```
## --- Simulated data example ---
## settings
n.used <- 1000
m <- 10
n <- n.used * m
set.seed(1234)
x <- data.frame(x1=rnorm(n), x2=runif(n))
cfs <- c(1.5,-1,0.5)
## fitting Exponential RSF model
dat1 <- simulateUsedAvail(x, cfs, n.used, m, link="log")
m1 <- rsf(status ~ .-status, dat1, m=0, B=0)
summary(m1)
## fitting Logistic RSPF model
dat2 <- simulateUsedAvail(x, cfs, n.used, m, link="logit")
m2 <- rspf(status ~ .-status, dat2, m=0, B=0)
summary(m2)
## --- Real data analysis from Lele & Keim 2006 ---
if (FALSE) {
goats$exp.HLI <- exp(goats$HLI)
goats$sin.SLOPE <- sin(pi * goats$SLOPE / 180)
goats$ELEVATION <- scale(goats$ELEVATION)
goats$ET <- scale(goats$ET)
goats$TASP <- scale(goats$TASP)
## Fit two RSPF models:
## global availability (m=0) and bootstrap (B=99)
m1 <- rspf(STATUS ~ TASP + sin.SLOPE + ELEVATION, goats, m=0, B = 99)
m2 <- rspf(STATUS ~ TASP + ELEVATION, goats, m=0, B = 99)
## Inspect the summaries
summary(m1)
summary(m2)
## Compare models: looks like m1 is better supported
CAIC(m1, m2)
## Visualize the relationships
plot(m1)
mep(m1) # marginal effects similar to plot but with CIs
kdepairs(m1) # 2D kernel density estimates
plot(m2)
kdepairs(m2)
mep(m2)
## fit and compare to null RSF model (not available for RSPF)
m3 <- rsf(STATUS ~ TASP + ELEVATION, goats, m=0, B = 0)
m4 <- rsf.null(Y=goats$STATUS, m=0)
CAIC(m3, m4)
}
```

Run the code above in your browser using DataLab