Analyse av rang-ordnete data
Av Ronny Klæboe Dato: 25.2.2010
Utklipp fra SEMNET
You have rankings and so should fit ranking models, like the Bradley-Terry-Luce model, which is actually fairly easy to do. Two nice texts on this are:
Fligner, M. A., & Verducci, J. S. (Eds.). (1993). Probability models and statistical analysis of ranking data. New York: Springer-Verlag.
Marden, J. I. (1995). Analyzing and modeling rank data. New York: Chapman & Hall.
Böckenholt, U. (1996). Analyzing multiattribute ranking data: Joint and conditional approaches.
British Journal of Mathematical and Statistical Psychology, 49, 57-78.
Critchlow, D. E., Fligner,M. A.,&Verducci, J. S. (1991). Probability models on rankings. Journal of Mathematical Psychology, 35, 294-318.
You can also fit latent class extensions of ranking models, as Croon (1989) has done, I’ve also fit a latent class version of the BTL ranking model to partial rankings and gave a review and some additional refs that you might find useful in the following (available at my website):
DeCarlo, L. T., & Luthar, S. S. (2000). Analysis and class validation of a measure of parental values perceived by early adolescents: An application of a latent class model for rankings. Educational and Psychological Measurement, 60, 578-591.
You can easily fit the models with free software such as LEM.