technical Analysis and Trading Strategies.

What is Survivorship Bias?

At its core, survivorship bias arises when we only observe entities that have "survived" some selection process, ignoring those that did not. This creates a skewed sample, leading to an overly optimistic or inaccurate assessment of the overall situation. The key is the *invisibility* of the failures. We don't hear about the businesses that went bankrupt, the products that flopped, the experiments that yielded negative results, or the investments that lost money – because they are no longer around to report their outcomes.

Imagine a shooting range where targets riddled with bullet holes are analyzed to improve shooting accuracy. If only the targets with many hits are examined, the analysis will be flawed. The targets that were quickly destroyed with a single, well-placed shot are missing, and their information (the areas *easily* hit) is lost. This provides a biased view of where shooters are actually aiming and which areas are most vulnerable.

How Survivorship Bias Manifests

Survivorship bias appears in several forms, often subtly influencing our perceptions. Here are some key manifestations:

Historical Data Bias: This is particularly prevalent in finance. Consider a fund performance database. Funds that have liquidated due to poor performance are often removed from the database. This leaves only the surviving funds, creating the illusion that the average fund performance is higher than it actually is. Investors relying on this data may overestimate their potential returns. This directly impacts the evaluation of Moving Averages and other long-term performance metrics.
Product/Business Success Bias: We tend to focus on the successful products and businesses, attributing their success to brilliant strategies, innovative ideas, or exceptional leadership. We rarely analyze the countless ventures that failed despite similar efforts. This can lead to a misunderstanding of the factors that truly drive success and a failure to learn from mistakes. Analyzing Candlestick Patterns on the stock charts of successful companies doesn't reveal the numerous companies that *tried* the same strategies and failed.
Medical Treatment Bias: In medicine, this can occur when evaluating the effectiveness of a treatment. If a treatment is only given to patients who are likely to respond well (e.g., those with mild symptoms), the apparent success rate will be inflated. Patients who were too ill to receive the treatment, or who didn't respond, are excluded from the analysis. This is why rigorous Double-Blind Studies are vital, attempting to address this bias.
Military Analysis Bias: During World War II, the Center for Naval Analyses studied battle damage to returning aircraft. They noted that certain areas of the planes were consistently riddled with bullet holes. Initially, they proposed reinforcing those areas. However, statistician Abraham Wald pointed out that they were only seeing the planes that *returned*. The areas *without* bullet holes were the critical ones – those were the areas where a hit meant the plane didn't survive to be analyzed. Reinforcing those areas was the correct course of action. This is a classic example of recognizing what you *don't* see.
Media Reporting Bias: The media often focuses on success stories, as they are more appealing and generate more interest. This creates a distorted view of reality, where failure is underreported and success is overemphasized. Looking at Bollinger Bands and applying them to news sentiment can be misleading if the news itself is biased towards positive outcomes.

Survivorship Bias in Finance and Investing

The financial world is particularly vulnerable to survivorship bias. Here's a detailed examination of its impact:

Mutual Fund Performance: The most common example. As mentioned earlier, databases often exclude funds that have been liquidated or merged. This leads to an overestimation of average fund returns. Investors may choose funds based on this biased data, expecting returns that are unlikely to be achieved. Sharpe Ratio calculations are also affected, appearing higher than they truly are.
Hedge Fund Performance: Hedge funds are even more susceptible. They often have shorter lifespans and a higher failure rate than mutual funds. Many hedge funds that perform poorly simply shut down, disappearing from performance databases. This creates a highly skewed picture of the hedge fund industry. Analyzing Fibonacci Retracements based on the performance of surviving hedge funds can be misleading.
Backtesting Trading Strategies: When backtesting a Trading Strategy, it's crucial to use a complete dataset that includes all historical data, including periods when the strategy would have failed. If the dataset only includes periods of success, the backtest results will be overly optimistic. Using a limited dataset can lead to overconfidence and poor trading decisions. This also applies to testing Elliott Wave Theory.
Index Construction: Stock market indices, such as the S&P 500, are not static. Companies are added and removed over time. Companies that have gone bankrupt or performed poorly are removed from the index. This creates a survivorship bias, as the index only reflects the performance of successful companies. Over the long term, this bias can significantly inflate the apparent returns of the index. Looking at Relative Strength Index (RSI) trends within the S&P 500 doesn't account for the companies that were *removed* from the index.
Venture Capital & Private Equity: The success stories of venture-backed startups often overshadow the vast number of failures. Venture capital funds typically invest in a portfolio of companies, expecting that a few big winners will offset the losses from many failures. Focusing solely on the successful exits creates a distorted view of the industry's overall performance. Analyzing MACD crossovers in the stock prices of successful startups ignores the countless failed ventures.
Quantitative Trading: Even quantitative trading strategies, which rely on mathematical models and algorithms, can be affected by survivorship bias. If the models are trained on historical data that is biased towards successful outcomes, they may not perform well in real-world trading. Strategies based on Ichimoku Cloud signals need to be tested on comprehensive datasets.

