Definition Bias
A bias or a distortion results from an error of data collection that leads to erroneous results in an investigation. There are different types of biases/distortions: systematic and random. Systematic biases/distortions can occur in the sample selection phase. This is referred to as selection bias. Trying to figure out the most popular basketball team in the U.S. by asking only people in L.A. is likely to produce a highly distorted result. Another form of systematic bias/distortion is social desirability bias. This occurs when survey respondents select socially acceptable responses that do not reflect their actual opinions. See also the effect of social desirability. Random biases/distortions are defined as biases/distortions that cannot be traced to a causal relationship.
Please note that the definitions in our statistics encyclopedia are simplified explanations of terms. Our goal is to make the definitions accessible for a broad audience; thus it is possible that some definitions do not adhere entirely to scientific standards.