Subscribe Bookmark RSS Feed

slopes from two different regression curves for equivalency?

jdobiecki0

Community Trekker

Joined:

Jan 20, 2015

Can someone please provide direction on how to compare two different slopes from two different regression curves for equivalency?  I have data sets with one response (call it activity) and the main effect being time.  I have another effect, manufacturer (currently as Character/Nominal values) that I want to include to see if there's any difference in the two different regression curves as a result of different manufacuturers.  I'm using Jmp Ver 8.0.2.  Hope someone can help me.

2 REPLIES
Dan_Obermiller

Joined:

Apr 3, 2013

Have one data table, structured similar to this:

Activity   Time   Manufacturer

    9            0        A

   8.7          0        B

   8.3          1        B

   9.2          2       A

....

Fit a Model in JMP with Y = Activity and the following terms:  Time, Manufacturer, Time*Manufacturer.

In the report, if Manufacturer is significant, that tells you that the intercept for the time models are different. If the Time*Manufacturer term is significant then that tells you that the time slopes are different.  I am guessing this is what is needed. You did however state EQUIVALENCY. If you need EQUIVALENCY, the process is more complicated. I hope this is what you really needed.

Dan Obermiller
jdobiecki0

Community Trekker

Joined:

Jan 20, 2015

Thnaks DanO.  Correct answer (I forgot about the cross function for factors...it's been a while)