Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Historical Sources: How People Counted. A Method for Estimating the Rounding of Numbers

Historical Sources: How People Counted. A Method for Estimating the Rounding of Numbers Any census — or other enumeration exercise — which yields numerical data (counts) may include data collected using a variety of unspecified counting practices, such as ‘rounding’ to the nearest multiples of a ‘base-unit’, e.g. 5 or 10 or a (half-) dozen, as well as ‘exact’ counts. In general, the greater the age of the data-source, the greater the probability that the recorded data represent ‘rounded’ estimates as opposed to ‘exact’ counts. Also, the greater the number and diversity of the persons involved in data-collection, the greater the probability of variation in counting practice. The presence of ‘rounded’ data in many historical sources produces uncertainty when historians — or others — come to analyse such data. This article presents a new technique for analysing numerical data, one which illuminates our understanding of counting behaviour (whether of enumerators or respondents) and its effects on the resulting data. This method can be used to detect the presence of ‘rounded’ data within a data-set and to determine the frequencies of the counting practices involved. The methodology and its underlying principles are described and the method is illustrated by means of a case-study based on church/chapel attendance data from the Religious Census of 1851 for England and Wales. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Humanities and Arts Computing Edinburgh University Press

Historical Sources: How People Counted. A Method for Estimating the Rounding of Numbers

Loading next page...
 
/lp/edinburgh-university-press/historical-sources-how-people-counted-a-method-for-estimating-the-9azjxh5ZDC

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Edinburgh University Press
Copyright
Copyright © Edinburgh University Press
ISSN
1753-8548
eISSN
1755-1706
DOI
10.3366/hac.1997.9.1-3.43
Publisher site
See Article on Publisher Site

Abstract

Any census — or other enumeration exercise — which yields numerical data (counts) may include data collected using a variety of unspecified counting practices, such as ‘rounding’ to the nearest multiples of a ‘base-unit’, e.g. 5 or 10 or a (half-) dozen, as well as ‘exact’ counts. In general, the greater the age of the data-source, the greater the probability that the recorded data represent ‘rounded’ estimates as opposed to ‘exact’ counts. Also, the greater the number and diversity of the persons involved in data-collection, the greater the probability of variation in counting practice. The presence of ‘rounded’ data in many historical sources produces uncertainty when historians — or others — come to analyse such data. This article presents a new technique for analysing numerical data, one which illuminates our understanding of counting behaviour (whether of enumerators or respondents) and its effects on the resulting data. This method can be used to detect the presence of ‘rounded’ data within a data-set and to determine the frequencies of the counting practices involved. The methodology and its underlying principles are described and the method is illustrated by means of a case-study based on church/chapel attendance data from the Religious Census of 1851 for England and Wales.

Journal

International Journal of Humanities and Arts ComputingEdinburgh University Press

Published: Jan 1, 1997

There are no references for this article.