How to determine where significant differences lie after getting a significant F-ratio.

Planned comparisons:
To be used when you have specific a priori hypotheses.
- use separate F ratios or t-tests for the pairs of means you have hypothesized to differ
- the number that convey new information (: called orthogonal comparisons) will be equal to the number of groups (means) - 1

Unplanned comparisons: (fishing expeditions)
You have to consider two types of error: error rate per comparison, and the familywise error rate (which takes into consideration probability pyramiding).

a _FW = 1 - (1 - a )^c

Where:
c = number of comparisons, and
a = the per-comparison error rate

e.g., if making 4 comparisons:
a _FW = 1 - (1 - a )^c = 1-(1-.05)⁴ = 1-.95⁴ = .185)