IEEE Geospatial Computing: Spatial Analysis of Historic Surname Patterns in Great Britain
Combining Historic Interpretations of the Great Britain Population With Contemporary Spatial Analysis: the Case of Surnames<br />James Cheshire<br />Department of Geography and Centre for Advanced Spatial Analysis,<br />University College London <br />firstname.lastname@example.org spatialanalysis.co.uk<br />
Two sections:<br />1. “Homes of Family Names in Great Britain” <br /> (Guppy, 1890).<br />2. Contemporary Spatial Analysis.<br />The 1881 Census<br />Methods: <br />Lasker Distance<br />Hierarchical Clustering<br />
Homes of Family Names in Great Britain*.<br /><ul><li>Obtained approx. 8000 unique surnames from Kelly’s Post Office Directory.
Surnames were selected from Yeoman due to their “stationary habits and purity of extraction”.
Each name was also required to have a relative frequency of > 7/1000.
Created a matrix of with counties along the top and surnames down the side.
657 Registration Districts.** </li></ul>*Obtained from the UK Data Archive. Website:www.data-archive.ac.uk<br />** Downloadable from UK Borders. Website: http://edina.ac.uk/ukborders/<br />
Contemporary Spatial Analysis: Methods<br />Lasker Distance Calculation using the frequency of each surname within each registration district. <br />
1881 Census Surname Regions<br />7 Clusters<br />20 Clusters<br />
Summary<br />Two very different approaches:<br />Guppy:<br />Deductive.<br />Sampled only yeoman.<br /> Cheshire:<br />Inductive.<br />“Complete” population.<br />Surprisingly similar results.<br />