Mitigating Survivorship Bias

While it's impossible to eliminate survivorship bias completely, several steps can be taken to mitigate its effects:

Use Complete Datasets: This is the most important step. In finance, use databases that include both surviving and non-surviving funds or companies. Look for databases specifically designed to address survivorship bias. Ensure your backtesting datasets are comprehensive and include periods of both success and failure.
Look for "Dead Data": Actively seek out information about failures. Research companies that went bankrupt, funds that liquidated, and experiments that yielded negative results.
Consider the Selection Process: Understand how the sample you are observing was selected. What criteria were used to include or exclude entities? Are there any biases inherent in the selection process?
Be Skeptical of Success Stories: Don't automatically assume that success is due to skill or brilliance. Consider the role of luck and other factors. Question the narratives surrounding success stories.
Focus on Probabilities, Not Individual Cases: Instead of focusing on individual success stories, consider the overall probabilities of success and failure. What is the typical failure rate in the industry?
Apply Critical Thinking: Constantly question your assumptions and look for evidence that contradicts your beliefs. Be aware of your own biases and how they might be influencing your judgment.
Stress Test Your Strategies: When backtesting or evaluating trading strategies, subject them to rigorous stress tests. Simulate various market conditions, including periods of high volatility and economic downturns. Ensure the strategy can withstand adverse conditions. Consider Monte Carlo Simulation techniques.
Understand the Limitations of Historical Data: Recognize that historical data is not always a reliable predictor of future performance. Market conditions change over time, and strategies that worked in the past may not work in the future.
Diversify Your Investments: Diversification can help to mitigate the impact of survivorship bias by spreading your risk across a wider range of assets. Portfolio Rebalancing is a related concept.
Utilize Robust Statistical Methods: Employ statistical techniques that account for missing data and selection bias.

Tools and Resources

Several resources can help you address survivorship bias in your analysis:

Morningstar: Offers fund data that attempts to account for survivorship bias.
CRSP (Center for Research in Security Prices): Provides a comprehensive database of historical stock market data.
HFR (Hedge Fund Research): Offers data on the hedge fund industry, including information on fund closures.
Academic Research Papers: Search for research papers on survivorship bias in finance and other fields. Google Scholar is a good starting point.
Backtesting Platforms with Historical Data: Platforms like TradingView, MetaTrader, and NinjaTrader offer backtesting capabilities with access to historical data. Ensure you understand the data source and its limitations.
Financial News and Analysis Websites: Websites like Bloomberg, Reuters, and the Wall Street Journal provide financial news and analysis, which can help you identify potential cases of survivorship bias. Consider Volume Price Trend (VPT) analysis alongside news events.

By understanding survivorship bias and taking steps to mitigate its effects, you can make more informed decisions and avoid the pitfalls of flawed reasoning. It's a critical concept for anyone involved in investing, finance, or any field where success is often highlighted and failure is hidden. Remember to always consider the unseen and question the narratives surrounding success. Employing concepts like Donchian Channels and Average True Range (ATR) can provide a more objective view of market behavior, reducing reliance on biased success stories.

Start Trading Now

Sign up at IQ Option (Minimum deposit $10) Open an account at Pocket Option (Minimum deposit $5)

Join Our Community

Subscribe to our Telegram channel @strategybin to receive: ✓ Daily trading signals ✓ Exclusive strategy analysis ✓ Market trend alerts ✓ Educational materials for beginners