Table 2.

Conditional and marginal distributions for ordinal traits generated from nonproportional odds models

K = 3
P(Y <= 1 | dd) = 0.70	P(Y <= 1 | dD) = 0.30	P(Y <= 1 | DD) = 0.10	P(Y = 1) = 0.48
P(Y <= 2 | dd) = 0.90	P(Y <= 2 | dD) = 0.60	P(Y <= 2 | DD) = 0.50	P(Y = 2) = 0.26
			P(Y = 3) = 0.26
K = 4
P(Y <= 1 | dd) = 0.70	P(Y <= 1 | dD) = 0.30	P(Y <= 1 | DD) = 0.10	P(Y = 1) = 0.48
P(Y <= 2 | dd) = 0.80	P(Y <= 2 | dD) = 0.50	P(Y <= 2 | DD) = 0.35	P(Y = 2) = 0.16
P(Y <= 3 | dd) = 0.90	P(Y <= 3 | dD) = 0.70	P(Y <= 3 | DD) = 0.60	P(Y = 3) = 0.16
			P(Y = 4) = 0.21
K = 5
P(Y <= 1 | dd) = 0.70	P(Y <= 1 | dD) = 0.20	P(Y <= 1 | dd) = 0.05	P(Y = 1) = 0.43
P(Y <= 2 | dd) = 0.77	P(Y <= 2 | dD) = 0.45	P(Y <= 2 | dd) = 0.35	P(Y = 2) = 0.17
P(Y <= 3 | dd) = 0.85	P(Y <= 3 | dD) = 0.65	P(Y <= 3 | dd) = 0.55	P(Y = 3) = 0.14
P(Y <= 4 | dd) = 0.92	P(Y <= 4 | dD) = 0.80	P(Y <= 4 | dd) = 0.75	P(Y = 4) = 0.12
			P(Y = 5) = 0.15
K = 6
P(Y <= 1 | dd) = 0.60	P(Y <= 1 | dD) = 0.20	P(Y <= 1 | DD) = 0.05	P(Y = 1) = 0.38
P(Y <= 2 | dd) = 0.68	P(Y <= 2 | dD) = 0.32	P(Y <= 2 | DD) = 0.35	P(Y = 2) = 0.12
P(Y <= 3 | dd) = 0.72	P(Y <= 3 | dD) = 0.52	P(Y <= 3 | DD) = 0.48	P(Y = 3) = 0.12
P(Y <= 4 | dd) = 0.76	P(Y <= 4 | dD) = 0.68	P(Y <= 4 | DD) = 0.60	P(Y = 4) = 0.09
P(Y <= 5 | dd) = 0.80	P(Y <= 5 | dD) = 0.80	P(Y <= 5 | DD) = 0.72	P(Y = 5) = 0.08
			P(Y = 6) = 0.21