Table 1. Model selection results for fitted models ranked by AIC_c with number of parameters (K), log likelihood (LL), and AIC_c weights (w_i) to estimate black bear density in south-central Missouri, USA, for extensive and intensive sampling designs.

Design	Model	K	LL	AICc	ΔAICc	wi
Extensive	g0(bk), σ(.)	4	−254.5	519.0	0.0	0.5
	g0(bk), σ(sex)	5	−253.6	520.3	1.4	0.3
	g0(Bk), σ(.)	4	−255.9	521.8	2.8	0.1
	g0(Bk), σ(sex)	5	−254.9	523.0	4.0	0.1
	g0(sex), σ(sex)	5	−266.6	546.4	27.4	0.0
	g0(.), σ(.)	3	−274.0	555.1	36.1	0.0
	g0(.), σ(sex)	4	−272.7	555.4	36.4	0.0
	g0(b), σ(.)	4	−273.2	556.4	37.4	0.0
	g0(b), σ(sex)	5	−271.8	556.7	37.8	0.0
	g0(sex), σ(.)	4	−273.7	557.3	38.3	0.0
	g0(t), σ(.)	8	−273.6	572.1	53.1	0.0
	g0(t), σ(sex)	9	−272.3	574.6	55.6	0.0
Intensive	g0(bk), σ(.)	4	−1175.8	2360.0	0.0	0.8
	g0(bk), σ(sex)	5	−1175.8	2362.2	2.2	0.2
	g0(Bk), σ(.)	4	−1215.7	2439.9	79.9	0.0
	g0(Bk), σ(sex)	5	−1215.2	2441.0	81.0	0.0
	g0(b), σ(.)	4	−1246.6	2501.8	141.8	0.0
	g0(sex), σ(.)	4	−1246.9	2502.3	142.3	0.0
	g0(.), σ(.)	3	−1249.0	2504.3	144.3	0.0
	g0(t), σ(.)	8	−1245.0	2507.7	147.7	0.0
	g0(sex), σ(sex)	5	−1299.5	2609.6	249.7	0.0
	g0(.), σ(sex)	4	−1301.0	2610.6	250.6	0.0
	g0(b), σ(sex)	5	−1300.9	2612.5	252.5	0.0
	g0(t), σ(sex)	9	−1296.7	2613.6	253.6	0.0

We fitted models using the half-normal detection function with baseline capture probability (g₀) and scale parameter (σ). Effects on g₀ and σ included time as a factor (t), global learned response (b), snare-specific learned response (bk), and a snare-specific Markovian response (Bk), and sex. Parameters with “.” indicate no effect.