The executive function of bilingual and monolingual children: A technical efficiency approach

Abstract

This paper introduces a novel approach to evaluate performance in the executive functioning skills of bilingual and monolingual children. This approach targets method- and analysis-specific issues in the field, which has reached an impasse (Antoniou et al., 2021). This study moves beyond the traditional approach towards bilingualism by using an array of executive functioning tasks and frontier methodologies, which allow us to jointly consider multiple tasks and metrics in a new measure; technical efficiency (TE). We use a data envelopment analysis technique to estimate TE for a sample of 32 Greek-English bilingual and 38 Greek monolingual children. In a second stage, we compare the TE of the groups using an ANCOVA, a bootstrap regression, and a k-means nearest-neighbour technique, while controlling for a range of background variables. Results show that bilinguals have superior TE compared to their monolingual counterparts, being around 6.5% more efficient. Robustness tests reveal that TE yields similar results to the more complex conventional MANCOVA analyses, while utilising information in a more efficient way. By using the TE approach on a relevant existing dataset, we further highlight TE's advantages compared to conventional analyses; not only does TE use a single measure, instead of two principal components, but it also allows more group observations as it accounts for differences between the groups by construction.

Keywords: Bilinguals; Bootstrap; DEA; Executive function; Technical efficiency; k-means.

Fig. 1

Efficient frontiers. Notes. The figure shows the efficient frontier (solid black line) in the case of 1 output / 1 input (Case A), and 2 outputs / 1 input (Case B). The orange line represents the best-fit line from a regression model. The outputs are the accuracy scores in two executive function scores, BDST (Case A and B) and Count recall (Case B). The input is the non-verbal intellectual ability as proxied by the KBIT-2 score (Case A and B). The ten participants labelled A-J are a random sample from our dataset

Fig. 2

Box-plots of executive function metrics. Notes. The figure reports box plots of accuracy and response time metrics for bilinguals and monolingual groups

Fig. 3

Grammar, expressive vocabulary, and receptive vocabulary skill standardised scores. Notes. Standardised grammar, expressive vocabulary, and receptive vocabulary skill metrics for bilinguals and monolingual groups