hopit (version 0.11.6)

profile.hopit: Calculate the log likelihood profile for the fitted hopit model

Description

Calculate the log likelihood profile for the fitted hopit model

Usage

# S3 method for hopit
profile(fitted, ..., scope = 0.15, steps = 101)

Arguments

fitted

a hopit object (a fitted model).

...

unused now.

scope

a value (fraction) defining the plotting range for a coefficient. The range is c(coef \* (1-scope), coef \* (1+scope)).

steps

at how many equally spaced points the log likelihood function is calculated for each coefficient.

Author

Maciej J. Danko

See Also

plot.profile.hopit, print.profile.hopit, hopit

Examples

# \donttest{
# DATA
data(healthsurvey)

# the order of response levels decreases from the best health to
# the worst health; hence the hopit() parameter decreasing.levels
# is set to TRUE
levels(healthsurvey$health)

# Example 1 ---------------------

# fitting the model:
model1 <- hopit(latent.formula = health ~ hypertension + high_cholesterol +
                heart_attack_or_stroke + poor_mobility + very_poor_grip +
                depression + respiratory_problems +
                IADL_problems + obese + diabetes + other_diseases,
              thresh.formula = ~ sex + ageclass + country,
              decreasing.levels = TRUE,
              control = list(trace = FALSE),
              data = healthsurvey)

# check the fit using the profile function (at 51 points)
pr <- profile(model1, steps = 51)
print(pr, plotf = FALSE)

# plot profile
plot(pr, relative = FALSE)

# alternative plot
plot(pr, relative = TRUE)
# }