The conclusions from moral certainties are obtained like other conclusions, by induction. The induction from moral facts is like the induction from physical facts, with this difference--that the conclusions from moral facts are probabilities, like the facts on which they are founded. Whatever has physical certainty in its favour is considered demonstrable, and when sufficient probable evidence is adduced in favour of a proposition, it is considered to be fairly proved. Some persons, biased by the strictness of mathematical proof, insist upon the same accuracy in moral investigations. I have elsewhere pointed out the juvenility and infatuation of this error. Insist upon demonstration where the nature of the questions admits it. Less should not, in such case, suffice. Accept probability where probability is the sole evidence attainable. Never ask more than reason can grant. We must admit gradations of validity. What we are conscious of, we _know_. All we receive on testimony, we _believe_. Physical certainty is _knowledge_: moral certainty, _belief_. Hume remarks, in his 'Essay on Probabilities,' that 'Mr. Locke divides all arguments into demonstrative and probable. In this view, we must say, that it is only probable all men must die, or that the sun will rise to-morrow. But to conform our language more to common us, we ought to divide arguments into _demonstrations, proofs, and probabilities_. By proofs, meaning such arguments from experience as leave no room for doubt or opposition.'* * Hume's Essays, vol. 2, p.59. Conjecture is probable truth. Some subjects only furnish a sufficient number of facts to make them probable in the lowest degree--not to decide them as positively true. The propositions expressing results pertaining to such subjects are called conjectures. A conjecture founded on no fact or upon too few to make it likely, is called a vagary. It will be seen that probability is a thing of degree. A probability may vary in weight from a moral certainty, where it ranks next to a physical certainty, down to a conjecture, and descend lower in likelihood till it is lost in conjecture. Lord Kames remarks, in his preface to his 'Sketches'--'Most of the subjects handled in the following sheets, admit but of probable reasoning: and, with respect to such reasoning, it is often difficult to say, what degree of conviction they ought to produce. It is easy to form plausible arguments; but to form such as can stand the test of time, is not always easy. I could amuse the reader with numerous examples of conjectural arguments, which, fair at a distant view, vanish like a cloud on a near approach'. Did all authors so judiciously apprise their readers of the probable logical value of their speculations, fewer would be misled than now.