Probability & Statistics Codexery

Observational study

Last updated

In epidemiology, social sciences, psychology, and statistics, an observational study reaches conclusions without manipulating the independent variable, a necessity arising from ethical or practical constraints.[1] Unlike randomized controlled trials, where subjects are randomly allocated to treated or control groups, an observational study involves a researcher who does not assign subjects to those groups.[1]

Key facts and history

A randomized experiment would violate ethical standards if it required assigning subjects to a potentially harmful treatment.[2] For example, investigating a causal link between induced abortion and breast cancer would require randomly assigning pregnant women to receive abortions, which violates ethical principles.[2] The researcher may also lack control over the situation, such as when a community decides its own smoking ban.[2] A randomized experiment may be impractical for studying a very rare side effect, as the subject pool may be too small.[2]

Observational studies can provide information on "real world" use, though they cannot prove cause-and-effect relationships about safety or effectiveness.[3] Multivariate statistical techniques, such as matching methods, allow approximation of experimental control by accounting for observed factors.[4] When investigating the public health effects of a smoking ban, an observational study begins with a treatment group composed of communities that have already implemented such a ban.[2]

What the research sources say

The "Introductory Econometrics" chapter notes that economists generally have data from an observational study rather than a controlled experiment.[5] A 2008 edition of "A Dictionary of Epidemiology" defines the observational study concept and was published by Oxford University Press.[6][1]

References

  1. Wikipedia, "Observational study" (CC BY-SA 4.0), which cites: "Observational study"; "A Dictionary of Epidemiology", Oxford University Press, 2008 (we also read that source) en.wikipedia.org
  2. Wikipedia, "Observational study" (CC BY-SA 4.0), which cites: "A literature review on the representativeness of randomized controlled trial samples and implications for the external validity of trial results", Trials, November 2015 (original not read by us) en.wikipedia.org
  3. Wikipedia, "Observational study" (CC BY-SA 4.0), which cites: "Although observational studies cannot provide definitive evidence of safety, efficacy, or effectiveness, they can: 1) provide information on "real world" use a (original not read by us) en.wikipedia.org
  4. Wikipedia, "Observational study" (CC BY-SA 4.0), which cites: Rosenbaum, Paul R. 2009. Design of Observational Studies. New York: Springer.; King, "Why Propensity Scores Should Not Be Used for Matching", Political Analysis, 2019-05-07, p. 435–454 (original not read by us) en.wikipedia.org
  5. "Introductory Econometrics Chapter 18: Omitted Variable Bias", www3.wabash.edu. facts only, no text reused. www3.wabash.edu
  6. Open Library record, ISBN 9780195314496 ("A dictionary of epidemiology."). CC0 (metadata); book content not read. openlibrary.org

Each numbered sentence above was checked against the source it cites before publication. Sentences citing Wikipedia adapt text from the English Wikipedia article Observational study (contributors), used under CC BY-SA 4.0; this entry is available under the same licence. Other sources were used for facts only; no text or images are copied from them.

More in Probability & Statistics

Sources

Compiled from Wikipedia and the sources listed below. Text from Wikipedia is available under CC BY-SA 4.0; this entry is adapted from it.

Spotted an error? Know more?

Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced

Comments

Loading…
Open in the interactive codex →