Lab 05: Analysis in RMark
WILD 502 - Jay Rotella
Bring in the Data and Process it
Here, the data are for imaginary swamp squirrels. There are data for 6 sampling occasions and for 2 groups: squirrels first captured when they were juveniles or when they were older. There are also 2 continuous covariates: birth (birth date) and tail (tail length). The code creates tail length squared and provides information on precipitation levels during capture work each year, which might have affected capture probability (p).
library(knitr)
library(ggplot2)
library(RMark)## This is RMark 2.2.4
## Documentation available at http://www.phidot.org/software/mark/rmark/RMarkDocumentation.zipsq <- convert.inp("http://www.montana.edu/rotella/documents/502/SwampSquirrels.inp",
group.df = data.frame(age = c("juv","older")),
covariates = c("birth", "tail"))
sq$tail.sq <- sq$tail^2
sq.pr <- process.data(sq, model = "CJS",
age.var = 1,
initial.ages = c(0, 1),
groups = ("age"))
# Create default design data
# For Phi, values are 0 or older; for p the values are 1 or older
# This provides an individual covariate for each parameter type
# that changes as the animal ages
sq.ddl = make.design.data(sq.pr,
parameters = list(Phi = list(age.bins = c(0, 1, 6)),
p = list(age.bins = c(1, 2, 6))),
right = FALSE)
# Create precipitation variable
sq.ddl$p$precip = 0 # Start with 0 for all and then over-write
sq.ddl$p$precip[sq.ddl$p$time == 2] = 0.11
sq.ddl$p$precip[sq.ddl$p$time == 3] = 1.38
sq.ddl$p$precip[sq.ddl$p$time == 4] = 1.12
sq.ddl$p$precip[sq.ddl$p$time == 5] = 1.58
sq.ddl$p$precip[sq.ddl$p$time == 6] = 1.87Set up Function for Competing Models
run.sq = function() {
# Define range of models for Phi
#
Phi.dot = list(formula = ~ 1)
Phi.age = list(formula = ~ age)
Phi.age.birth = list(formula = ~ age + birth)
Phi.age.tail = list(formula = ~ age + tail)
Phi.age.tail.sq = list(formula = ~ age + tail + tail.sq)
Phi.age.birth.tail = list(formula = ~ age + birth + tail)
Phi.age.birth.tail.sq = list(formula = ~ age + birth + tail + tail.sq)
# Define range of models for p
p.dot = list(formula = ~ 1)
p.time = list(formula = ~ -1 + time)
p.precip = list(formula = ~ precip)
# Create models for all combinations of phi & p
sq.model.list = create.model.list("CJS")
# NOTE: to avoid having all the output for each model appear when you
# call the function, add ', output=FALSE' after 'ddl=sq.ddl' below.
# Here, I don't do that so you can see the output for each model,
# but this might not be desired if you have many models.
sq.results = mark.wrapper(sq.model.list,
data = sq.pr, ddl = sq.ddl)
#
# Return model table and list of models
#
return(sq.results)
}Run the Models
The code below runs all combinations of structures in the function for \(\phi\) and \(p\). The code also produces a model-selection table.
sq.res <- run.sq()##
## Phi.age.p.dot##
## Output summary for CJS model
## Name : Phi(~age)p(~1)
##
## Npar : 3
## -2lnL: 2186.255
## AICc : 2192.278
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 0.6239824 0.2112875 0.2098589 1.0381059
## Phi:age[1,6] 1.9388934 0.3890517 1.1763520 2.7014349
## p:(Intercept) -0.9559930 0.0903185 -1.1330172 -0.7789687
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6511237 0.9284338 0.9284338 0.9284338 0.9284338
## 2 0.6511237 0.9284338 0.9284338 0.9284338
## 3 0.6511237 0.9284338 0.9284338
## 4 0.6511237 0.9284338
## 5 0.6511237
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9284338 0.9284338 0.9284338 0.9284338 0.9284338
## 2 0.9284338 0.9284338 0.9284338 0.9284338
## 3 0.9284338 0.9284338 0.9284338
## 4 0.9284338 0.9284338
## 5 0.9284338
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2776812 0.2776812 0.2776812 0.2776812 0.2776812
## 2 0.2776812 0.2776812 0.2776812 0.2776812
## 3 0.2776812 0.2776812 0.2776812
## 4 0.2776812 0.2776812
## 5 0.2776812
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2776812 0.2776812 0.2776812 0.2776812 0.2776812
## 2 0.2776812 0.2776812 0.2776812 0.2776812
## 3 0.2776812 0.2776812 0.2776812
## 4 0.2776812 0.2776812
## 5 0.2776812##
## Phi.age.birth.p.dot##
## Output summary for CJS model
## Name : Phi(~age + birth)p(~1)
##
## Npar : 4
## -2lnL: 2183.682
## AICc : 2191.72
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.8179051 0.8074219 0.2353583 3.4004520
## Phi:age[1,6] 1.8336413 0.3714952 1.1055107 2.5617719
## Phi:birth -0.0511213 0.0322114 -0.1142558 0.0120131
## p:(Intercept) -0.9486139 0.0888767 -1.1228123 -0.7744155
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6619364 0.9245319 0.9245319 0.9245319 0.9245319
## 2 0.6619364 0.9245319 0.9245319 0.9245319
## 3 0.6619364 0.9245319 0.9245319
## 4 0.6619364 0.9245319
## 5 0.6619364
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9245319 0.9245319 0.9245319 0.9245319 0.9245319
