Null hypothesis significance tests, a misleading approach to scientific knowledge: Some implications for eating disorders research

COVID Isolation Eating Scale (CIES): Analysis of the impact of confinement in eating disorders and obesity—A collaborative international study

“…The comparison between groups defined by the diagnosis (AN, BN, OSFED and obese) was based on analysis of variance analyses (ANOVAs), with post‐hoc pairwise comparisons estimated via Bonferroni's procedure. For all these analyses, significant tests were complemented with the estimation of the effect size through Cohen's‐ d coefficient, considering null effect for | d | < 0.20, low‐poor for | d | > 0.20, mild‐medium for | d | > 0.50 and large‐high for | d | > 0.80) (Cohen, 1988; Kelley & Preacher, 2012; Granero, 2020).…”

The impact of duration of illness on treatment nonresponse and drop‐out: Exploring the relevance of enduring eating disorder concept

“…Other comparisons between the groups were based on χ 2 tests for categorical variables and analysis of variance for quantitative measures. Effect size for proportion differences was estimated with the Cohen's h coefficient and for mean differences with the Cohen's d coefficient (poor effect size was considered for |h| or |d| lower than 0.20, mild-moderate for |h| or |d| higher than 0.50 and highlarge for |h| or |d| higher than 0.80; Granero et al, 2020). Finner correction was used to control for Type I error (Finner, 1993) due to multiple statistical comparisons.…”

Hippocampal volumes in anorexia nervosa at different stages of the disorder

“…The statistical threshold was calculated using the false discovery rate method in order to control for inflation errors due to multiple comparisons. To improve and facilitate the interpretation of the results, we calculated the effect-sizes of hippocampal volumes comparisons (Granero et al, 2020). Both left and right hippocampal volumes were significantly smaller in AN patients in comparison to healthy women.…”