… is from page 155 of Fritz Machlup ‘s 1954 essay “The Problem of Verification in Economics ,” as it is reprinted in the 1978 collection of some of his essays on scientific method, Methodology of Economics and Other Social Sciences  (original emphases):
Where the economist’s prediction is conditional, that is, based upon specified conditions, but where it is not possible to check the fulfillment of all the conditions stipulated, the underlying theory cannot be disconfirmed whatever the outcome observed….
This does not mean complete frustration of all attempts to verify economic theories. But it does mean that the tests of most of our theories will be more nearly of the character of illustrations than of verifications of the kind possible in relation with repeatable controlled experiments or with recurring fully-identified situations. And this implies that our tests cannot be convincing enough to compel acceptance, even when a majority of reasonable men in the field should be prepared to accept them as conclusive, and to approve the theories so tested as “not disconfirmed,” that is, as “O.K.”
As Hayek noted, economics and other social sciences deal with complex phenomena . This reality means that the real-world phenomena studied by economists and other social scientists are influenced by numerous variables that cannot be controlled by the observing scientist, and that are always changing – and changing in ways that are often unobservable even in principle (and, even more often, unobservable in practice). For this reason alone, sound reasoning – reasoning that is coherent, logical, grounded on plausible foundations, and that gives to those who follow it a genuine sense of being able to better understand observed reality – is especially important.