. Author manuscript; available in PMC: 2011 Jun 22.

Published in final edited form as: Comput Stat Data Anal. 2009 Feb 15;53(4):1110–1121. doi: 10.1016/j.csda.2008.10.019

Table 3.

Models used for assessing the performance of the tree procedure. The covariate Z_ik’s are generated from a discrete uniform distribution over values (1/10, 2/10, …, 10/10).

	Model Form
A′	λ_ik(t) = exp (−1 + 2 × 1_{_Z_{_ik₁≤0.5}} + 1_{_Z_{_ik₂≤0.5}}) · w_i, with w_i ~ Γ(1, 1)
B′	λ_ik(t) = exp (−1 + 2 × 1_{_Z_{_ik₁≤0.5}} + 1_{_Z_{_ik₂≤0.5}} + w_i), with w_i ~ N (0, 1)
C′	λ_ik(t) = exp (−1 + 2 × 1_{_Z_{_ik₁≤0.5}} + 1_{_Z_{_ik₂≤0.5}}), not absolutely continuous
D′	λ_ik(t) = exp (1 + 2 × 1_{_Z_{_ik₁≤0.5}} + 1_{_Z_{_ik₂≤0.5}}), absolutely continuous
E′	λ_ik(t) = λ₀(t) exp (−1 + 2 × 1_{_Z_{_ik₁≤0.5}}) + 1_{_Z_{_ik₂≤0.5}} · w_i, with w_i ~ Γ(1, 1), λ₀(t) = αλt^α⁻¹, α = 1.5, and λ = 0.1