Bias in Statistics > Central Tendency Bias
What is Central Tendency Bias?
Central tendency bias (sometimes called central tendency error) is a tendency for a rater to place most items in the middle of a rating scale. For example, on a 10 point scale, a manager might place most of his employees in the middle (4-7), with a few people getting high(8-10) or low(1-3) rated performances.
Avoiding Central Tendency Bias
Central tendency bias can be avoided by:
- Make questions clear. If the rater isn’t clear on what the question is asking for, they are more likely to answer in the middle (Mangione, 1995).
- Don’t require justification for higher ratings. Some employee performance scales require a manager to provide written justification for placing an employee higher on the scale. This has been shown to increase bias (Landy & Conte, 2009).
- Have raters rank items from highest to lowest. If no two items can have the same rank, this avoids the rater placing items in the middle.
- Leave out the center items. For example, on a satisfaction scale of 1 to 5, leave out the 3.
It’s also been suggested that a shortened rating scale (e.g. 1,2,3) can help limit this bias, but that would still open up the opportunity for the rater to mark most items a “2”.
Beginning-Ending List Bias
A similar bias is beginning-ending list bias (also called the serial position effect). Given a large number of choices, people who don’t read the entire list tend to pick items at the beginning or at the end of the list (Mangione, 1995). Even if they do real the while lists, people tend to remember the first or last choice they read and so are more likely to choose the first or last options.
Landy, F. & Conte, J. (2009). Work in the 21st Century: An Introduction to Industrial and Organizational Psychology. Wiley-Blackwell; 3 edition.
Mangione, T. (1995). Mail Surveys: Improving the Quality. Book 40 in Applied Social Research Methods. SAGE Publications, Inc; 1 edition.
If you prefer an online interactive environment to learn R and statistics, this free R Tutorial by Datacamp is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try this Statistics with R track.Comments are now closed for this post. Need to post a correction? Please post a comment on our Facebook page.