Hostname: page-component-84b7d79bbc-c654p Total loading time: 0 Render date: 2024-07-29T12:51:41.815Z Has data issue: false hasContentIssue false
  • English
  • Français

The Graphic Method of Adjusting Mortality Tables. — A description of its objects, and its advantages as compared with other methods, and an application of it to obtain a Graduated Mortality Table from Mr. A. J. Finlaison's Observations on the Mortality of the Female Government Annuitants, 4 years and upwards after purchase

Published online by Cambridge University Press:  18 August 2016

T. B. Sprague
T. B. Sprague
Affiliation:
Institute of Actuaries
Get access Rights & Permissions [Opens in a new window]

Extract

I have on various occasions stated that, in my opinion, the graphic method is the best one to employ in graduating a mortality table; and I have more than once had it in contemplation to explain fully the grounds for this opinion, describing the advantages of the graphic method, and the objections I see to the use of some other methods which are commonly employed. In order to do this satisfactorily, it is clearly essential to give a graduation of some mortality observations; and my attention having been again drawn to the subject by reading Mr. Higham's brief, but extremely interesting and suggestive paper, On the Graduation of Mortality Tables (J.I.A. xxv, 15), in which he speaks unfavourably of the graphic method, I think that an examination of his reasoning and results will furnish me with the most suitable opportunity I could have for stating my views on the whole subject.

Type
Research Article
Information
Journal of the Institute of Actuaries , Volume 26 , Issue 2 , October 1886 , pp. 77 - 120
Copyright
Copyright © Institute and Faculty of Actuaries 1887

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

page 79 note * This is Diagram No. 1 of the present paper.

page 91 note * Messrs. Layton, the publishers of this Journal, have had paper of this kind specially prepared, which I find to be very suitable. Although the ruling is slightly inaccurate in parts, as the lines are not all at precisely the same distance, I do not think this is likely to lead to any inconvenience, as I find the error to be not greater than that which I am myself liable to make in estimating fractions of an interval, and errors arising from both these causes are readily corrected by inspection.

page 100 note * In this calculation the probabilities here set down are not used, but those given by Mr. Finlaison to 5 decimal places.

page 115 note * Essay on Probabilities, p. 162.