Normative data for two tests of face matching under ecological conditions

Abstract

How do humans process unfamiliar faces, and how can we reliably identify individuals that are most proficient at it? Motivated by its relevance in applied contexts, much empirical work has sought to answer these questions. Controlled laboratory tests have been developed to understand the contribution of different variables and inter-individual differences. However, such face processing tests involving stimuli derived from ideal conditions, or manipulations and tasks that are not representative of real life, may lack ecological validity. This crucial consideration is often overlooked when laboratory tests are used to predict real-life proficiency. The present study followed the rationale that traditionally used controlled tests should be paired with more realistic, and ecologically meaningful ones – in terms of the stimuli and tasks performed. Testing large and heterogenous samples, we standardized two underused tests of facial identity matching: the Yearbook Test (YBT; Bruck et al., 1991) and the Face Identity Card Sorting Test (FICST; Jenkins et al., 2011). These procedurally simple tests mimic real-life challenges in face perception, as they assess unfamiliar facial identity matching across superficial image changes, or substantial age-related change in appearance. Beyond providing normative data, we describe how performance measured by these tests relates to that observed on more commonly used tests of face recognition (CFMT+; Russell et al., 2009) and perception (EFCT; PICT; White et al., 2015). Our findings suggest that (i) the YBT and FICST are easy-to-use, preferable alternatives to pairwise face matching tasks, which are prone to speed-accuracy trade-offs; (ii) challenging and ecologically valid tests should complement highly controlled measures when aiming to identify individuals with superior face processing abilities for real-life purposes.

Differences between and within individuals, and subprocesses of face cognition: implications for theory, research and personnel selection

“…This is especially important in the light of increasing reports of at best moderate correlations between individual tests of face processing (even within the same subprocess; e.g. [26,37,42,52]). The performance measures considered here were response accuracy (i.e.…”

Towards a ‘manifesto’ for super‐recognizer research

“…Bate et al, 2019), as well as the specific roles which to-be-selected individuals are expected to perform (e.g., passport control or crowd search? These procedures for assessment must (1) incorporate multiple tests and measures within these tests (e.g., accuracy and reaction time (see Stacchi, Huguenin-Elie, Caldara, & Ramon, 2019), and (2) ensure that individuals are identified accurately and reliably as SRs (Bate et al, 2019;Young & Noyes, 2019;cf. The framework should also incorporate guidelines to ensure selection of experimental procedures most suitable for assessing specific roles and identifying abilities that are critical in that specific operational context.…”

“…The framework should also incorporate guidelines to ensure selection of experimental procedures most suitable for assessing specific roles and identifying abilities that are critical in that specific operational context. That is, all adopted procedures require sufficient psychometric calibration to meet the criterion of valid and reliable diagnostic sensitivity (see also Bate et al, 2018;Bobak, Pampoulov, & Bate, 2016;Stacchi, et al, 2019). Wilmer et al, 2012).…”

“…The framework should also incorporate guidelines to ensure selection of experimental procedures most suitable for assessing specific roles and identifying abilities that are critical in that specific operational context. These procedures for assessment must (1) incorporate multiple tests and measures within these tests (e.g., accuracy and reaction time (see Stacchi, Huguenin-Elie, Caldara, & Ramon, 2019), and (2) ensure that individuals are identified accurately and reliably as SRs (Bate et al, 2019;Young & Noyes, 2019;cf. Wilmer et al, 2012).…”

“…Wilmer et al, 2012). That is, all adopted procedures require sufficient psychometric calibration to meet the criterion of valid and reliable diagnostic sensitivity (see also Bate et al, 2018;Bobak, Pampoulov, & Bate, 2016;Stacchi, et al, 2019).…”