Skip to main content
. Author manuscript; available in PMC: 2011 Oct 1.
Published in final edited form as: J Stat Plan Inference. 2010 Oct 1;140(10):2801–2808. doi: 10.1016/j.jspi.2010.03.002

Figure 1.

Figure 1

Panel (a) shows the data. The figure plots monocyte count versus day of the first cycle chemotherapy for n = 47 patients. Panel (b) shows prediction for y~ arranged by x~ from lowest (“1”) to highest (“5”) level of carboplatinum. Panel (c) shows for comparison prediction without covariate-dependent clustering. By construction prediction in (c) is identical for all patients.