Cognitivefunction improved by an average of 3 points in the fish oil group (n=20) and this within-group change was statistically significant at the .05 level (p=.043); cognitive function improved by 2.1 points in the placebo group (n=20) and this within-group change was not statistically significant (p=.087). The average between-group difference (0.9 points) was not statistically significant (p=.47). However, the authors write in their abstract: “The fish oil group improved significantly (p.05). Thus, fish oil may be beneficial for improving cognitive function.” This is a highly misleading presentation of results. Significance within one group but not the other does not imply a significant difference between groups [19].Solution: When reporting the results of controlled trials, the abstract should only present between-group comparisons, and the primary conclusions should be based only on between-group comparisons.