Some Additional Evidence on Survival Biases

Some Additional Evidence on Survival Biases I. Introduction A FREQUENT PROBLEM IN the analysis of f m ’ financial time series is the need to impose survivorship criteria and the difficulty of determining their effects. Survivorship criteria usually are imposed in order to obtain sufficient observations for estimation purposes. But realizations of financial time series are unlikely to be independent of whether fmsurvive. Thus, the requirement of a long series for estimation purposes could result in an unrepresentative set of firms’ series, and inferences concerning population characteristics could be biased. In our study [I] of the time series firms’ annual earnings, we required sample members to have twenty consecutive years of earnings data. This required all sample members to have survived for at least twenty years, which would have reduced the likelihood of firms with poor earnings performance entering the sample. An additional and more subtle bias arose because of the criteria imposed by Standard and Poor’s when they constructed the Compustat file, which we used in that study. Their sample was selected essentially on the grounds that firms were of interest to security analysts, who were the likely market for the file, at the time of its construction. The file was then constructed http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png The Journal of Finance Wiley

Some Additional Evidence on Survival Biases

The Journal of Finance, Volume 34 (1) – Mar 1, 1979

Loading next page...
 
/lp/wiley/some-additional-evidence-on-survival-biases-18nZc1WR85
Publisher
Wiley
Copyright
1979 The American Finance Association
ISSN
0022-1082
eISSN
1540-6261
DOI
10.1111/j.1540-6261.1979.tb02080.x
Publisher site
See Article on Publisher Site

Abstract

I. Introduction A FREQUENT PROBLEM IN the analysis of f m ’ financial time series is the need to impose survivorship criteria and the difficulty of determining their effects. Survivorship criteria usually are imposed in order to obtain sufficient observations for estimation purposes. But realizations of financial time series are unlikely to be independent of whether fmsurvive. Thus, the requirement of a long series for estimation purposes could result in an unrepresentative set of firms’ series, and inferences concerning population characteristics could be biased. In our study [I] of the time series firms’ annual earnings, we required sample members to have twenty consecutive years of earnings data. This required all sample members to have survived for at least twenty years, which would have reduced the likelihood of firms with poor earnings performance entering the sample. An additional and more subtle bias arose because of the criteria imposed by Standard and Poor’s when they constructed the Compustat file, which we used in that study. Their sample was selected essentially on the grounds that firms were of interest to security analysts, who were the likely market for the file, at the time of its construction. The file was then constructed

Journal

The Journal of FinanceWiley

Published: Mar 1, 1979

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create folders to
organize your research

Export folders, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off