I have run a 1 way ANOVA and carried out some post hocs to see which direction the results go in. If I report the direction of the findings - e.g. this group was higher than the other, which statistic do I quote? I have carried out Games-Howell post hoc and all it seems to come with is an associated p value, is this all that I report?
Tell me more
×
Cross Validated is a question and answer site for
statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
|
|
||||
|
|
|
You can report the $p$-values, or can make a figure with the means (plus/minus the standard error) and indicate with different letters those means that are statistically different according to G&H test. Games and Howell procedure uses the Studentized maximum modulus distribution. Hope it help! and excuse my english |
||||
|
|
|
The approach is just one of many possible ways to adjust for multiplicity. You could also apply bootstrap p-value adjustment ala Westfall and Young. |
||||
|
|
