Pictorial mnemonic-strategy interventions for children with special needs: Illustration of a multiply randomized single-case crossover design

Abstract

An innovative single-case crossover design containing multiple forms of randomization was implemented with eight participants in seven weekly sessions, during which instruction was given in the use of two different pictorial mnemonic (memory-enhancing) strategies: one designed to improve the children's learning of the dates of various inventions and the other designed to improve the children's acquisition of unfamiliar vocabulary items. A composite randomization statistical test revealed that when compared with the children's own preferred learning methods, the mnemonic-strategy approach produced the predicted facilitation effects. At the same time, it was evident that mnemonic instruction enhanced children's performance to a greater extent on the vocabulary task than on the inventions task. In-depth examination of both individual student performance profiles and the tasks/procedures were conducted, yielding recommendations and challenges for follow-up single-case intervention research on the topic.

Randomization procedures in single‐case intervention research contexts: (Some of) “the rest of the story”

“…Between-and within-case (phase) intervention randomization, along with intervention start-point-randomization, would improve both the experimental control and statistical power of the study . For an actual research application and discussion of a combination of these three different randomization types, see the earlier referenced Hwang et al (2018) study.…”

“…(For details on the tensions between the behavior analytic and statistical traditions, readers should refer to the early exchange between Edgington, 1980 a,b;and Kazdin, 1980.) In addition, in an actual SCI investigation, Hwang, Levin, and Johnson (2018) include an extensive discussion of these issues. We further believe that a SCI researcher's decision about whether to adopt design randomization is not a willy-nilly process.…”

“…Kratochwill and Levin (2010), who provided comprehensive arguments for elevating a SCI study's internal validity through randomized designs, were at the time unaware of Edgington's (1996) cogent essay with the same message. In addition, in an actual SCI investigation, Hwang, Levin, and Johnson (2018) include an extensive discussion of these issues. In the limited space allotted us here, our primary purpose is not to reiterate and elaborate on those arguments.…”

The Composite Hypothesis Contrast Procedure: A Novel Sequential Multiple-Comparison Approach

“…A situation that incorporates aspects of Designs 2 and 3 was implemented in the previously cited Hwang et al (2016) study where, in the context of a single-case crossover design (Levin, Ferron, & Gafurov, 2014), four different learning strategies (two experimental and two control) were predicted to have similar effects on two different outcome measures. Moreover, in that single-case design, the outcome measures of interest were the amounts of change/improvement between the baseline (A) phase and the intervention (B) phase of the study.…”

“…In the course of a recent research investigation-a single-case intervention study conducted by Hwang, Levin, and Johnson (2016)-we stumbled upon an interesting data-analysis situation that was reminiscent of one that had been considered a generation ago (Levin, Serlin, & Seaman, 1994). To summarize the take-home message of that 1994 article: Starting with a univariate K = 3 independent means one-way layout, we demonstrated that: (a) When an initial omnibus hypothesis test (of, for example, "All μ k are equal") is rejected based on a Type I error probability of α, (b) if any sub-hypothesis subsumed by the rejected hypothesis is tested at α, then (c) the resulting familywise Type I error probability (α FW ) associated with entire set of tested hypotheses is equal to α.…”