Bonferroni Correction p value in SPSS

Question

I have run an analysis on data using SPSS. I have a repeated measures design with 7 conditions. I chose to do pairwise comparisons to see where the effects lie and used the Bonferroni correction. If I've understood it correctly k(k-1)/2 would give an adjusted p value of .002. However, what I'm confused with is the output in SPSS. It says something is significant at .003. Could somebody explain this and how would I report it? I wasn't sure if I was supposed to check the significance value against the new .002 one and therefore should conclude it isn't significant.

Answer 1

With Bonferroni correction you multiply the $p$-values by the number of comparisons that you made, so you can calculate it by hand. SPSS calculates it exactly the same way

Statistical textbooks often present Bonferroni adjustment (or correction) in the following terms. First, divide the desired alpha-level by the number of comparisons. Second, use the number so calculated as the p-value for determining significance. So, for example, with alpha set at .05, and three comparisons, the LSD p-value required for significance would be .05/3 = .0167.

(source IBM's page; cf. this answer).

---

I imagine that the difference could be caused by different way of rounding that was used or some other trivial reason.