Editing Observational error (section)

==Science and experiments==
When either [[random variable|randomness]] or uncertainty modeled by [[probability theory]] is attributed to such errors, they are "errors" in the sense in which that term is used in [[statistics]]; see [[errors and residuals in statistics]].

[[File:Measurement distribution with systematic and random errors.svg|thumb|Distribution of measurements of known true value, with both constant systematic error and normally distributed random error.]]

Every time a measurement is repeated, slightly different results are obtained. The common [[statistical model]] used is that the error has two additive parts:<ref name=Heinrich-2007>{{Cite journal |last=Heinrich |first=Joel |last2=Lyons |first2=Louis |date=2007-11-01 |title=Systematic Errors |url=https://www.annualreviews.org/doi/10.1146/annurev.nucl.57.090506.123052 |journal=Annual Review of Nuclear and Particle Science |language=en |volume=57 |issue=1 |pages=145–169 |doi=10.1146/annurev.nucl.57.090506.123052 |issn=0163-8998}}</ref>
#'''Random error''' which may vary from observation to another.
#'''Systematic error''' which always occurs, with the same value, when we use the instrument in the same way and in the same case.
Some errors are not clearly random or systematic such as the uncertainty in the calibration of an instrument.<ref name=Heinrich-2007/>

Random errors or statistical errors in measurement lead to measurable values being inconsistent between repeated measurements of a [[time-invariant|constant]] attribute or [[physical quantity|quantity]] are taken. Random errors create [[measurement uncertainty]]. These errors are [[correlation (statistics)|uncorrelated]] between measurements. Repeated measurements will fall in a pattern and in a large set of such measurements a [[standard deviation]] can be calculated as a estimate of the amount of statistical error.<ref name=Heinrich-2007/>{{rp|147}}

Systematic errors are errors that are not determined by chance but are introduced by repeatable processes inherent to the [[system]].<ref>{{cite web|url=http://www.merriam-webster.com/dictionary/systematic%20error |title=Systematic error |website=Merriam-webster.com |access-date=2016-09-10}}</ref> Sources of systematic errors include errors in equipment calibration, uncertainty in correction terms applied during experimental analysis, errors due the use of approximate theoretical models.<ref name=Heinrich-2007/>{{rp|loc=supl}}
Systematic error is sometimes called '''statistical bias'''. It may often be reduced with standardized procedures. 

Part of the learning process in the various [[science]]s is learning how to use standard instruments and protocols so as to minimize systematic error.
Over a long period of time, systematic errors in science can be resolved and become a form of "negative knowledge": scientist build up an understanding of how to avoid specific kinds of systematic errors.<ref>{{Cite journal |last=Allchin |first=Douglas |date=March 2001 |title=Error Types |url=https://direct.mit.edu/posc/article/9/1/38-58/15089 |journal=Perspectives on Science |language=en |volume=9 |issue=1 |pages=38–58 |doi=10.1162/10636140152947786 |issn=1063-6145}}</ref>