## 2 0.9245319 0.9245319 0.9245319 0.9245319
## 3 0.9245319 0.9245319 0.9245319
## 4 0.9245319 0.9245319
## 5 0.9245319
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2791637 0.2791637 0.2791637 0.2791637 0.2791637
## 2 0.2791637 0.2791637 0.2791637 0.2791637
## 3 0.2791637 0.2791637 0.2791637
## 4 0.2791637 0.2791637
## 5 0.2791637
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2791637 0.2791637 0.2791637 0.2791637 0.2791637
## 2 0.2791637 0.2791637 0.2791637 0.2791637
## 3 0.2791637 0.2791637 0.2791637
## 4 0.2791637 0.2791637
## 5 0.2791637##
## Phi.age.birth.tail.p.dot##
## Output summary for CJS model
## Name : Phi(~age + birth + tail)p(~1)
##
## Npar : 5
## -2lnL: 2183.089
## AICc : 2193.147
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.4273145 0.9301214 -0.3957235 3.2503525
## Phi:age[1,6] 1.8000886 0.3598210 1.0948393 2.5053378
## Phi:birth -0.0540289 0.0322413 -0.1172218 0.0091640
## Phi:tail 0.0257815 0.0331620 -0.0392160 0.0907791
## p:(Intercept) -0.9399963 0.0888603 -1.1141625 -0.7658300
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6607887 0.9217885 0.9217885 0.9217885 0.9217885
## 2 0.6607887 0.9217885 0.9217885 0.9217885
## 3 0.6607887 0.9217885 0.9217885
## 4 0.6607887 0.9217885
## 5 0.6607887
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9217885 0.9217885 0.9217885 0.9217885 0.9217885
## 2 0.9217885 0.9217885 0.9217885 0.9217885
## 3 0.9217885 0.9217885 0.9217885
## 4 0.9217885 0.9217885
## 5 0.9217885
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2809011 0.2809011 0.2809011 0.2809011 0.2809011
## 2 0.2809011 0.2809011 0.2809011 0.2809011
## 3 0.2809011 0.2809011 0.2809011
## 4 0.2809011 0.2809011
## 5 0.2809011
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2809011 0.2809011 0.2809011 0.2809011 0.2809011
## 2 0.2809011 0.2809011 0.2809011 0.2809011
## 3 0.2809011 0.2809011 0.2809011
## 4 0.2809011 0.2809011
## 5 0.2809011##
## Phi.age.birth.tail.sq.p.dot##
## Output summary for CJS model
## Name : Phi(~age + birth + tail + tail.sq)p(~1)
##
## Npar : 6
## -2lnL: 2170.843
## AICc : 2182.923
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) -5.6597369 2.2231079 -10.0170290 -1.3024452
## Phi:age[1,6] 1.8775891 0.3692920 1.1537768 2.6014013
## Phi:birth -0.0632787 0.0329433 -0.1278475 0.0012902
## Phi:tail 0.9156725 0.2717132 0.3831146 1.4482304
## Phi:tail.sq -0.0252988 0.0076885 -0.0403683 -0.0102293
## p:(Intercept) -0.9436603 0.0881330 -1.1164009 -0.7709196
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.664303 0.9282504 0.9282504 0.9282504 0.9282504
## 2 0.6643030 0.9282504 0.9282504 0.9282504
## 3 0.6643030 0.9282504 0.9282504
## 4 0.6643030 0.9282504
## 5 0.6643030
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9282504 0.9282504 0.9282504 0.9282504 0.9282504
## 2 0.9282504 0.9282504 0.9282504 0.9282504
## 3 0.9282504 0.9282504 0.9282504
## 4 0.9282504 0.9282504
## 5 0.9282504
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2801616 0.2801616 0.2801616 0.2801616 0.2801616
## 2 0.2801616 0.2801616 0.2801616 0.2801616
## 3 0.2801616 0.2801616 0.2801616
## 4 0.2801616 0.2801616
## 5 0.2801616
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2801616 0.2801616 0.2801616 0.2801616 0.2801616
## 2 0.2801616 0.2801616 0.2801616 0.2801616
## 3 0.2801616 0.2801616 0.2801616
## 4 0.2801616 0.2801616
## 5 0.2801616##
## Phi.age.tail.p.dot##
## Output summary for CJS model
## Name : Phi(~age + tail)p(~1)
##
## Npar : 4
## -2lnL: 2185.969
## AICc : 2194.007
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 0.3033554 0.6191434 -0.9101657 1.5168764
## Phi:age[1,6] 1.9125222 0.3778012 1.1720318 2.6530127
## Phi:tail 0.0179118 0.0330763 -0.0469177 0.0827413
## p:(Intercept) -0.9485703 0.0904427 -1.1258380 -0.7713027
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6494088 0.9261475 0.9261475 0.9261475 0.9261475
## 2 0.6494088 0.9261475 0.9261475 0.9261475
## 3 0.6494088 0.9261475 0.9261475
## 4 0.6494088 0.9261475
## 5 0.6494088
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9261475 0.9261475 0.9261475 0.9261475 0.9261475
## 2 0.9261475 0.9261475 0.9261475 0.9261475
## 3 0.9261475 0.9261475 0.9261475
## 4 0.9261475 0.9261475
## 5 0.9261475
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2791724 0.2791724 0.2791724 0.2791724 0.2791724
## 2 0.2791724 0.2791724 0.2791724 0.2791724
## 3 0.2791724 0.2791724 0.2791724
## 4 0.2791724 0.2791724
## 5 0.2791724
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2791724 0.2791724 0.2791724 0.2791724 0.2791724
