. Author manuscript; available in PMC: 2024 Jan 12.

Published in final edited form as: J Comput Graph Stat. 2023 Jan 12;32(3):1131–1144. doi: 10.1080/10618600.2022.2149540

Table 2.

The five cluster-specific mean trajectories used in Case 2

Cluster 1	Cluster 2	Cluster 3	Cluster 4
$f_{c_{1}}^{(1)} (t) = 8 t - 0.6 t^{2}$ ,	$f_{c_{2}}^{(1)} (t) = 20 - 6 t + 0.3 t^{2}$ ,	$f_{c_{3}}^{(1)} (t) = 0$ ,	$f_{c_{4}}^{(1)} (t) = 20$ ,
$f_{c_{1}}^{(2)} (t) = t$ ,	$f_{c_{2}}^{(2)} (t) = - t$ ,	$f_{c_{3}}^{(2)} (t) = - 7 t + 0.5 t^{2}$ ,	$f_{c_{4}}^{(2)} (t) = - 20 + t$ ,
$f_{c_{1}}^{(3)} (t) = - 10 + 6 t - 0.4 t^{2}$ ,	$f_{c_{2}}^{(3)} (t) = - 10 + 6 t - 0.4 t^{2}$ ,	$f_{c_{3}}^{(3)} (t) = 0.2 t$ ,	$f_{c_{4}}^{(3)} (t) = 0.2 t$ ,
$f_{c_{1}}^{(4)} (t) = - 1 + t$ ,	$f_{c_{2}}^{(4)} (t) = - 1 + t$ ,	$f_{c_{3}}^{(4)} (t) = - 1 + t$ ,	$f_{c_{4}}^{(4)} (t) = 10 + 2 t - 0.2 t^{2}$ ,
$f_{c_{1}}^{(5)} (t) = - 2 t + 0.1 t^{2}$	$f_{c_{2}}^{(5)} (t) = - 2 t + 0.1 t^{2}$	$f_{c_{3}}^{(5)} (t) = - 2 t + 0.1 t^{2}$	$f_{c_{4}}^{(5)} (t) = - 2 t + 0.1 t^{2}$