Sampling in archives: A review

Abstract

Confronted with the sheer mass of records created by modern bureaucracies, archivists have employed sampling, both as a tool to determine the research potential of records and as an appraisal device. The term sampling as used in archival literature usually means either to cull from a large records series the most significant files or documents (subjective sampling) or to select statistically a small portion from a large universe that will accurately reflect all important aspects of the larger universe (statistical sampling). The former method has been employed for a generation and has been applied in those records series in which only the exceptional case is worthy of preservation. Statistical sampling, on the other hand, has been used to capture the typical cases in a series. The effectiveness of either method, and indeed the decision to sample itself, must always be rooted in the professional judgment of those archivists most familiar with the historical value of the materials they administer.