## 2 0.2791724 0.2791724 0.2791724 0.2791724
## 3 0.2791724 0.2791724 0.2791724
## 4 0.2791724 0.2791724
## 5 0.2791724##
## Phi.age.tail.sq.p.dot##
## Output summary for CJS model
## Name : Phi(~age + tail + tail.sq)p(~1)
##
## Npar : 5
## -2lnL: 2174.668
## AICc : 2184.725
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) -6.7132890 2.2229803 -11.0703300 -2.3562476
## Phi:age[1,6] 2.0081081 0.3886780 1.2462992 2.7699170
## Phi:tail 0.8723724 0.2706970 0.3418063 1.4029386
## Phi:tail.sq -0.0242767 0.0076751 -0.0393198 -0.0092336
## p:(Intercept) -0.9528451 0.0890875 -1.1274567 -0.7782335
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6510651 0.9328824 0.9328824 0.9328824 0.9328824
## 2 0.6510651 0.9328824 0.9328824 0.9328824
## 3 0.6510651 0.9328824 0.9328824
## 4 0.6510651 0.9328824
## 5 0.6510651
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9328824 0.9328824 0.9328824 0.9328824 0.9328824
## 2 0.9328824 0.9328824 0.9328824 0.9328824
## 3 0.9328824 0.9328824 0.9328824
## 4 0.9328824 0.9328824
## 5 0.9328824
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.278313 0.278313 0.278313 0.278313 0.278313
## 2 0.278313 0.278313 0.278313 0.278313
## 3 0.278313 0.278313 0.278313
## 4 0.278313 0.278313
## 5 0.278313
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.278313 0.278313 0.278313 0.278313 0.278313
## 2 0.278313 0.278313 0.278313 0.278313
## 3 0.278313 0.278313 0.278313
## 4 0.278313 0.278313
## 5 0.278313##
## Phi.dot.p.dot##
## Output summary for CJS model
## Name : Phi(~1)p(~1)
##
## Npar : 2
## -2lnL: 2210.491
## AICc : 2214.503
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 2.089115 0.2336739 1.631114 2.5471163
## p:(Intercept) -1.061821 0.0894965 -1.237235 -0.8864082
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.8898407 0.8898407 0.8898407 0.8898407 0.8898407
## 2 0.8898407 0.8898407 0.8898407 0.8898407
## 3 0.8898407 0.8898407 0.8898407
## 4 0.8898407 0.8898407
## 5 0.8898407
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.8898407 0.8898407 0.8898407 0.8898407 0.8898407
## 2 0.8898407 0.8898407 0.8898407 0.8898407
## 3 0.8898407 0.8898407 0.8898407
## 4 0.8898407 0.8898407
## 5 0.8898407
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2569615 0.2569615 0.2569615 0.2569615 0.2569615
## 2 0.2569615 0.2569615 0.2569615 0.2569615
## 3 0.2569615 0.2569615 0.2569615
## 4 0.2569615 0.2569615
## 5 0.2569615
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2569615 0.2569615 0.2569615 0.2569615 0.2569615
## 2 0.2569615 0.2569615 0.2569615 0.2569615
## 3 0.2569615 0.2569615 0.2569615
## 4 0.2569615 0.2569615
## 5 0.2569615##
## Phi.age.p.precip##
## Output summary for CJS model
## Name : Phi(~age)p(~precip)
##
## Npar : 4
## -2lnL: 2179.104
## AICc : 2187.142
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 0.5843557 0.2089558 0.1748023 0.9939092
## Phi:age[1,6] 1.6961371 0.3420609 1.0256977 2.3665764
## p:(Intercept) -1.4338217 0.2058808 -1.8373480 -1.0302954
## p:precip 0.3678666 0.1420190 0.0895094 0.6462239
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.642069 0.9072485 0.9072485 0.9072485 0.9072485
## 2 0.6420690 0.9072485 0.9072485 0.9072485
## 3 0.6420690 0.9072485 0.9072485
## 4 0.6420690 0.9072485
## 5 0.6420690
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9072485 0.9072485 0.9072485 0.9072485 0.9072485
## 2 0.9072485 0.9072485 0.9072485 0.9072485
## 3 0.9072485 0.9072485 0.9072485
## 4 0.9072485 0.9072485
## 5 0.9072485
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1988725 0.2837033 0.2646748 0.2988893 0.3217129
## 2 0.2837033 0.2646748 0.2988893 0.3217129
## 3 0.2646748 0.2988893 0.3217129
## 4 0.2988893 0.3217129
## 5 0.3217129
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1988725 0.2837033 0.2646748 0.2988893 0.3217129
## 2 0.2837033 0.2646748 0.2988893 0.3217129
## 3 0.2646748 0.2988893 0.3217129
## 4 0.2988893 0.3217129
## 5 0.3217129##
## Phi.age.birth.p.precip##
## Output summary for CJS model
## Name : Phi(~age + birth)p(~precip)
##
## Npar : 5
## -2lnL: 2176.414
## AICc : 2186.472
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.6789227 0.7305315 0.2470809 3.1107645
## Phi:age[1,6] 1.6196341 0.3346467 0.9637265 2.2755418
## Phi:birth -0.0469024 0.0289931 -0.1037289 0.0099240
## p:(Intercept) -1.4328090 0.2061664 -1.8368952 -1.0287228
## p:precip 0.3702742 0.1417990 0.0923482 0.6482002
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6519284 0.9044053 0.9044053 0.9044053 0.9044053
## 2 0.6519284 0.9044053 0.9044053 0.9044053
## 3 0.6519284 0.9044053 0.9044053
## 4 0.6519284 0.9044053
## 5 0.6519284
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9044053 0.9044053 0.9044053 0.9044053 0.9044053
