Performance Expectancies Moderate the Effectiveness of More or Less Generative Activities Over Time

Abstract

We examined if the benefits of generation for long-term learning depend on individual differences in performance expectancies (PEs) prior to learning. We predicted that a greater generative activity (problem-solving) compared to less generative activity (worked-examples) should be more effective for pupils with higher PEs, especially in the long run. As a comparison group for problem-solving, we implemented a special type of worked-examples that decreased engaging in self-explanations, because our main prediction focused on PEs moderating the long-term effectivity of less versus greater generative activities. We tested students' immediate and delayed performance (after 3 months) using coherent curricular materials on linear functions in a sample of eighth graders (advanced school track). The results were partly in line with our predictions: Although we found no moderation of PE and generative activity, we obtained the predicted 3-way interaction of PE, generative activity, and time. Immediately, greater generative activity (problem-solving) was beneficial for pupils with higher PEs, while for pupils with lower PEs, problem-solving versus worked-examples did not differ. In the delayed test, this pattern reversed: for lower PEs, greater generative activity outperformed less generative activities, but there was no difference for higher PEs. Unexpectedly, the initial advantage of problem-solving for higher PEs could not be maintained, decreasing over three subsequent months, whereas the performance in the worked-example condition remained at a comparable level for higher PEs. The change in performance in the problem-solving condition for lower PEs was descriptively less pronounced than in the worked-example condition, but statistically not different. We further investigated the effects of problem-solving and worked-examples on changes in PEs after learning and after testing, hinting at gradual decrease in PEs and greater metacognitive accuracy in the problem-solving condition due to a reduction of overconfidence.

Keywords: desirable difficulties; generation effect; long-term learning; meta-cognition; performance expectancies; problem-solving; worked-examples.

FIGURE 1

Timeline and schematic design in-class Session Time 1. Gray-colored arrays denote the same procedures and materials for all participants; white arrays show the differing procedures and materials according to the experimental manipulation. PE, performance expectancy; PT, problem set; EP, estimated performance; thus PE1-PS1, performance expectancy measurement 1 for problem set 1; PE2-PS1, performance expectancy measurement 2 for problem set 1; PE3-PS1, performance expectancy measurement 3 for problem set 1; PE1-PS2, performance expectancy measurement 1 for problem set 2; PE2-PS2, performance expectancy measurement 2 for problem set 2; EP1-PS1, estimated performance for problem set 1; EP1-PS2, estimated performance for problem set 2.

FIGURE 2

Learning phase: manipulation problem set 1.

FIGURE 3

Learning phase: manipulation problem set 2.

FIGURE 4

Timeline and schematic design in-class Session Time 2. PE4-PS1, performance expectancy measurement 4 for problem set 1; PE1-PS2, performance expectancy measurement 3 for problem set 2.

FIGURE 5

Immediate post-test scores for both learning conditions at different levels of initial performance expectancies. WEX, worked-examples (0), n = 32; PBS, problem-solving (1), n = 28. Error bars represent the standard error of the mean [WEX: 1.73 (–1SD), 1.02 (Mean), 1.33 (+1SD); PBS: 1.26 (–1SD), 1.06 (Mean), 1.58 (+1SD)]. Performance expectancies (standardized) are depicted for lower, medium, and higher levels. Post-test scores could range from 0 to 42.

FIGURE 6

Delayed post-test scores for both learning conditions at different levels of initial performance expectancies. WEX, worked-examples (0), n = 32; PBS, problem-solving (1), n = 29. Error bars represent the standard error of the mean [WEX: 1.91 (–1SD), 1.13 (Mean), 1.48 (+1SD); PBS: 1.40 (–1SD), 1.17 (Mean), 1.75 (+1SD)]. Performance expectancies (standardized) are depicted for lower, medium, and higher levels. Post-test scores could range from 0 to 42.

FIGURE 7

Performance changes across both post-test by learning condition and initial performance expectancies. Change scores on the y-axis were computed by subtracting the delayed post-test scores from the immediate post-test scores: Zero means no change, negative values mean performance loss, and positive values mean performance gains. The x-axis anchors these changes for both learning conditions (WEX, worked-example (0), n = 32; PBS, problem-solving (1), n = 29) for lower, medium, and higher levels of performance expectancies. Error bars represent the standard error of the mean [WEX: 1.74 (–1SD), 1.03 (Mean), 1.35 (+1SD); PBS: 1.27 (–1SD), 1.07 (Mean), 1.60 (+1SD)].

FIGURE 8

Change in performance expectancies by learning conditions. Error bars represent the standard error of the mean. Values could range from expecting 0 points to 42 points in the performance tests.

FIGURE 9

Main effect of calibration accuracy. Error bars represent the standard error of the mean.