General script for fit model with saving student residuals for different variables

Bmllnn — Thu, 16 Jan 2025 20:46:33 GMT

I am trying to create a script that I can use every time with minimum work to do ANOVA and Chi-sq directly.

I started the script:

Names Default To Here(1);
dt=Current Data Table();

dlg = Column Dialog(																	
			name = ColList( "Parameters", Min Col(1) ), 								
			subject = ColList( "Treatment", Min Col(1), MaxCol(1) ),
			Reffect = ColList( "Random", Min Col(0), MaxCol(2) )
			);

// Stop if the user did not press 'OK'		
If( dlg["Button"] != 1, Beep(); Throw());

name = dlg[ "name" ];
subject = dlg["subject"];
Reffect = dlg ["Reffect"];
show (name, subject, Reffect);

dt<<Fit Model(
	Y( name[1]),
	Effects( subject[1]),
	Random Effects( Reffect[1]),
	NoBounds( 1 ),
	Personality( "Standard Least Squares" ),
	Method( "REML" ),
	Emphasis( "Effect Leverage" ),
	Run(
		Profiler( 0 ),
		name[1] << {Summary of Fit( 1 ), Analysis of Variance( 0 ),
		Parameter Estimates( 1 ), Scaled Estimates( 0 ),
		Plot Actual by Predicted( 1 ), Plot Residual by Predicted( 1 ),
		Plot Studentized Residuals( 0 ), Plot Effect Leverage( 1 ),
		Plot Residual by Normal Quantiles( 0 ), Interaction Plots( 0 ), AICc( 0 ),
		Show VIF( 0 )}
	)
);
obj << Studentized Residuals;
//obj << Close Window;

However, there is an issue to do the fit model. The fit model box open only with the Y.

on the Y most of the time I need to add more than 1 variable as well, so I will have more student residuals to save to be able to verify the outliers, then the normal distribuition and the equal variance.

Thanks for your help :)

Re: General script for fit model with saving student residuals for different variables

HadleyMyers — Fri, 17 Jan 2025 20:19:05 GMT

Hi,

Try adjusting the code to add eval(eval expr(expr))). There's a blog post here that explains a little about how this works. Also, the way the column dialog window is set up allows multiple Ys to be selected.

Eval(Eval Expr(obj=dt<<Fit Model( Y( expr(name)), Effects( expr(subject)), Random Effects( expr(Reffect)), NoBounds( 1 ), Personality( "Standard Least Squares" ), Method( "REML" ), Emphasis( "Effect Leverage" ), Run( Profiler( 0 ), name[1] << {Summary of Fit( 1 ), Analysis of Variance( 0 ), Parameter Estimates( 1 ), Scaled Estimates( 0 ), Plot Actual by Predicted( 1 ), Plot Residual by Predicted( 1 ), Plot Studentized Residuals( 0 ), Plot Effect Leverage( 1 ), Plot Residual by Normal Quantiles( 0 ), Interaction Plots( 0 ), AICc( 0 ), Show VIF( 0 )} ) )));

topic General script for fit model with saving student residuals for different variables in Discussions

General script for fit model with saving student residuals for different variables

Re: General script for fit model with saving student residuals for different variables