Survivorship bias


Also found in: Wikipedia.

Survivorship bias

Usually pertaining to fund manager or individual investor performance. Suppose we examined the performance over the last ten years of a group of managers that exist today. This performance is biased upwards because we are only considering those that survived for 10 years. That is, some dropped out because of poor performance. Hence, in evaluating performance, one has to be careful to include both the current and the managers that dropped out of the sample due to poor performance.

Survivorship Bias

In finance, the tendency to exclude failed companies or managers from performance evaluations or studies simply because they do not exist. Survivorship bias can result in skewed findings in a study and lead a casual reader to believe that a study shows a rosier picture than it really does. Mutual funds, especially smaller ones, are especially susceptible to survivorship bias. At any given time, 90% of mutual funds will claim to be in the top 25% of performers. Technically, they are correct, but only because the other 75% have closed or merged. Manager universe comparisons have also been criticized for exhibiting signs of survivorship bias. It is also known as survivor bias.
References in periodicals archive ?
The SS&C GlobeOp Hedge Fund Performance Index is transparent, consistent in data processing, and free from selection or survivorship bias.
However, the study concludes that this result is probably a reflection of survivorship bias, since it finds little evidence of performance persistence from year to year among these managers, and evidence to suggest that the risk-adjusted performance of these experienced managers actually declined over the ten year study sample period, that is, a decline in performance as experience increases
Admittedly, all of these proxies of long-short equity performance have their problems, including survivorship bias, self-selection bias and inclusion of funds that aren't truly representative of the category.
equity mutual funds from 1990 through 2012, based largely on information from the CRSP Survivorship Bias Free Mutual Fund database that tracks fund returns, dividend and capital gains distributions, total net assets, fees, flows, and investment objectives.
The tests were carefully constructed to be free of both look-ahead and survivorship bias.
Survivorship bias in marketing material is often high.
Investigators included living and deceased patients to avoid survivorship bias.
Malkiel (1995) presents two important findings for a sample of equity mutual funds examined from 1971-1991: in the aggregate, funds underperformed the market, with the S&P 500 as the benchmark and significant survivorship bias exists, which may be leading to erroneous finds of performance persistence.
Besides using more robust performance evaluation techniques (conditional multi-factor models) to analyse overall performance as well as timing and selectivity abilities of fund managers, the analysis is complemented with robustness tests to check for possible effects that may arise from survivorship bias, management fees and spurious regressions.
Ackermann, McEnally, and Ravenscraft (1999) pointed out that hedge fund databases have survivorship bias, liquidation bias, backfill bias, and selection bias.
This discussion touches on the issues of survivorship bias and persistence in performance, among other topics.
Survivor Bias Free Database -- data is available on inactive companies allowing researchers to remove survivorship bias from their research.