To many Dr. Stark’s conclusion may appear to be a natural and obvious sequitur from the evidence upon which it is founded. Admitting the facts—and I see no reason for doubting them—it may appear at first sight that we are bound to accept the conclusion that241 matrimony is favourable to longevity. Yet the consideration of a few parallel cases will suffice to show how small a foundation the figures I have quoted supply for such a conclusion. What would be thought, for example, of any of the following inferences?—Among hot-house plants there is observed a greater variety and brilliance of colour than among those which are kept in the open air; therefore the housing of plants conduces to the splendour of their colouring. Or again: The average height of Life Guardsmen is greater than that of the rest of the male population; therefore to be a Life Guardsman conduces to tallness of stature. Or to take an example still more closely illustrative of Dr. Stark’s reasoning: The average longevity of noblemen exceeds that of untitled persons; therefore to have a title is conducive to longevity; or borrowing his words, to remain without a title ‘is more destructive to life than the most unwholesome trades, or than residence in an unwholesome house or district, where there has never been the most distant attempt at sanitary improvement of any kind.’

  is absurd in each of the above instances, and we are able at once to show where the flaw in the reasoning lies. We know that splendid flowers are more commonly selected for housing, and that Life Guardsmen are chosen for their tallness, so that we are prevented from falling into the mistake of ascribing splendour of colour in the one instance, or tallness in the other, to the influence of causes which have nothing whatever to do with those attributes;242 nor is anyone likely to ascribe the longevity of our nobility to the possession of a title. Yet there is nothing in any one of the above inferences which is in reality more unsound than Dr. Stark’s inference from the mortality bills, when the latter are considered with due reference to the principles of interpretation which statisticians are bound to follow style Two considerations must have caused Scheer the gravest possible anxiety..

The fact is, that in dealing with statistics the utmost care is required in order that our inferences may not be pushed beyond the evidence afforded by our facts. In the present instance, we have simply to deal with the fact that the death-rate of unmarried men is higher than the death-rate of married men and widowers. From this fact we cannot reason as Dr. Stark has done to a simple conclusion. All that we can do is to show that one of three conclusions must be adopted:—Either matrimony is favourable (directly or indirectly) to longevity, in a degree sufficient wholly to account for the observed peculiarity; or a principle of selection—the effect of which is such as, on the whole, to fill the ranks of married men from among the healthier and stronger portion of the community—operates in a sufficient degree to account wholly for the observed death-rates; or lastly, the observed death-rates are due to the combination, in some unknown proportion, of the two causes just mentioned.