Consider two hypothetical studies comparing men and women. In the first, a large sample of $500$ women and $500$ men yields a strong relationship of Cohen's $d = 0.50$. Such a strong result in a large sample is highly unlikely if the null hypothesis were true, meaning the null hypothesis would be rejected. In the second, a small sample of $3$ women and $3$ men yields a weak relationship of Cohen's $d = 0.10$. This weak result in a small sample is quite likely to occur by chance, so the null hypothesis would be retained.