Sources of Bias in Research

OT Dude Academy’s Free NBCOT® Exam Prep Course Research Methods and Psychometrics Sources of Bias in Research

Can you describe the following sources of bias without looking it up? Answers below.

  • Recall bias
  • Selection bias
  • Observation bias
  • Confirmation bias
  • Publishing bias
  • Volunteer bias
  • Admission bias
  • Survivor bias
  • Data analysis bias
Recall bias
  • When participants rely on their memory and report certain experiences more readily than others in the past.
Selection bias
  • Sampling that under- or over-represents the population. This can be avoided with random sampling.
Observer bias
  • When participants are aware they are being observed and alter the way they behave or respond; Hawthorne effect.
Confirmation bias
  • During data interpretation, researchers may look for information that confirms their ideas or hypotheses.
Publishing bias
  • Studies with negative findings are less likely to be submitted or published by journals because they are often perceived to be less interesting for readers.
Volunteer bias
  • Participants who volunteer to participate are different than the general population. An example is recruiting only healthy participants to the study.
Admission bias
  • The chance of being recruited in a study is higher for certain groups. An example is recruiting participants only from hospital settings
Survivor bias
  • A study favors certain participants who make it past a certain obstacle or point in time and ignores those who did not. An example is participants who may die before the study ends.
Data analysis bias
  • A researcher can introduce bias in data analysis by analyzing data in a way that gives preference to the conclusions in favor of the research hypothesis. There are various opportunities by which bias can be introduced during data analysis, such as by fabricating, abusing or manipulating the data.

    • reporting non-existing data from experiments that were never done (data fabrication);

    • eliminating data that do not support your hypothesis (outliers, or even whole subgroups);

    • using inappropriate statistical tests to test your data;

    • performing multiple testing (“fishing for P”) by pair-wise comparisons (), testing multiple endpoints and performing secondary or subgroup analyses, which were not part of the original plan in order “to find” statistically significant difference regardless to hypothesis.

References

Medical Research Council and Chief Scientist Office Social and Public Health Sciences Unit. (n.d.). Common Sources of Bias. Retrieved from https://www.understandinghealthresearch.org/useful-information/common-sources-of-bias-2

Simundić A. M. (2013). Bias in research. Biochemia medica, 23(1), 12–15. https://doi.org/10.11613/bm.2013.003

Previous Lesson
Back to Topic
Next Lesson