Hi,
du solltest die Variable auf keinen Fall in Gruppen sortieren. Wenn die Verteilung Verletzungen der Annahmen impliziert (check das durch Residuendiagnostik), gibt es Lösungen.
Durch Gruppenbildung verschenkst du Information und senkst die Power:
Preacher, K.J., Rucker, D.D., MacCallum, R.C., & Nicewander, W.A. (2005). Use of the extreme groups approach: A critical reexamination and new recommendations. Psychological Methods, 10, 178-192.
http://kuscholarworks.ku.edu/dspace/bit ... r_2005.pdfBaneshi, M.R., & Talei, A.R. (2011). Dichotomisation of Continuous Data: Review of Methods, Advantages, and Disadvantages. Iranian Journal of Cancer Prevention, 4(1), 26-32.
Owen, S.V., & Froman, R.D. (2005). Why carve up your continuous data? Research in Nursing and Health, 28, 496-503.
Royston, P., Altman, D.G., & Sauerbrei, W. (2006). Dichotomizing continuous predictors in multiple regression: a bad idea. Statistics in Medicine, 25(1), 127-141.
http://www-psychology.concordia.ca/fac/ ... oyston.pdfShentu, Y., & Xie, M. (2010). A note on dichotomization of continuous response variable in the presence of contamination and model misspecification. Statistics in Medicine, 29, 2200-2214.
http://www.stat.rutgers.edu/home/mxie/R ... /dicho.pdfNg, C.G. (2010). Outcomes of dichotomizing a continuous variable in the psychiatric early readmission prediction model. MJP Online Early, MJP-02-05-10.
http://mjpsychiatry.org/index.php/mjp/a ... File/78/72Streiner, D.L. (2002). Breaking up is hard to do: the heartbreak of dichotomizing continuous data. Canadian Journal of Psychiatry, 47(3), 262-266.
http://www.humanstress.ca/documents/pdf ... -split.pdfIrwin, J. R., & McClelland, G. H. (2003). Negative consequences of dichotomizing continuous predictor variables. Journal of Marketing Research, 40, 366-371.
Fitzsimons, G.J. (2008). Death to Dichotomizing. Journal of Consumer Research, 35(1), 5-8.
Gruß
Holger