goodness of fit - include in a script

[#1]

Dear all, 

I'm triyng to add a goodness of fit after a distribution, using a script. There is a loop. The analysis is performed for n columns.

this is the part of the code:

	
	disti = dt << Distribution(
		stack( 0 ),
		Continuous Distribution( 
		Column( listName[i] )),
		Normal Quantile Plot( 1 ),
		Fit Distribution( Normal(Goodness of Fit( 1 ) )),
		Capability Analysis( 1 ),
		Invisible( 1 ) 
			
	);
	

But no goodness of fit appears... and  I don't konw why..

Do you have an idea?

 What does it mean the "1" parameter of this function?

Thank you 

Maïna

[#2 · Accepted solution]

I have expanded your script slightly, to make it a functioning script.  Your code works well using the Semiconductor Capability data table.  I suggest that you look at the makeup of your data or the list, "listName".

Names Default To Here( 1 );
dt = Open( "$SAMPLE_DATA\semiconductor capability.jmp" );

listName = dt << get column names( numeric, continuous );

For( i = 1, i <= 2, i++,
	disti = dt << Distribution(
		stack( 0 ),
		Continuous Distribution( Column( listName[i] ) ),
		Normal Quantile Plot( 1 ),
		Fit Distribution( Normal( Goodness of Fit( 1 ) ) ),
		Capability Analysis( 1 ),
		Invisible( 1 ) 
			
	)
);

[#3]

Thank you Jim, 

I have already do this loop :) IThe script is bigger ! 

My first script was like that:

The distribution appears, the capability analysis too, but not the goodness of fit test... 

I don't understand why ;(

	disti = dt << Distribution(
		stack( 0 ),
		Continuous Distribution( Column( listName[i] ) ),
		Normal Quantile Plot( 1 ),
		Capability Analysis( 1 ),
		Invisible( 1 )

 But I want to add a goodness of fit analysis below the histogram of the distribution.

Tks 

[#4]

Do you have the same problem if you run Jim's script?

[#5]

No, It works well !

[#6]

I used your script, and just attached a different data table, so that is why I suggested that you need to look elsewhere.

[#7]

Or do I have no place to display the result?
Would that be possible?

[#8]

Are the columns you are analyzing of Modeling Type Continuous?  If they are Ordinal or Nominal, they will not provide a goodness of fit

[#9]

yes, all my columns are in continuous type