the presence and absence of the sun succeed each other, and if this
alternation were to cease, we might have either day or night unfollowed
by one another. There are thus two kinds of uniformities of succession,
the one unconditional, the other conditional on the first: laws of
causation, and other successions dependent on those laws. All ultimate
laws are laws of causation, and the only universal law beyond the pale
of mathematics is the law of universal causation, namely, that every
phaenomenon has a phaenomenal cause; has some phaenomenon other than
itself, or some combination of phaenomena, on which it is invariably and
unconditionally consequent. It is on the universality of this law that
the possibility rests of establishing a canon of Induction. A general
proposition inductively obtained is only then proved to be true, when
the instances on which it rests are such that if they have been
correctly observed, the falsity of the generalization would be
inconsistent with the constancy of causation; with the universality of
the fact that the phaenomena of nature take place according to
invariable laws of succession.[9] It is probable, therefore, that M.
Comte's determined abstinence from the word and the idea of Cause, had
much to do with his inability to conceive an Inductive Logic, by
diverting his attention from the only basis upon which it could be
founded.

We are afraid it must also be said, though shown only by slight
indications in his fundamental work, and coming out in full evidence
only in his later writings--that M. Comte, at bottom, was not so
solicitous about completeness of proof as becomes a positive
philosopher, and that the unimpeachable objectivity, as he would have
called it, of a conception--its exact correspondence to the realities of
outward fact--was not, with him, an indispensable condition of adopting
it, if it was subjectively useful, by affording facilities to the mind