## 2 0.9044053 0.9044053 0.9044053 0.9044053
## 3 0.9044053 0.9044053 0.9044053
## 4 0.9044053 0.9044053
## 5 0.9044053
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1990761 0.284585 0.2653973 0.2998997 0.3229175
## 2 0.284585 0.2653973 0.2998997 0.3229175
## 3 0.2653973 0.2998997 0.3229175
## 4 0.2998997 0.3229175
## 5 0.3229175
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1990761 0.284585 0.2653973 0.2998997 0.3229175
## 2 0.284585 0.2653973 0.2998997 0.3229175
## 3 0.2653973 0.2998997 0.3229175
## 4 0.2998997 0.3229175
## 5 0.3229175##
## Phi.age.birth.tail.p.precip##
## Output summary for CJS model
## Name : Phi(~age + birth + tail)p(~precip)
##
## Npar : 6
## -2lnL: 2175.531
## AICc : 2187.612
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.2519767 0.8381723 -0.3908411 2.8947945
## Phi:age[1,6] 1.5976922 0.3262301 0.9582812 2.2371032
## Phi:birth -0.0498363 0.0290203 -0.1067160 0.0070434
## Phi:tail 0.0278200 0.0294482 -0.0298985 0.0855384
## p:(Intercept) -1.4345751 0.2064732 -1.8392625 -1.0298876
## p:precip 0.3774840 0.1417749 0.0996051 0.6553629
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.650466 0.9019234 0.9019234 0.9019234 0.9019234
## 2 0.6504660 0.9019234 0.9019234 0.9019234
## 3 0.6504660 0.9019234 0.9019234
## 4 0.6504660 0.9019234
## 5 0.6504660
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9019234 0.9019234 0.9019234 0.9019234 0.9019234
## 2 0.9019234 0.9019234 0.9019234 0.9019234
## 3 0.9019234 0.9019234 0.9019234
## 4 0.9019234 0.9019234
## 5 0.9019234
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.198921 0.2862541 0.2666291 0.3019245 0.3254845
## 2 0.2862541 0.2666291 0.3019245 0.3254845
## 3 0.2666291 0.3019245 0.3254845
## 4 0.3019245 0.3254845
## 5 0.3254845
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.198921 0.2862541 0.2666291 0.3019245 0.3254845
## 2 0.2862541 0.2666291 0.3019245 0.3254845
## 3 0.2666291 0.3019245 0.3254845
## 4 0.3019245 0.3254845
## 5 0.3254845##
## Phi.age.birth.tail.sq.p.precip##
## Output summary for CJS model
## Name : Phi(~age + birth + tail + tail.sq)p(~precip)
##
## Npar : 7
## -2lnL: 2163.95
## AICc : 2178.057
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) -5.0243332 2.0295906 -9.0023309 -1.0463356000
## Phi:age[1,6] 1.6786653 0.3385933 1.0150223 2.3423082000
## Phi:birth -0.0582659 0.0297967 -0.1166675 0.0001357313
## Phi:tail 0.8179389 0.2474912 0.3328561 1.3030216000
## Phi:tail.sq -0.0225186 0.0070058 -0.0362499 -0.0087873000
## p:(Intercept) -1.4161906 0.2060090 -1.8199681 -1.0124130000
## p:precip 0.3596383 0.1412744 0.0827404 0.6365363000
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6520406 0.9094293 0.9094293 0.9094293 0.9094293
## 2 0.6520406 0.9094293 0.9094293 0.9094293
## 3 0.6520406 0.9094293 0.9094293
## 4 0.6520406 0.9094293
## 5 0.6520406
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9094293 0.9094293 0.9094293 0.9094293 0.9094293
## 2 0.9094293 0.9094293 0.9094293 0.9094293
## 3 0.9094293 0.9094293 0.9094293
## 4 0.9094293 0.9094293
## 5 0.9094293
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2015507 0.2849804 0.2663158 0.2998605 0.3222028
## 2 0.2849804 0.2663158 0.2998605 0.3222028
## 3 0.2663158 0.2998605 0.3222028
## 4 0.2998605 0.3222028
## 5 0.3222028
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2015507 0.2849804 0.2663158 0.2998605 0.3222028
## 2 0.2849804 0.2663158 0.2998605 0.3222028
## 3 0.2663158 0.2998605 0.3222028
## 4 0.2998605 0.3222028
## 5 0.3222028##
## Phi.age.tail.p.precip##
## Output summary for CJS model
## Name : Phi(~age + tail)p(~precip)
##
## Npar : 5
## -2lnL: 2178.574
## AICc : 2188.631
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 0.2019063 0.5510543 -0.8781601 1.2819727
## Phi:age[1,6] 1.6796106 0.3334565 1.0260360 2.3331853
## Phi:tail 0.0213746 0.0291133 -0.0356874 0.0784366
## p:(Intercept) -1.4350950 0.2061509 -1.8391509 -1.0310392
## p:precip 0.3741405 0.1420270 0.0957675 0.6525134
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6400361 0.9050923 0.9050923 0.9050923 0.9050923
## 2 0.6400361 0.9050923 0.9050923 0.9050923
## 3 0.6400361 0.9050923 0.9050923
## 4 0.6400361 0.9050923
## 5 0.6400361
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9050923 0.9050923 0.9050923 0.9050923 0.9050923
## 2 0.9050923 0.9050923 0.9050923 0.9050923
## 3 0.9050923 0.9050923 0.9050923
## 4 0.9050923 0.9050923
## 5 0.9050923
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1987796 0.2852063 0.265796 0.3007029 0.3239994
## 2 0.2852063 0.265796 0.3007029 0.3239994
## 3 0.265796 0.3007029 0.3239994
## 4 0.3007029 0.3239994
## 5 0.3239994
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1987796 0.2852063 0.265796 0.3007029 0.3239994
