?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Technical+note%3A+Bias+and+the+quantification+of+stability&rft.creator=Turney%2C+Peter+D.&rft.subject=Artificial+Intelligence&rft.subject=Machine+Learning&rft.subject=Statistical+Models&rft.description=Research+on+bias+in+machine+learning+algorithms+has+generally+been+concerned+with+the%0Aimpact+of+bias+on+predictive+accuracy.+We+believe+that+there+are+other+factors+that+should%0Aalso+play+a+role+in+the+evaluation+of+bias.+One+such+factor+is+the+stability+of+the+algorithm%3B%0Ain+other+words%2C+the+repeatability+of+the+results.+If+we+obtain+two+sets+of+data+from+the+same%0Aphenomenon%2C+with+the+same+underlying+probability+distribution%2C+then+we+would+like+our%0Alearning+algorithm+to+induce+approximately+the+same+concepts+from+both+sets+of+data.+This%0Apaper+introduces+a+method+for+quantifying+stability%2C+based+on+a+measure+of+the+agreement%0Abetween+concepts.+We+also+discuss+the+relationships+among+stability%2C+predictive+accuracy%2C%0Aand+bias.&rft.publisher=Kluwer&rft.date=1995&rft.type=Journal+(Paginated)&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F1819%2F3%2FNRC-38313.pdf&rft.identifier=++Turney%2C+Peter+D.++(1995)+Technical+note%3A+Bias+and+the+quantification+of+stability.++%5BJournal+(Paginated)%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F1819%2F