Triple R: A package for round robin analyses using R

Triple R is a package for the statistic software R that analyzes multivariate Round-Robin data using a Social Relations Model (SRM) approach (Kenny, 1994; Kenny, Kashy, & Cook, 2006). Triple can be used for analyzing data based on a single, or on multiple Round-Robin groups. Given this kind of data, Triple R has two advantages over SOREMO (Kenny, 1998), the classic software for analyzing Round-Robin data: First, Triple R is not restricted regarding to the number of participants. Second, Triple R uses within-group t-tests, which were shown to be superior to the jackknife method (Lashley & Bond, 1997). Classic between-group t-tests (weighted for group size) are provided as well.

Triple R consists of one versatile function for the analysis of a single Round-Robin group. The function gives results for SRM analyses based on four variants of data:

• univariate analysis of one manifest variable (i.e. actor, partner and relationship variance, actor-partner covariance and relationship variance)
• univariate SRM analyses on construct level, with two indicators defining one construct (in this case, error variance can be calculated beyond the indices mentioned above)
• bivariate SRM analyses for two manifest variables
• bivariate SRM analyses between two constructs, each measured with two manifest variables (i.e. in this case four round robin matrices have to be provided)

The estimation of the SRM parameters is based on formulae provided by Kenny (1994; p. 236-244). For tests of significance, Triple R computes standard errors by using formulae published by Bond and Lashley (1996) for the case of a univariate SRM analysis. The formulae for the standard errors of the bivariate SRM parameters were kindly provided to us by C. F. Bond in personal communication.

Download/ Installation

To use Triple R, the statistic software R needs to be installed first. R can be obtained free of charge at http://www.r-project.org. Although not necessary, it is convenient to additionally use an editor that has been customized to R (e.g., Tinn-R for Windows, or TextMate for Mac OS X).

The latest stable version of the TripleR package can be directly installed from CRAN into the R library by typing:

into your R console. Package binaries are provided both for Windows and Mac OS X; R version >= 2.9 is needed. More information on how to install packages can be found on R-Wiki. Note that you need to have installation rights for the program folders of R. Please ask your administrator if you have problems with installing R packages.

For current developments of the package, also see R-Forge: https://r-forge.r-project.org/projects/tripler/. Developer versions of TripleR can be installed from the R-Forge repository:

Please be aware that these developer versions can be unstable or might provide different results. For productive usage we strongly recommend using only the official releases (stable versions) provided on CRAN.

After installation you have to load the package from the library by typing:

Type ?RR for online-help and on how to use the Round-Robin function implemented in Triple R. For an example analysis please copy and paste the example code into the R console.

SRM effects can be read out by typing:

Citation

Please cite Triple R if you use this package in your own research:

Schmukle, S.C., Schönbrodt, F.D., & Back, M.D. (2010). Triple R: A package for round robin analyses using R (version 0.3). Retrieved from http://www.persoc.net/Toolbox/TripleR.

References

Bond, C. F., Jr., & Lashley, B. R. (1996). Round-robin analyses of social interactions: Exact and estimated standard errors. Psychometrika, 61, 303-311.

Kenny, D. A. (1994). Interpersonal perception: A social relations analysis. New York: Guilford Press.

Kenny, D. A. (1998). SOREMO [Computer software]. University of Connecticut.

Kenny, D. A., Kashy, D. A., & Cook, W. L. (2006). Dyadic data analysis. New York: Guilford.

Lashley, B. R., & Bond, C. F., Jr. (1997). Significance testing for round robin data. Psychological Methods, 2, 278-291.