Full Idea
A general proposition collected from particulars is often more certainly true than any one of the particular propositions from which, by an act of induction, it was inferred. It might be erroneous in any instance, but cannot be erroneous in all of them.
Gist of Idea
Inductive generalisation is more reliable than one of its instances; they can't all be wrong
Source
John Stuart Mill (System of Logic [1843], 4.1.2), quoted by Peter Lipton - Inference to the Best Explanation (2nd) 11 'The scientific'
Book Reference
Lipton,Peter: 'Inference to the Best Explanation (2nd ed)' [Routledge 2004], p.204
A Reaction
One anomaly can be ignored, but several can't, especially if the anomalies agree.