Quality Control of Body Measurement Data Using Linear Regression Methods

Body measurement data are inherently inaccurate and quite error-prone due to manual measurement and data collection. In this study, professionally collected and self-collected body measurement data were used to investigate to what extent potentially erroneous data can be identified during collection by utilizing the anthropologically given correlation of body measurements. The study specifically uses a dataset created within the framework of a project for made-to-measure pattern creation, consisting of data from 2053 female individuals with up to 52 recorded body measurements. Using linear regression, a method for validating the collected data is defined, wherein potentially inconsistent data are identified based on tolerance intervals. The tolerance intervals calculated within the study are specific to the particular application and the personal data used in the study. The outlined method is applicable to almost any set of manually collected body data in at least the triple-digit range, enabling the identification of probable data errors already during their collection.