## 2 0.2852063 0.265796 0.3007029 0.3239994
## 3 0.265796 0.3007029 0.3239994
## 4 0.3007029 0.3239994
## 5 0.3239994##
## Phi.age.tail.sq.p.precip##
## Output summary for CJS model
## Name : Phi(~age + tail + tail.sq)p(~precip)
##
## Npar : 6
## -2lnL: 2167.932
## AICc : 2180.012
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) -5.9658156 2.0235423 -9.9319585 -1.9996727
## Phi:age[1,6] 1.7772673 0.3501030 1.0910653 2.4634693
## Phi:tail 0.7745215 0.2456306 0.2930856 1.2559575
## Phi:tail.sq -0.0214688 0.0069674 -0.0351248 -0.0078127
## p:(Intercept) -1.4177717 0.2056497 -1.8208452 -1.0146982
## p:precip 0.3559452 0.1414734 0.0786573 0.6332330
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6401238 0.9131858 0.9131858 0.9131858 0.9131858
## 2 0.6401238 0.9131858 0.9131858 0.9131858
## 3 0.6401238 0.9131858 0.9131858
## 4 0.6401238 0.9131858
## 5 0.6401238
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9131858 0.9131858 0.9131858 0.9131858 0.9131858
## 2 0.9131858 0.9131858 0.9131858 0.9131858
## 3 0.9131858 0.9131858 0.9131858
## 4 0.9131858 0.9131858
## 5 0.9131858
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.2012311 0.2836216 0.2652002 0.2983058 0.3203521
## 2 0.2836216 0.2652002 0.2983058 0.3203521
## 3 0.2652002 0.2983058 0.3203521
## 4 0.2983058 0.3203521
## 5 0.3203521
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.2012311 0.2836216 0.2652002 0.2983058 0.3203521
## 2 0.2836216 0.2652002 0.2983058 0.3203521
## 3 0.2652002 0.2983058 0.3203521
## 4 0.2983058 0.3203521
## 5 0.3203521##
## Phi.dot.p.precip##
## Output summary for CJS model
## Name : Phi(~1)p(~precip)
##
## Npar : 3
## -2lnL: 2200.961
## AICc : 2206.983
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.8756740 0.2073306 1.4693060 2.2820419
## p:(Intercept) -1.5951476 0.2017074 -1.9904941 -1.1998011
## p:precip 0.4149045 0.1396750 0.1411415 0.6886674
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.8671134 0.8671134 0.8671134 0.8671134 0.8671134
## 2 0.8671134 0.8671134 0.8671134 0.8671134
## 3 0.8671134 0.8671134 0.8671134
## 4 0.8671134 0.8671134
## 5 0.8671134
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.8671134 0.8671134 0.8671134 0.8671134 0.8671134
## 2 0.8671134 0.8671134 0.8671134 0.8671134
## 3 0.8671134 0.8671134 0.8671134
## 4 0.8671134 0.8671134
## 5 0.8671134
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1751573 0.2645253 0.2440772 0.2809814 0.3059173
## 2 0.2645253 0.2440772 0.2809814 0.3059173
## 3 0.2440772 0.2809814 0.3059173
## 4 0.2809814 0.3059173
## 5 0.3059173
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1751573 0.2645253 0.2440772 0.2809814 0.3059173
## 2 0.2645253 0.2440772 0.2809814 0.3059173
## 3 0.2440772 0.2809814 0.3059173
## 4 0.2809814 0.3059173
## 5 0.3059173##
## Phi.age.p.time##
## Output summary for CJS model
## Name : Phi(~age)p(~-1 + time)
##
## Npar : 7
## -2lnL: 2172.442
## AICc : 2186.549
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 0.5810684 0.2077221 0.1739330 0.9882038
## Phi:age[1,6] 1.7358842 0.3495131 1.0508386 2.4209298
## p:time2 -1.5648782 0.2511311 -2.0570951 -1.0726613
## p:time3 -0.9339069 0.1602830 -1.2480617 -0.6197521
## p:time4 -1.0213624 0.1423085 -1.3002871 -0.7424376
## p:time5 -0.6450328 0.1383838 -0.9162651 -0.3738006
## p:time6 -0.9045854 0.1414412 -1.1818103 -0.6273606
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6413132 0.9102713 0.9102713 0.9102713 0.9102713
## 2 0.6413132 0.9102713 0.9102713 0.9102713
## 3 0.6413132 0.9102713 0.9102713
## 4 0.6413132 0.9102713
## 5 0.6413132
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9102713 0.9102713 0.9102713 0.9102713 0.9102713
## 2 0.9102713 0.9102713 0.9102713 0.9102713
## 3 0.9102713 0.9102713 0.9102713
## 4 0.9102713 0.9102713
## 5 0.9102713
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1729478 0.2821328 0.2647621 0.3441098 0.2881091
## 2 0.2821328 0.2647621 0.3441098 0.2881091
## 3 0.2647621 0.3441098 0.2881091
## 4 0.3441098 0.2881091
## 5 0.2881091
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1729478 0.2821328 0.2647621 0.3441098 0.2881091
## 2 0.2821328 0.2647621 0.3441098 0.2881091
## 3 0.2647621 0.3441098 0.2881091
## 4 0.3441098 0.2881091
## 5 0.2881091##
## Phi.age.birth.p.time##
## Output summary for CJS model
## Name : Phi(~age + birth)p(~-1 + time)
##
## Npar : 8
## -2lnL: 2169.773
## AICc : 2185.911
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.6803385 0.7353355 0.2390808 3.1215962
