help > RE: Design matrix and contrast for 2 way ANOVA, and f-value
Jan 23, 2020  12:01 AM | Andrew Zalesky
RE: Design matrix and contrast for 2 way ANOVA, and f-value
Yes this is basically correct, but I suggest plotting the interaction so that you can fully understand the nature of the effect.

Originally posted by davideit7:
Dear Dr. Zalesky,

sorry my question was not really clear.
My doubts are more related to the difference between contrasts:

[0 0 0 1] vs [0 0 0 -1]

Since I'm testing for the interaction between treatment (placebo/drug) and condition (A/B) using t-test, depending from the contrast I will address only one-sided alternative hypothesis, likewise for the main effect.

So I was wondering what are the differences between the two contrasts, for the interaction? I mean by looking at my design matrix:

1-P_A 1  1  1  1
1-P_B 1  1 -1 -1
2-P_A 1  1  1  1
2-P_B 1  1 -1 -1
3-D_A 1 -1  1 -1
3-D_B 1 -1 -1  1
4-D_A 1 -1  1 -1
4-D_B 1 -1 -1  1

I would say that the first contrast (0 0 0 1) will test whether connectivity is increased in the placebo_A and drug_B conditions, while the negative contrast (0 0 0 -1) will test for an increase in connectivity for placebo_B and drug_A condition. Is this correct?

Sincerly,

Davide

Threaded View

TitleAuthorDate
Woomi Ban May 30, 2019
davideit7 Dec 5, 2019
Andrew Zalesky Dec 6, 2019
davideit7 Dec 6, 2019
Andrew Zalesky Dec 7, 2019
davideit7 Jan 20, 2020
Andrew Zalesky Jan 21, 2020
davideit7 Jan 22, 2020
RE: Design matrix and contrast for 2 way ANOVA, and f-value
Andrew Zalesky Jan 23, 2020
Woomi Ban Jun 10, 2019
Andrew Zalesky Jun 10, 2019
Andrew Zalesky Jun 1, 2019