[R] Zeta-squared transformation use R?

[jlh.membership]

Yes, absolutely! Sorry about that:

zeta.sq <- function(data) {
  z       <- scale(data)
  zeta.sq <- ifelse(z>0,1+z^2,1/(1+z^2))
}



-----Original Message-----
From: Michael Dewey [mailto:info at aghmed.fsnet.co.uk] 
Sent: Monday, July 14, 2014 6:57 AM
To: jlh.membership; 'Miles Yang'
Cc: r-help at r-project.org
Subject: Re: [R] Zeta-squared transformation use R?

At 18:14 13/07/2014, jlh.membership wrote:
>Hi Miles,
>
>If I read the paper correctly, zeta-squared is
>simply: (1+z^2) for z>=0, and 1/(1+z^2) for z<=0, where z is the 
>z-score (Eqn. 11 in the paper). Z-scores can be calculated in R using 
>the scale(...) function. So this should produce a zeta-squared transformation.
>
>zeta.sq <- function(data) {
>   z.sq    <- scale(data)^2
>   zeta.sq <- ifelse(z.sq>0,1+z.sq,1/(1+z.sq)) }

I would have thought the test needed to be on z to be consistent with the description above, not z^2?


>Simple example: 100 respondents, 3 questions. 
>First question scored on (1,7), second question 
>scored on (-10,10), third question scored on (0,100) in 0.01 increments.
>
>set.seed(1)    # for reproducible example
>df <- data.frame(Q1=sample(1:7,100,replace=T),
>                  Q2=sample(-10:10,100,replace=T),
>                  Q3=sample(seq(0,1,len=101),100,replace=T))
># transform the data...
>result <- zeta.sq(df)
>
>Regards,
>
>John Howard
>Prism Marketing Group
>http://www.prismmg.com
>
>
>-----Original Message-----
>From: Miles Yang [mailto:miles2yang at gmail.com]
>Sent: Saturday, July 12, 2014 7:31 AM
>To: Jeff Newmiller
>Cc: r-help at r-project.org
>Subject: Re: [R] Zeta-squared transformation use R?
>
>Hi Jeff,
>
>Yes, I searched that but it comes out 
>"zeta-squared coefficient" instead of transformation method.
>
>I hope if there is someone have the experience 
>in applying "zeta-squared transformation" in R?
>
>Appreciate any help on this.
>
>Regards,
>miles
>
>
>On Sat, Jul 12, 2014 at 4:01 PM, Jeff Newmiller <jdnewmil at dcn.davis.ca.us>
>wrote:
>
> > Have you tried
> >
> > RSiteSearch("zeta squared")
> >
> > ?
> >
> > Someone may recognize this, but it never hurts to communicate where
> > you have already looked.
> >
> > ---------------------------------------------------------------------------
> > Jeff Newmiller                        The     .....       .....  Go Live...
> > DCN:<jdnewmil at dcn.davis.ca.us>        Basics: ##.#.       ##.#.  Live
> > Go...
> >                                       Live:   OO#.. Dead: OO#..  Playing
> > Research Engineer (Solar/Batteries            O.O#.       #.O#.  with
> > /Software/Embedded Controllers)               .OO#.       .OO#.  rocks...1k
> > ----------------------------------------------------------------------
> > ----- Sent from my phone. Please excuse my brevity.
> >
> > On July 11, 2014 9:44:43 PM PDT, Miles Yang <miles2yang at gmail.com> wrote:
> > >Hi R-helpers,
> > >
> > >Is there any packages can do "*zeta-squared transformation*"?
> > >
> > >The Zeta-squared transformation comes from the following article:
> > >Standardizing Variables in Multiplicative Choice Models Lee G. Cooper
> > >and Masao Nakanishi Journal of Consumer Research, Vol. 10, No. 1
> > >(Jun., 1983), pp. 96-108
> > >
> > >Thanks for any help in advance.
> > >
> > >miles
> >
> >
>
>
>--
>－－－－－－－－－－－－－－－－－－
>Miles Yang
>Mobile：+61-411-985-538
>E-mail：miles2yang at gmail.com
>Web: Miles Yang Website <https://sites.google.com/site/miles2yang/>
>－－－－－－－－－－－－－－－－－－
>
>         [[alternative HTML version deleted]]

Michael Dewey
info at aghmed.fsnet.co.uk
http://www.aghmed.fsnet.co.uk/home.html