## Phi:age[1,6] 1.6569443 0.3403175 0.9899219 2.3239666
## Phi:birth -0.0471390 0.0292421 -0.1044535 0.0101755
## p:time2 -1.5607732 0.2512738 -2.0532698 -1.0682765
## p:time3 -0.9287182 0.1602301 -1.2427693 -0.6146672
## p:time4 -1.0193522 0.1419337 -1.2975422 -0.7411622
## p:time5 -0.6389728 0.1374340 -0.9083434 -0.3696022
## p:time6 -0.8979978 0.1399847 -1.1723678 -0.6236277
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6510457 0.9072561 0.9072561 0.9072561 0.9072561
## 2 0.6510457 0.9072561 0.9072561 0.9072561
## 3 0.6510457 0.9072561 0.9072561
## 4 0.6510457 0.9072561
## 5 0.6510457
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9072561 0.9072561 0.9072561 0.9072561 0.9072561
## 2 0.9072561 0.9072561 0.9072561 0.9072561
## 3 0.9072561 0.9072561 0.9072561
## 4 0.9072561 0.9072561
## 5 0.9072561
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1735357 0.2831848 0.2651536 0.3454788 0.2894621
## 2 0.2831848 0.2651536 0.3454788 0.2894621
## 3 0.2651536 0.3454788 0.2894621
## 4 0.3454788 0.2894621
## 5 0.2894621
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1735357 0.2831848 0.2651536 0.3454788 0.2894621
## 2 0.2831848 0.2651536 0.3454788 0.2894621
## 3 0.2651536 0.3454788 0.2894621
## 4 0.3454788 0.2894621
## 5 0.2894621##
## Phi.age.birth.tail.p.time##
## Output summary for CJS model
## Name : Phi(~age + birth + tail)p(~-1 + time)
##
## Npar : 9
## -2lnL: 2168.845
## AICc : 2187.017
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.2375183 0.8430454 -0.4148507 2.8898872
## Phi:age[1,6] 1.6313583 0.3303989 0.9837764 2.2789402
## Phi:birth -0.0501287 0.0292196 -0.1073992 0.0071417
## Phi:tail 0.0287647 0.0296592 -0.0293674 0.0868968
## p:time2 -1.5596560 0.2513896 -2.0523795 -1.0669325
## p:time3 -0.9258463 0.1603739 -1.2401791 -0.6115136
## p:time4 -1.0117521 0.1420098 -1.2900913 -0.7334129
## p:time5 -0.6258509 0.1374759 -0.8953037 -0.3563982
## p:time6 -0.8849180 0.1395781 -1.1584911 -0.6113450
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6494418 0.9044731 0.9044731 0.9044731 0.9044731
## 2 0.6494418 0.9044731 0.9044731 0.9044731
## 3 0.6494418 0.9044731 0.9044731
## 4 0.6494418 0.9044731
## 5 0.6494418
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9044731 0.9044731 0.9044731 0.9044731 0.9044731
## 2 0.9044731 0.9044731 0.9044731 0.9044731
## 3 0.9044731 0.9044731 0.9044731
## 4 0.9044731 0.9044731
## 5 0.9044731
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.173696 0.2837682 0.2666371 0.3484519 0.2921597
## 2 0.2837682 0.2666371 0.3484519 0.2921597
## 3 0.2666371 0.3484519 0.2921597
## 4 0.3484519 0.2921597
## 5 0.2921597
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.173696 0.2837682 0.2666371 0.3484519 0.2921597
## 2 0.2837682 0.2666371 0.3484519 0.2921597
## 3 0.2666371 0.3484519 0.2921597
## 4 0.3484519 0.2921597
## 5 0.2921597##
## Phi.age.birth.tail.sq.p.time##
## Output summary for CJS model
## Name : Phi(~age + birth + tail + tail.sq)p(~-1 + time)
##
## Npar : 10
## -2lnL: 2157.187
## AICc : 2177.398
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) -5.0927900 2.0441283 -9.0992816 -1.0862984000
## Phi:age[1,6] 1.7131736 0.3428982 1.0410930 2.3852541000
## Phi:birth -0.0587077 0.0300232 -0.1175531 0.0001377502
## Phi:tail 0.8260532 0.2494577 0.3371161 1.3149904000
## Phi:tail.sq -0.0227242 0.0070620 -0.0365657 -0.0088828000
## p:time2 -1.5479843 0.2514709 -2.0408672 -1.0551014000
## p:time3 -0.9237405 0.1602830 -1.2378952 -0.6095859000
## p:time4 -1.0146898 0.1418154 -1.2926479 -0.7367316000
## p:time5 -0.6364805 0.1367337 -0.9044785 -0.3684824000
## p:time6 -0.9013689 0.1383831 -1.1725998 -0.6301379000
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6512416 0.9119495 0.9119495 0.9119495 0.9119495
## 2 0.6512416 0.9119495 0.9119495 0.9119495
## 3 0.6512416 0.9119495 0.9119495
## 4 0.6512416 0.9119495
## 5 0.6512416
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9119495 0.9119495 0.9119495 0.9119495 0.9119495
## 2 0.9119495 0.9119495 0.9119495 0.9119495
## 3 0.9119495 0.9119495 0.9119495
## 4 0.9119495 0.9119495
## 5 0.9119495
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1753776 0.2841963 0.2660631 0.3460426 0.2887693
## 2 0.2841963 0.2660631 0.3460426 0.2887693
## 3 0.2660631 0.3460426 0.2887693
## 4 0.3460426 0.2887693
## 5 0.2887693
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1753776 0.2841963 0.2660631 0.3460426 0.2887693
## 2 0.2841963 0.2660631 0.3460426 0.2887693
## 3 0.2660631 0.3460426 0.2887693
## 4 0.3460426 0.2887693
## 5 0.2887693##
## Phi.age.tail.p.time##
## Output summary for CJS model
## Name : Phi(~age + tail)p(~-1 + time)
##
## Npar : 8
## -2lnL: 2171.878
## AICc : 2188.016
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 0.1826811 0.5545395 -0.9042164 1.2695786
