A meta-analysis of 32 studies on the effectiveness of “self-talk” on sports performance was summarized as follows: The analysis revealed a positive moderate effect size (ES = .48). The moderator analyses showed that self-talk interventions were more effective for tasks involving relatively fine, compared with relatively gross, motor demands, and for novel, compared with well-learned, tasks (Hatzigeorgiadis et al., 2011, p. 348).
a. Read the explanation of a fixed effects model on page 539. Based on the quote above, do you think a fixed effects model would be appropriate for this meta-analysis? Explain.
b. Another quote from the article was: “The fail-safe statistic indicated that it would be unlikely that a sufficient number of unpublished studies (102) would exist to reduce the effect to a trivial size” (Hatzigeorgiadis, 2011, p. 351). Explain what the “fail-safe statistic” is, and why it is important to include it in the report.