Complex span tasks interleave a memory task (requiring one to remember a set of items in the correct order) with a secondary processing task (e.g., judge the correctness of equations). Working memory (WM) capacity is often assessed with complex working memory span tasks (complex span tasks for short e.g., reading span, operation span see Conway et al., 2005).
Working memory is information temporarily held in mind, which can be useful to complete a diverse range of cognitive tasks ( Baddeley & Hitch, 1974). This result suggests that i) complex span tasks might overestimate storage capacity in general, and ii) the difference between simple and complex span performance levels must rest in some mechanism other than prevention of a chunking strategy by the interleaved processing task in complex span tasks. The prediction that chunking is important solely in simple spans was not confirmed: Effects of information compression contributed to performance levels to a similar extent in both tasks according to a theoretically-based metric. The three other conditions were predicted to prevent chunking processes, either because the interleaved processing task did not allow any chunking process to occur or because the noncompressible material inherently limited the chunkability of information.
We predicted an interaction between the types of tasks and chunkability/compressibility, supporting a single higher span for the condition in which a simple span task was combined with chunkable items. To manipulate the chunkability of the stimulus lists, our method involved a measure of their compressibility, i.e., the extent to which a pattern exists that can be detected and used as a basis of chunk formation. It follows that the respective spans of these two types of tasks could be equal (at around 4 ± 1) if stimulus lists exclusively used nonchunkable stimulus items. One possible reason for the higher span of simple span tasks is that participants can take advantage of the spare time to chunk multiple items together to form fewer independent units, approximating 4 ± 1 chunks. Consequently, the average span is usually lower (4 ± 1 items) than in simple span tasks (7 ± 2 items).
Complex working memory span tasks were designed to engage multiple aspects of working memory and impose interleaved processing demands that limit the use of mnemonic strategies, such as chunking.