Using statistical smoothing to date medieval manuscripts

TL;DR

This paper presents a statistical smoothing method to estimate the dates of medieval manuscripts by leveraging a large dataset of both dated and undated documents, improving dating accuracy through similarity assessment.

Contribution

It introduces a multivariate kernel smoothing approach for dating manuscripts, combining distance measures and statistical techniques to enhance historical dating methods.

Findings

Effective dating of 5000 undated manuscripts using the method

Improved accuracy over traditional dating techniques

Demonstrated applicability to medieval English manuscripts

Abstract

We discuss the use of multivariate kernel smoothing methods to date manuscripts dating from the 11th to the 15th centuries, in the English county of Essex. The dataset consists of some 3300 dated and 5000 undated manuscripts, and the former are used as a training sample for imputing dates for the latter. It is assumed that two manuscripts that are ``close'', in a sense that may be defined by a vector of measures of distance for documents, will have close dates. Using this approach, statistical ideas are used to assess ``similarity'', by smoothing among distance measures, and thus to estimate dates for the 5000 undated manuscripts by reference to the dated ones.