## Phi:age[1,6] 1.7157495 0.3392964 1.0507285 2.3807705
## Phi:tail 0.0222556 0.0293665 -0.0353027 0.0798139
## p:time2 -1.5637197 0.2512220 -2.0561148 -1.0713247
## p:time3 -0.9310193 0.1603589 -1.2453227 -0.6167158
## p:time4 -1.0143326 0.1423370 -1.2933130 -0.7353521
## p:time5 -0.6334409 0.1383822 -0.9046700 -0.3622118
## p:time6 -0.8928490 0.1410487 -1.1693045 -0.6163935
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6391539 0.9078317 0.9078317 0.9078317 0.9078317
## 2 0.6391539 0.9078317 0.9078317 0.9078317
## 3 0.6391539 0.9078317 0.9078317
## 4 0.6391539 0.9078317
## 5 0.6391539
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.9078317 0.9078317 0.9078317 0.9078317 0.9078317
## 2 0.9078317 0.9078317 0.9078317 0.9078317
## 3 0.9078317 0.9078317 0.9078317
## 4 0.9078317 0.9078317
## 5 0.9078317
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1731135 0.282718 0.2661328 0.3467307 0.2905222
## 2 0.282718 0.2661328 0.3467307 0.2905222
## 3 0.2661328 0.3467307 0.2905222
## 4 0.3467307 0.2905222
## 5 0.2905222
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1731135 0.282718 0.2661328 0.3467307 0.2905222
## 2 0.282718 0.2661328 0.3467307 0.2905222
## 3 0.2661328 0.3467307 0.2905222
## 4 0.3467307 0.2905222
## 5 0.2905222##
## Phi.age.tail.sq.p.time##
## Output summary for CJS model
## Name : Phi(~age + tail + tail.sq)p(~-1 + time)
##
## Npar : 9
## -2lnL: 2161.168
## AICc : 2179.341
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) -6.0460045 2.0409139 -10.0461960 -2.0458132
## Phi:age[1,6] 1.8149999 0.3561472 1.1169513 2.5130485
## Phi:tail 0.7829781 0.2478430 0.2972059 1.2687504
## Phi:tail.sq -0.0216863 0.0070310 -0.0354671 -0.0079055
## p:time2 -1.5532375 0.2512630 -2.0457130 -1.0607621
## p:time3 -0.9300766 0.1602493 -1.2441652 -0.6159881
## p:time4 -1.0185860 0.1421402 -1.2971807 -0.7399913
## p:time5 -0.6458697 0.1375829 -0.9155322 -0.3762072
## p:time6 -0.9107972 0.1397270 -1.1846621 -0.6369323
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.6393695 0.9158790 0.9158790 0.9158790 0.9158790
## 2 0.6393695 0.9158790 0.9158790 0.9158790
## 3 0.6393695 0.9158790 0.9158790
## 4 0.6393695 0.9158790
## 5 0.6393695
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.915879 0.915879 0.915879 0.915879 0.915879
## 2 0.915879 0.915879 0.915879 0.915879
## 3 0.915879 0.915879 0.915879
## 4 0.915879 0.915879
## 5 0.915879
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1746192 0.2829092 0.2653029 0.3439209 0.2868367
## 2 0.2829092 0.2653029 0.3439209 0.2868367
## 3 0.2653029 0.3439209 0.2868367
## 4 0.3439209 0.2868367
## 5 0.2868367
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1746192 0.2829092 0.2653029 0.3439209 0.2868367
## 2 0.2829092 0.2653029 0.3439209 0.2868367
## 3 0.2653029 0.3439209 0.2868367
## 4 0.3439209 0.2868367
## 5 0.2868367##
## Phi.dot.p.time##
## Output summary for CJS model
## Name : Phi(~1)p(~-1 + time)
##
## Npar : 6
## -2lnL: 2195.052
## AICc : 2207.132
##
## Beta
## estimate se lcl ucl
## Phi:(Intercept) 1.8882523 0.2110171 1.474659 2.3018459
## p:time2 -1.6958572 0.2472842 -2.180534 -1.2111801
## p:time3 -1.0688695 0.1566973 -1.375996 -0.7617429
## p:time4 -1.1238157 0.1407573 -1.399700 -0.8479313
## p:time5 -0.7401474 0.1364025 -1.007496 -0.4727985
## p:time6 -0.9582791 0.1417113 -1.236033 -0.6805250
##
##
## Real Parameter Phi
## Group:agejuv
## 1 2 3 4 5
## 1 0.8685561 0.8685561 0.8685561 0.8685561 0.8685561
## 2 0.8685561 0.8685561 0.8685561 0.8685561
## 3 0.8685561 0.8685561 0.8685561
## 4 0.8685561 0.8685561
## 5 0.8685561
##
## Group:ageolder
## 1 2 3 4 5
## 1 0.8685561 0.8685561 0.8685561 0.8685561 0.8685561
## 2 0.8685561 0.8685561 0.8685561 0.8685561
## 3 0.8685561 0.8685561 0.8685561
## 4 0.8685561 0.8685561
## 5 0.8685561
##
##
## Real Parameter p
## Group:agejuv
## 2 3 4 5 6
## 1 0.1550071 0.2556181 0.2453042 0.3229719 0.2772229
## 2 0.2556181 0.2453042 0.3229719 0.2772229
## 3 0.2453042 0.3229719 0.2772229
## 4 0.3229719 0.2772229
## 5 0.2772229
##
## Group:ageolder
## 2 3 4 5 6
## 1 0.1550071 0.2556181 0.2453042 0.3229719 0.2772229
## 2 0.2556181 0.2453042 0.3229719 0.2772229
## 3 0.2453042 0.3229719 0.2772229
## 4 0.3229719 0.2772229
## 5 0.2772229sq.res## model npar AICc
## 9 Phi(~age + birth + tail + tail.sq)p(~-1 + time) 10 2177.398
## 8 Phi(~age + birth + tail + tail.sq)p(~precip) 7 2178.057
## 18 Phi(~age + tail + tail.sq)p(~-1 + time) 9 2179.341
## 17 Phi(~age + tail + tail.sq)p(~precip) 6 2180.012
## 7 Phi(~age + birth + tail + tail.sq)p(~1) 6 2182.923
## 16 Phi(~age + tail + tail.sq)p(~1) 5 2184.725
## 3 Phi(~age + birth)p(~-1 + time) 8 2185.911
## 2 Phi(~age + birth)p(~precip) 5 2186.472
## 12 Phi(~age)p(~-1 + time) 7 2186.549
## 6 Phi(~age + birth + tail)p(~-1 + time) 