Re: [R-SIG-Mac] Problem running TOBIT for R 3.2 at SPSS 24 Interface MAC Sierra 10.12.1

2016-12-08 Thread Peter Dalgaard
It really should be SPSS's responsibility to track these issues. They are 
sponging off our work, precariously close to overstepping the license 
conditions, creating new problems, then expecting us to come and fix them.

As for the concrete issue, you seem to be bitten by what was a major annoyance 
in the 3.2 series: pbkrtest requiring R >= 3.2.3 and hence all packages 
depending on it (like car) doing so as well. 

If SPSS hardcodes the R version, you are up the proverbial creek... You might 
get away with hacking the DESCRIPTION file for pbkrtest to make it install (not 
work, but you likely won't use it anyway) under 3.2.0. Of course, if it breaks 
you can keep both pieces.

I'd probably be more inclined to save out the data set, fire up an appropriate 
version of R (or RStudio), do

library(foreign)
d <- read.spss("myfile.sav", to.data.frame=TRUE)
library(AER)


and so forth.

You may need to study the R syntax a little. Achim and Christian wrote an 
inexpensive book called "Applied Econometrics with R"

-pd

> On 8 Dec 2016, at 10:34 , Andreas Schröder  
> wrote:
> 
> Dear R-SIG-Mac members, 
> 
> This is my first post and I would like to thank you first of all for helping 
> out fellow users of R!
> 
> I am currently doing my master thesis and struggle with making the TOBIT 
> regression run on my SPSS 24, operated with Mac (OS Sierra 10.12.1). 
> 
> I use SPSS 24 and have the installer plugin-in for R successfully  installed. 
> I installed the correct R version 3.2 and also XQuartz but if I try to 
> execute the TOBIT regression (I can choose it in my SPSS menu now) I get 
> constantly dialogues showing that certain packages would be missing (CAR, AED 
> etc.). (Pic 1). Apparently, those packages have been added later to R (higher 
> r version than the one mandated by my spss 24 version). I downloaded the 
> versions R 3.2.5 that is referred to in the first picture but once I try 
> installing it, I get displayed another error message by SPSS that the version 
> of R was incorrect. Also manually installing the AER package on R 3.2. did 
> not work for me because I do not know where to find and executable file 
> within the AER package. (Pic 3)
> 
> 
> I already spent yesterday and partly the day before to find my mistake but I 
> couldn’t resolve the issue.
> I am glad to receive any kind of input!
> 
> Best, 
> 
> Andreas
> 
> 
> ___
> R-SIG-Mac mailing list
> R-SIG-Mac@r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-mac

___
R-SIG-Mac mailing list
R-SIG-Mac@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-mac

[R-SIG-Mac] Problem running TOBIT for R 3.2 at SPSS 24 Interface MAC Sierra 10.12.1

2016-12-08 Thread Andreas Schröder
Dear R-SIG-Mac members, 

This is my first post and I would like to thank you first of all for helping 
out fellow users of R!

I am currently doing my master thesis and struggle with making the TOBIT 
regression run on my SPSS 24, operated with Mac (OS Sierra 10.12.1). 

I use SPSS 24 and have the installer plugin-in for R successfully  installed. I 
installed the correct R version 3.2 and also XQuartz but if I try to execute 
the TOBIT regression (I can choose it in my SPSS menu now) I get constantly 
dialogues showing that certain packages would be missing (CAR, AED etc.). (Pic 
1). Apparently, those packages have been added later to R (higher r version 
than the one mandated by my spss 24 version). I downloaded the versions R 3.2.5 
that is referred to in the first picture but once I try installing it, I get 
displayed another error message by SPSS that the version of R was incorrect. 
Also manually installing the AER package on R 3.2. did not work for me because 
I do not know where to find and executable file within the AER package. (Pic 3)


I already spent yesterday and partly the day before to find my mistake but I 
couldn’t resolve the issue.
I am glad to receive any kind of input!

Best, 

Andreas

___
R-SIG-Mac mailing list
R-SIG-Mac@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-mac