Categorical: Stat Testing Issue

Question

In JMP 11 I am setting up a structured data table and when I get to setting up the stat testing columns, weird things start to happen.

I have 5 columns of data, not all are supposed to stat against each other. However, when I allow them to stat against each other, I see some results that I would expect.

For example:

A/B/C/D/E -> A is sig different than C & D, which is correct and as I would expect

Now when I set up the stat testing so that C is not tested against D & E, this appears to break.

A/B/C,A/D,A/E,B/D,B/E -> A no longer is flagged as being sig different than C & D

This issue happens in many places in the data table and I have no idea why this is happening. Are there any other Categorical users that have run into this and have an explanation?

mcstagger · Answer

Stan,

If you open San Francisco Crime.jmp and run out Day of the Week across the top and Category down the side, you can see this interaction perfectly.

When you do this, go ahead and paste in the above stat testing schemes. What you will notice is that when you apply the second scheme (A/B/C,A/D,A/E,B/D,B/E), comparisons are similar that were previously flagged as significant no longer are.

For example:

A/B/C/D/E -> Vandalism -> Column A stats against C,D,e (UPPER 90%, LOWER 80%)

A/B/C,A/D,A/E,B/D,B/E -> Vandalism -> Column A now only stats against e (LOWER 80%) even though A is still being compared against both C and D

stan_koprowski · Answer

Hello,

If you could post the data tables, sanitized as appropriate, that you are working with that will make it easier for us reproduce the issue and to see what you have and what you are trying to do.

Alternatively, you could private message melinda.thielbar or myself and we would be more than happy to assist you further.

Best,

Stan