“…First, estimating an effect size for group differences in key dependent variables was a challenge. There is little previous research on metacognitive monitoring in ASD and existing studies have used a variety of tasks that are arguably not directly comparable (e.g., Cooper, Plaisted-Grant, Baron-Cohen, & Simons, 2016 ; Grainger, Williams, & Lind, 2016a , 2016b ; Nicholson et al, 2019 ; Williams, Bergström, & Grainger, 2018 ; Williams & Happé, 2010 ; Williams & Happé, 2009 ; Wilkinson, Best, Minshew, & Strauss, 2010 ; Wojcik, Allen, Brown, & Souchay, 2011 ; Wojcik et al, 2014 ), so basing an effect size on the weighted effect size across previous studies was inappropriate, in our view. Second, we predicted a null effect for the between-groups difference in gambling accuracy, which makes estimating “sufficient power” difficult.…”