Non-numerical features fail to predict numerical performance in real-world stimuli

Abstract

It has been proposed that humans use non-numerical features (such as convex hull and surface area) to estimate the number of objects in a scene. This would be an evolutionarily advantageous strategy if such features truly patterned with number in the world, but this has never been empirically tested. Here, we quantify the strength of the relationship between number and non-numerical features in two relevant image sets: the illustrations from children’s counting books, and real-world photographs. We find that non-numerical features are much less predictive of the number of objects in counting books than in photographs, despite the former being specifically designed for use in teaching children about numbers. Then, across three behavioral experiments, we ask whether the stronger relationship in photographs predicts better number estimation performance in adults (N = 120) and in children (N = 94; M age = 7;2 years). Our experiments reveal that number estimation is easier from the counting books than the photographs, even though non-numerical features are less predictive of number in books. This analysis uses real-world stimuli and draws into question the claim that non-numerical features are intrinsically involved in number extraction.