Dissociating lexical and sublexical contributions to transposed-word effects

When two sequences of words are presented successively for 400 ms each, it is harder to decide that the two sequences differ when the difference is generated by transposing two words compared with a condition where the same two words are replaced by different words. Interestingly, this transposed-word effect is obtained even when the first sequence is ungrammatical. One account of the effect seen with ungrammatical sequences is that participants detect mismatching letters rather than words. Under this account, the migration of letter identities across adjacent words would make it harder to judge the transposed-word condition as being different. The present experiment put this account to test by comparing transposition effects to sequences of words vs. pseudowords. We hypothesized that if same-different judgments are made on the basis of sublexical orthographic information only, then we should observe similar effects for words and pseudowords. Although transposition effects were found with pseudoword stimuli, the effects were significantly reduced compared to word sequences. This suggests that the noisy bottom-up allocation of word identities to locations along a line of text is one key mechanism driving transposed-word effects.