[Rd] How to do a "Box's M" Test with

[Duncan Murdoch]

On 27/10/2017 8:10 AM, Morkus via R-devel wrote:
> Trying to get past a frustrating error to do a "simple" Box's M test using Java.
> 
> The Box's M test says it will work with a data.frame.
> 
> Here's the setup code:
> 
> REXP myDf = REXP.createDataFrame(new RList(
> new REXP[]
> {
> new REXPDouble(d1),
> new REXPDouble(d2),
> new REXPDouble(d3),
> new REXPDouble(d4),
> new REXPInteger(d5)
> }));
> 
> Here's the call:
> 
> REXP boxMResult = rConnection.eval( "boxM(" + myDf+ "[,-5], " + myDf + " [, 5])");

I don't really know the R Java interface, but this doesn't make sense. 
You are pasting an REXP object myDf into a string to evaluate.  It would 
make sense to assign that dataframe object to an R variable, and paste 
the name of that variable into your expression, or to construct a 
language object containing the dataframe object, but I don't know how to 
do those things.

Duncan Murdoch

> 
> But, I keep getting syntax errors.
> 
> If this code isn't right, how do you build a data.frame R will like?  No examples I can find, anywhere.
> 
> Not sure what to try next. I've tried just sending a string with everything commented, but nothing I've tried works.
> 
> Can anyone please suggest something to try?
> 
> Thanks in advance.
> 
> - M
> 
> Sent from [ProtonMail](https://protonmail.com), Swiss-based encrypted email.
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-devel at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel
>