Hi
I would appreciate your opinion/advice on the following:
I have a very large dataset (21 occasions, 19158 individuals) and am using Burnham’s model for joint live-dead analysis. My results table shows very large AICc values and very large differences in AICc-values (these are the 10 best models):
- Code: Select all
model npar AICc DeltaAICc weight Deviance
78 S(~time)p(~ageclass)r(~time)F(~sex) 47 118320.2 0 1 34072.4
76 S(~time)p(~ageclass)r(~time)F(~ageclass) 47 118666.6 346 0 34418.9
75 S(~time)p(~ageclass)r(~1)F(~sex) 28 118697.6 377 0 34487.9
73 S(~time)p(~ageclass)r(~1)F(~ageclass) 28 119032.4 712 0 34822.7
3 S(~ageclass)p(~ageclass)r(~1)F(~sex) 10 119182.4 862 0 35008.7
6 S(~ageclass)p(~ageclass)r(~time)F(~sex) 29 119347.5 1027 0 35135.8
77 S(~time)p(~ageclass)r(~time)F(~1) 45 119362.7 1043 0 35118.9
49 S(~sex)p(~ageclass)r(~1)F(~ageclass) 10 119540.4 1220 0 35366.7
54 S(~sex)p(~ageclass)r(~time)F(~sex) 29 119567.0 1247 0 35355.3
52 S(~sex)p(~ageclass)r(~time)F(~ageclass) 29 119618.6 1298 0 35406.9
Should I worry about these large values?
And what could be causing them?
I have already tried using new initial values for the second best model, but the results are the same, so lack of convergence does not seem to be the problem (moreover nearly all differences between AICc values are large).
I haven’t corrected the AICc values for the median c-hat yet, but the first rough calculations of the median c-hat showed only little overdispersion (c-hat ~ 1.1-1.2).
Many thanks,
Maja