Lui estimators

[#1]

How can Liu's estimations be calculated using JMP pro?!

Attached
Real data obtained from the Central Child Hospital in Baghdad - Iraq, representing the number of cases of congenital defects of children in the heart and circulatory system for the period (2006-2011).

regards

[#2]

I have two comments that might help.

First of all, I showed how you can make sure that JMP finds R after you install it. Here is the JSL code for that purpose. Does the path that I use match the path that you should use? Please make sure that the location is correct.

// make sure JMP can find the desired installed version of R
Set Environment Variable( "R_HOME", "C:\Program Files\R\R-4.1.3" );

Your R script refers to a dta data frame, but that is a JMP data table that that you did not send. You sent JMP data columns as individual vectors to R instead. So you must either create the data frame in R from the vectors that you sent, or send the data table instead of the vectors and use it in R. JMP creates a data frame for R automatically, so the latter approach seems easier and more efficient. See my second example above.

Also, be sure to call this function at the end of your script:

R Term();

[#3]

dear sir

dta = Open( "/D:/Rdata/fatima data.jmp" );

the location is correct.

I don't know how to convert a table to data frame using JMP pro.

My main target is to implement (Liu Regression) through JmpPro, even if the data is hypothetical from a simulation.

[#4]

The R extension to JMP is documented in the Scripting Guide, available in the JMP Documentation Library, under the Help Pull Down Menu.  Here is a copy of the mapping of JMP data structures to R structures, followed by an example of Sending a JMP data table to a Data Frame in R.

Names Default To Here( 1 );
// Open Data Table: big class.jmp
// → Data Table( "big class" )
dt = Open( "$SAMPLE_DATA/big class.jmp" );
R Init();
R Send( dt );
R Submit( "print(dt)" );
R Term();

[#5]

Dear Sir

The code you sent has been executed successfully.
But I am trying to implement Leo regression on my data
attachments:
A picture of the output, and I don't know where the error is?!

Names Default to Here( 1 );

// make sure JMP can find the desired installed version of R
Set Environment Variable( "R_HOME", "C:\Program Files\R\R-4.1.3" );

// Open Data Table: PoiReg.jmp
dta = Open( "/D:/Rdata/PoiReg.jmp" );
x1 = :x1 << Get As Matrix;
x2 = :x2 << Get As Matrix;
x3 = :x3 << Get As Matrix;
x4 = :x4 << Get As Matrix;
x5 = :x5 << Get As Matrix;
x6 = :x6 << Get As Matrix;
x7 = :x7 << Get As Matrix;
y = :y << Get As Matrix;

Close( dta, No Save );

// connect to R session
R Init( );

// send JMP data as vectors
R Send( x1 );
R Send( x2 );
R Send( x3 );
R Send( x4 );
R Send( x5 );
R Send( x6 );
R Send( x7 );
R Send( y );

// use centered function in liureg package with entire data set
R Submit("
library(Matrix)
library(glmnet)
library(liureg)
library (readxl)
## liu regression

lu.reg <- liu(y~., data=as.data.frame(dta), d=seq(0, 0.1, 0.1), scaling= \!"centered\!")
print(lu.reg)
");

// close R connection
R Term();

[#6]

Your error message is coming from R.  The code is looking for a data frame called DTE. From my examination of your code, you did not Send the data table to R from JMP.

[#7]

Dear Sir

i don't know how to do that?!
the data is opened in jmp correctly

[#8]

How to move a data table from JMP to R was previously detailed in a response I made on Monday.  An example illustrating rhe openinf of a table in JMP, Sending it to R, and then finally printing the table in R was provided.  All of this is also detailed in a specific section in the Scripting Guide on Extending JMP with R.  I strongly suggest you read and study that section. 

[#9 · Accepted solution]

You send the individual vectors but then you refer to the data table in the liureg function call. You didn't send the data table as a data frame. You didn't make a data frame in R from the vectors. There are several approaches but it seems to me that the easiest way is to send the JMP data table as a data frame instead of individual vectors. I should you how to do it both ways but you mixed them together and left out the important parts in the process.

Try this script:

Names Default to Here( 1 );

// make sure JMP can find the desired installed version of R
Set Environment Variable( "R_HOME", "C:\Program Files\R\R-4.1.3" );

// Open Data Table: PoiReg.jmp
dta = Open( "/D:/Rdata/PoiReg.jmp" );

// connect to R session
R Init( );

// send JMP data as vectors
R Send( dta );

// use centered function in liureg package with entire data set
R Submit("
library(Matrix)
library(glmnet)
library(liureg)
library (readxl)
## liu regression

lu.reg <- liu(y~., data=dta, d=seq(0, 0.1, 0.1), scaling= \!"centered\!")
print(lu.reg)
");

// close R connection
R Term();

[#10]

Yes, great job!!. R codes were run and executed through the JMPpro script. I just added the summary function: summary(lu.reg)
In the next step I will try to ask the developers of JMPpro, to convert the Liu regression method into a plugin.

Thank you very much to everyone who helped me
Thank you very much Mr.markbailey

regards

[#11]

Names Default to Here( 1 );

// make sure JMP can find the desired installed version of R
Set Environment Variable( "R_HOME", "C:\Program Files\R\R-4.1.3" );

// Open Data Table: fatima data.jmp
dta = Open( "/D:/Rdata/fatima data.jmp" );
x1 = :the totals of the children weights << Get As Matrix;
x2 = :age sums of children parents << Get As Matrix;
x3 = :age sums of the mothers of the children << Get As Matrix;
x4 = :number of infected male children << Get As Matrix;
x5 = :number of infected female children << Get As Matrix;
x6 = :number of infected children born from consanguineous marriages << Get As Matrix;
x7 = :children whose mothers were exposed to radiation during pregnancy << Get As Matrix;
y = :total children with congenital heart defects << Get As Matrix;

Close( dta, No Save );

// connect to R session
R Init( );

// send JMP data as vectors
R Send( x1 );
R Send( x2 );
R Send( x3 );
R Send( x4 );
R Send( x5 );
R Send( x6 );
R Send( x7 );
R Send( y );

// use mcreg function in mcr package with entire data set
R Submit("
library(liureg)
mod <-liu(y~., data = as.data.frame(dta), d = seq(0, 0.1, 0.01), scaling = "centered")
print( mod )
## Liu Var-Cov matrix
vcov(mod)
## Liu biasing parameters by researchers
dest(mod)
## Liu related statistics
lstats(mod)
");

this is my script to run (liu regression) from jmp to R.

not run?!

#note: the data attached in below