Gráficos de medias LS en análisis factoriales del modelo de ajuste

[AvigdorC]

Actualmente, la variable del eje X en factorial de 2 vías es un factor u otro (alternando usando Shift), pero es mejor poder ver ambos gráficos alternativos juntos (uno encima del otro).

[Audrey_Shull]

Esto se abordó en JMP 14 y posteriores. Para ver un ejemplo, podemos usar el archivo de datos de muestra 3 Factors Crossed.jmp:

open("$SAMPLE_DATA\Variability Data\3 Factors Crossed.jmp");
Fit Model(
Y( :new Y ),
Effects(
:Operator,
:Part,
:Operator * :Part,
:Instrument,
:Operator * :Instrument,
:Part * :Instrument,
:Operator * :Part * :Instrument
),
Personality( "Standard Least Squares" ),
Emphasis( "Effect Leverage" ),
Run(
:new Y << {Summary of Fit( 1 ), Analysis of Variance( 1 ),
Parameter Estimates( 1 ), Lack of Fit( 0 ), Scaled Estimates( 0 ),
Plot Actual by Predicted( 1 ), Plot Regression( 0 ),
Plot Residual by Predicted( 1 ), Plot Studentized Residuals( 0 ),
Plot Effect Leverage( 1 ), Plot Residual by Normal Quantiles( 0 ),
Box Cox Y Transformation( 0 ), {:Operator * :Part <<
{Least Squares Means Plot( Overlay Term List( Operator ) ),
Least Squares Means Plot( Overlay Term List( Part ) )}, :Operator * :Part *
:Instrument << {Least Squares Means Plot(
Overlay Term List( Operator ),
Plot By Term List( Part )
)}}}
),
SendToReport(
Dispatch( {"Response new Y"}, "Operator", OutlineBox, {Close( 1 )} ),
Dispatch( {"Response new Y"}, "Part", OutlineBox, {Close( 1 )} ),
Dispatch( {"Response new Y"}, "Instrument", OutlineBox, {Close( 1 )} ),
Dispatch(
{"Response new Y"},
"Operator*Instrument",
OutlineBox,
{Close( 1 )}
),
Dispatch( {"Response new Y"}, "Part*Instrument", OutlineBox, {Close( 1 )} )
)
);