Hello, I am currently working on my final research project and I am a bit stuck. I am trying to determine the reliability of an accelerometer (RT3).

My subjects did some running at a set speed on a treadmill with an RT3 recording their activity and then again the same thing the next week.

I am using an ICC to test the correlation of the repeatability of the activity counts on the RT3 the first and second day. but i am not sure whether to use a one-way random, a two-way random or a two-way mixed model.

also, I am doing a sub analysis for when the same monitor was used for both tests and for when a different monitor was used for both tests and I am not sure if these would need different models of ICC tests too.

Ive done loads of reading up on this and I honestly cant work out which one to use. Any help appreciated

Tom