Jump to ContentJump to Main Navigation
Names and Naming Patterns in England
                        1538–1700$

Scott Smith-Bannister

Print publication date: 1997

Print ISBN-13: 9780198206637

Published to Oxford Scholarship Online: October 2011

DOI: 10.1093/acprof:oso/9780198206637.001.0001

Show Summary Details
Page of

PRINTED FROM OXFORD SCHOLARSHIP ONLINE (www.oxfordscholarship.com). (c) Copyright Oxford University Press, 2017. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a monograph in OSO for personal use (for details see http://www.oxfordscholarship.com/page/privacy-policy). Subscriber: null; date: 27 February 2017

Appendix B: The Measurement of the Degree of Association between Two Lists of Personal Names: An Adaptation of Spearman’s Rank-Order Correlation

Appendix B: The Measurement of the Degree of Association between Two Lists of Personal Names: An Adaptation of Spearman’s Rank-Order Correlation

Source:
Names and Naming Patterns in England 1538–1700
Publisher:
Oxford University Press

THE chief problem involved in using Spearman’s rank-order correlation to measure the association between two lists of names is that the names on two distinct lists need not entirely coincide; one or more names may be different on each of the lists. This is, in itself, evidence of a degree of differentiation between the names used by, for example, two different social groups. To counteract the difficulty posed by having two lists of different names it has been necessary to adapt Spearman’s test. Throughout this book, in the instances in which this technique has been used, a name that is absent from the list of names with which it is being compared has been allotted a value equal to n or the number of names on the list of names in the equation:

Appendix B: The Measurement of the Degree of
                            Association between Two Lists of Personal Names: An Adaptation of
                            Spearman’s Rank-Order Correlation

where n is the number of names in a list and d is the difference between the ranking of a name in two lists.

This modification embodies the principal tenets implicit in the use of Spearman’s correlation. A name ranked, say, ninth in one list of ten names but absent from the list with which it was being compared would be given a rank of ten in the (p.191) second list. Such a decision would, when the calculation of the correlation was made, emphasize that the degree of difference between the use of this particular name, perhaps by the members of two different social groups, was limited, given that the name was not especially common as a name for a member of either social group. In contrast, should a name be a highly popular choice as a name for the members of one social group but absent from among the list of the more common names of the second group, assigning a value equivalent to the number of names in the list would emphasize the degree of difference between the two lists of names.

In keeping with the numerical limits of Spearman’s correlation, ail the values for the degree of association between two lists of names fall between +1 and –1.