9 2187.017
## 11 Phi(~age)p(~precip) 4 2187.142
## 5 Phi(~age + birth + tail)p(~precip) 6 2187.612
## 15 Phi(~age + tail)p(~-1 + time) 8 2188.016
## 14 Phi(~age + tail)p(~precip) 5 2188.631
## 1 Phi(~age + birth)p(~1) 4 2191.720
## 10 Phi(~age)p(~1) 3 2192.278
## 4 Phi(~age + birth + tail)p(~1) 5 2193.147
## 13 Phi(~age + tail)p(~1) 4 2194.007
## 20 Phi(~1)p(~precip) 3 2206.983
## 21 Phi(~1)p(~-1 + time) 6 2207.132
## 19 Phi(~1)p(~1) 2 2214.503
## DeltaAICc weight Deviance
## 9 0.0000000 3.960075e-01 2157.1874
## 8 0.6584446 2.849207e-01 2163.9497
## 18 1.9422838 1.499484e-01 2161.1682
## 17 2.6137992 1.071826e-01 2167.9319
## 7 5.5247992 2.500394e-02 2170.8429
## 16 7.3269219 1.015506e-02 2174.6680
## 3 8.5127690 5.612794e-03 2169.7733
## 2 9.0734219 4.240674e-03 2176.4145
## 12 9.1508446 4.079649e-03 138.7836
## 6 9.6187838 3.228576e-03 2168.8447
## 11 9.7440015 3.032637e-03 145.4457
## 5 10.2131992 2.398476e-03 2175.5313
## 15 10.6176690 1.959322e-03 2171.8782
## 14 11.2325219 1.440762e-03 2178.5736
## 1 14.3221015 3.073963e-04 2183.6823
## 10 14.8798271 2.325894e-04 152.5968
## 4 15.7483219 1.506603e-04 2183.0894
## 13 16.6085015 9.799708e-05 2185.9687
## 20 29.5850271 1.490721e-07 167.3020
## 21 29.7338992 1.383787e-07 161.3935
## 19 37.1041877 3.472413e-09 176.8326names(sq.res)## [1] "Phi.age.birth.p.dot" "Phi.age.birth.p.precip"
## [3] "Phi.age.birth.p.time" "Phi.age.birth.tail.p.dot"
## [5] "Phi.age.birth.tail.p.precip" "Phi.age.birth.tail.p.time"
## [7] "Phi.age.birth.tail.sq.p.dot" "Phi.age.birth.tail.sq.p.precip"
## [9] "Phi.age.birth.tail.sq.p.time" "Phi.age.p.dot"
## [11] "Phi.age.p.precip" "Phi.age.p.time"
## [13] "Phi.age.tail.p.dot" "Phi.age.tail.p.precip"
## [15] "Phi.age.tail.p.time" "Phi.age.tail.sq.p.dot"
## [17] "Phi.age.tail.sq.p.precip" "Phi.age.tail.sq.p.time"
## [19] "Phi.dot.p.dot" "Phi.dot.p.precip"
## [21] "Phi.dot.p.time" "model.table"Examine Output for Models of Interest
top <- sq.res$Phi.age.birth.tail.sq.p.time
top$results$beta## estimate se lcl ucl
## Phi:(Intercept) -5.0927900 2.0441283 -9.0992816 -1.0862984000
## Phi:age[1,6] 1.7131736 0.3428982 1.0410930 2.3852541000
## Phi:birth -0.0587077 0.0300232 -0.1175531 0.0001377502
## Phi:tail 0.8260532 0.2494577 0.3371161 1.3149904000
## Phi:tail.sq -0.0227242 0.0070620 -0.0365657 -0.0088828000
## p:time2 -1.5479843 0.2514709 -2.0408672 -1.0551014000
## p:time3 -0.9237405 0.1602830 -1.2378952 -0.6095859000
## p:time4 -1.0146898 0.1418154 -1.2926479 -0.7367316000
## p:time5 -0.6364805 0.1367337 -0.9044785 -0.3684824000
## p:time6 -0.9013689 0.1383831 -1.1725998 -0.6301379000Make Predictions for \(\phi\) from Top Model
min.tail <- min(sq$tail)
max.tail <- max(sq$tail)
tail.values <- seq(from = min.tail, to = max.tail, by = 0.25)
birth.values <- c(quantile(sq$birth, 0.05),
mean(sq$birth),
quantile(sq$birth, 0.95))
pred.dat <- expand.grid(birth = birth.values,
tail = tail.values)
pred.dat$tail.sq <- pred.dat$tail^2
# make predictions for rows of 'sq.ddl' associated with juveniles,
# i.e., (par.index=1, 2) = a juvenile and an adult
pred.top <- covariate.predictions(top, data = pred.dat, indices = c(1, 2))
# view head of the prediction data.frame
head(pred.top$estimates)## vcv.index model.index par.index birth tail tail.sq estimate
## 1 1 1 1 15.50000 10 100 0.4963382
## 2 2 2 2 15.50000 10 100 0.8453422
## 3 3 1 1 22.41667 10 100 0.3963471
## 4 4 2 2 22.41667 10 100 0.7845641
## 5 5 1 1 29.50000 10 100 0.3022608
## 6 6 2 2 29.50000 10 100 0.7061210
## se lcl ucl fixed
## 1 0.10138297 0.3079901 0.6857314
## 2 0.05095075 0.7180251 0.9214611
## 3 0.08572080 0.2454666 0.5699191
## 4 0.05835719 0.6492519 0.8775227
## 5 0.08966914 0.1584377 0.4991971
## 6 0.08684269 0.5140905 0.8451242Plot phi versus tail length: make the plot
Here, you can see how to make the plot using the ‘ggplot2’ package
pred = pred.top$estimates
# use parameter index to create age_class variable
pred$age_class = ifelse(pred$par.index == 1, "juv", "older")
# Store information on birth date values
pred$birthdate = ifelse(pred$birth == mean(sq$birth), "b - bd_avg",
ifelse(pred$birth == quantile(sq$birth, 0.05), "a - bd_.05",
"c - bd_.95"))
# build and store the plot in object 'p'
ggplot(pred, aes(x = tail, y = estimate, group = age_class)) +
geom_line(aes(color = age_class), size = 1.5) +
geom_ribbon(aes(ymin = lcl, ymax = ucl), alpha = 0.2) +
xlab("Tail Length") + ylab("Apparent Survival Rate") +
ylim(0, 1) + facet_wrap( ~ birthdate) +
theme(legend.position="top")
Clean up files created
# if you're running this code, it's wise to cleanup files
# you can use the next 2 lines without comments to do that
#rm(list=ls(all=TRUE))
#cleanup(ask = FALSE)