7. Contrast Coding Flashcards
The F-statistic tests…
the overall fit of the model
Model parameters tell us about…
specific differences between means
Dummy coding compares…
each category to a baseline
Orthogonal contrasts is…
It is driven by…
It is planned…
It controls…
… contrast coding
… hypothesis
… a priori
… type 1 type error
Post hoc tests are not…
They compare…
They involve multiple t-tests adjusted for…
… planned (not hypothesis driven)
… all pairs of means
… the number of tests
Trend analysis is useful only for…
Ordered means
The variability explained by the model (SSm) is due to…
This variability sometimes represents…
participants being assigned to different groups
an experimental manipulation
SSm variability can be broken down further to test…
specific hypotheses about which groups might differ
We break down the variance according to hypotheses made “a priori”. What does this mean?
Before the experiment
To control type 1 error rates, contrasts must be…
If a group is single out in a contrast, then that group…
independent (they must test unique hypotheses)
should not be used in any subsequent contrasts
Each contrast should compare only ____ chunks of variation
2
You should always end up with ____ less contrast than the number of groups
one less (K-1)
What are the 5 rules for coding planned contrasts?
- Groups coded with positive weights compared to groups coded with negative weights
- The sum of weights for a comparison should be zero
- If a group is not involved in a comparison, assign it a weight of 0
- For a given contrast, the initial weight assigned to the group(s) in one chunk of variation should be equal to the number of groups in the opposite chunk of variation
- To get the final weight, divide the initial weights by the number of groups with non-zero weights
When should you use a post hoc test?
In the absence of specific hypotheses
Post hoc tests compare all pairs of means to see…
where the specific differences lie
