Fixed omitted v. Fixed missing in test probabilities under distribution

BL

I am having difficulty understanding what the options for test probabilities mean in a goodness of fit test.

 

In both of the following, I typed in COUNTS and NOT proportions, the only difference was in result.  I can SEE which one matches what I got with Minitab but I can’t explain WHY it does.    Any ideas?

 

 

 

 

 

 

JMP community question 9_28_2018.pdf

Mark_Bailey

You enter the 2014 counts in the data table and use them in the Freq role to launch Distribution. You enter the historical estimates from 2004 in the hypothesized probabilities when you select the Test Probabilities command in Distribution. I get the same result as shown in your attachment.

 

Is this homework?