An error caused by something in the experimental or theoretical setup, typically an assumption that proves incorrect or invalid.

That part of the inaccuracy of a measuring instrument, or statistical estimate of a parameter, that is due to a single cause or small number of causes having the same sign, and hence, in principle, is correctable; a bias or constant offset from the true value. In the absence of random errors, the true value is equal to the instrumental reading or statistical mean estimate minus the systematic error.

A wrong result due to bias. Sources of variation will distort the result in one direction.

the consistent underestimation or overestimation of a true value, due to poor sampling technique.

mean that would result from an infinite number of measurements of the same measurand carried out under repeatability conditions minus a true value of the measurand.

A consistent score component (often observed indirectly) not related to the test performance. Related to construct-irrelevance and construct underrepresentation. American Educational Research Association, American Psychological Association, & National Council on Measurement in Education. (1999). Standards for educational and psychological testing. Washington, DC: American Educational Research Association, p. 183.