How working memory relates to children's reading comprehension: the importance of domain-specificity in storage and processing

Abstract

Working memory is considered a well-established predictor of individual variation in reading comprehension in children and adults. However, how storage and processing capacities of working memory in both the phonological and semantic domain relate to reading comprehension is still unclear. In the current study, we investigated the contribution of phonological and semantic storage, and phonological and semantic processing to reading comprehension in 123 Dutch children in fifth grade. We conducted regression and mediation analyses to find out to what extent variation in reading comprehension could be explained by storage and processing capacities in both the phonological and the semantic domain, while controlling for children's decoding and vocabulary. The analyses included tasks that reflect storage only, and working memory tasks that assess processing in addition to storage. Regression analysis including only storage tasks as predictor measures, revealed semantic storage to be a better predictor of reading comprehension than phonological storage. Adding phonological and semantic working memory tasks as additional predictors to the model showed that semantic working memory explained individual variation in reading comprehension over and above all other memory measures. Additional mediation analysis made it clear that semantic storage contributed indirectly to reading comprehension via semantic working memory, indicating that semantic storage tapped by working memory, in addition to processing capacities, explains individual variation in reading comprehension. It can thus be concluded that semantic storage plays a more important role in children's reading comprehension than previously thought.

Keywords: Children; Domain-specificity; Reading comprehension; Storage; Working memory.

Fig. 1

Mediation of the relation between semantic storage and reading comprehension by semantic working memory. Note *p < .05; **p < .01; ***p < .001. The values belonging to the ab path were: β = .32, SD = .21, p = .005