cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Browse apps to extend the software in the new JMP Marketplace
Choose Language Hide Translation Bar
JMPNOVICE509
Level I

Fit Y by X with multiple y data and one control group

Hi

 

I have multiple different groups and one control. I would like to do one Fit Y by X analysi where I have the different groups on separate plots but have the control group comparator on every plot. For example Control grp A with grps B, C, D and control grp A with grps E, F, G. Hoping to do all in one without needing to use hide/exclude and plot multiple times.

 

Thanks

 

R.

1 REPLY 1
ian_jmp
Level X

Re: Fit Y by X with multiple y data and one control group

Probably not quite what you want, but you could try using 'Favourites' with the Local Data Filter (and then perhaps journal the filtered results to get them in one place).

To see this, run the code below to make a table, then run the saved script in the table:

New Table( "Test",
	Add Rows( 100 ),
	New Script(
		"Oneway",
		Oneway(
			Y( :Response ),
			X( :Group ),
			Automatic Recalc( 1 ),
			Local Data Filter(
				Add Filter(
					columns( :Group ),
					Display( :Group, Size( 160, 105 ), List Display )
				),
				Favorites(
					"Group = Control, B, C, D"(Match( columns( :Group ),
						Where( :Group == {1, 2, 3, 4} )
					)),
					"Group = Control, E, F, G"(Match( columns( :Group ),
						Where( :Group == {1, 5, 6, 7} )
					))
				)
			)
		)
	),
	New Column( "Group",
		Numeric,
		"Nominal",
		Format( "Best", 12 ),
		Formula( Random Integer( 1, 7 ) ),
		Value Labels(
			{1 = "Control", 2 = "B", 3 = "C", 4 = "D", 5 = "E", 6 = "F", 7 = "G"}
		),
		Use Value Labels( 1 )
	),
	New Column( "Response",
		Numeric,
		"Continuous",
		Format( "Fixed Dec", 12, 2 ),
		Formula( Random Normal() )
	)
)