[R] DIF

[Phil Chalmers]

As well, the mirt package contains a function for DIF using likelihood 
ratio tests via multiple-group estimation methods (the multiple group 
estimation generally goes beyond simply testing for DIF), as well Wald 
tests if the information matrix was computed. Hope that helps.

Phil

On Wednesday, December 10, 2014 2:20:51 PM UTC-5, munevver kaya wrote:
>
> Thanks, Achim and Richard, 
> I will take into consideration your solutions. 
> Best, 
>
> On Tue, Dec 9, 2014 at 11:36 PM, Achim Zeileis <Achim.... at uibk.ac.at 
> <javascript:>> 
> wrote: 
>
> > On Tue, 9 Dec 2014, Richard M. Heiberger wrote: 
> > 
> >  I recommend the likert() function in the HH package. 
> >> 
> >> install.packages("HH") 
> >> library(HH) 
> >> ?likert 
> >> 
> > 
> > I think this only visualizes the polytomous items but provides no formal 
> > inference for IRT modeling and DIF testing. 
> > 
> > For fitting polytomous IRT models (PCM, RSM, etc.) there are various R 
> > packages available, probably most prominently the "eRm" package. This 
> also 
> > includes several tests for DIF. But many other approaches are also 
> > available (including the "lordif" package). A good first overview is 
> given 
> > in the Psychometrics task view on CRAN, see: http://CRAN.R-project.org/ 
> > view=Psychometrics 
> > 
> > hth, 
> > 
> > Z 
> > 
> > 
> >> 
> >> On Tue, Dec 9, 2014 at 3:22 AM, munevver kaya <munevv... at gmail.com 
> <javascript:>> 
> >> wrote: 
> >> 
> >>> Hello, 
> >>> I will analyze polytomous differential item functioning for IRT. I 
> have a 
> >>> Likert type scale. For example, I want to analyze items in term of 
> >>> gender. 
> >>> Is lordifsufficient for this or are there any other packages in R 
> >>> programme? 
> >>> Best Regards, 
> >>> 
> >>>         [[alternative HTML version deleted]] 
> >>> 
> >>> ______________________________________________ 
> >>> R-h... at r-project.org <javascript:> mailing list -- To UNSUBSCRIBE and 
> more, see 
> >>> https://stat.ethz.ch/mailman/listinfo/r-help 
> >>> PLEASE do read the posting guide http://www.R-project.org/ 
> >>> posting-guide.html 
> >>> and provide commented, minimal, self-contained, reproducible code. 
> >>> 
> >> 
> >> ______________________________________________ 
> >> R-h... at r-project.org <javascript:> mailing list -- To UNSUBSCRIBE and 
> more, see 
> >> https://stat.ethz.ch/mailman/listinfo/r-help 
> >> PLEASE do read the posting guide http://www.R-project.org/ 
> >> posting-guide.html 
> >> and provide commented, minimal, self-contained, reproducible code. 
> >> 
> >> 
>
>         [[alternative HTML version deleted]] 
>
> ______________________________________________ 
> R-h... at r-project.org <javascript:> mailing list -- To UNSUBSCRIBE and 
> more, see 
> https://stat.ethz.ch/mailman/listinfo/r-help 
> PLEASE do read the posting guide 
> http://www.R-project.org/posting-guide.html 
> and provide commented, minimal, self-contained, reproducible code. 
>