search

PNNL-TES / bahn-rs-test

MIT License
2 stars 1 forks source link

Incorrect slope test (?) #5

Open bpbond opened 5 years ago

bpbond commented 5 years ago

I see a lot of places where you test for slope=1, I think, e.g.:

slope_test <- summary( m1_MAT )$coefficients[ 2, 4 ]

But this extracts (from the model summary object) the test for whether the slope is different from zero, not from one.

bpbond commented 5 years ago

A couple different ways to do this are given here.

jinshijian commented 5 years ago

Yes, that's true, use this method it actually tests whether slope differs from zero. I said 1 because it makes more sense. Maybe I should update the code to make it test whether significantly differ from 1.

bpbond commented 5 years ago

Yes, that's definitely the test we want.