Specify a monotonic predictor term in brms. The function does not evaluate its arguments -- it exists purely to help set up a model.

mo(x, id = NA)

Arguments

x

An integer variable or an ordered factor to be modeled as monotonic.

id

Optional character string. All monotonic terms with the same id within one formula will be modeled as having the same simplex (shape) parameter vector. If all monotonic terms of the same predictor have the same id, the resulting predictions will be conditionally monotonic for all values of interacting covariates (Bürkner & Charpentier, 2020).

Details

See Bürkner and Charpentier (2020) for the underlying theory. For detailed documentation of the formula syntax used for monotonic terms, see help(brmsformula) as well as vignette("brms_monotonic").

References

Bürkner P. C. & Charpentier E. (2020). Modeling Monotonic Effects of Ordinal Predictors in Regression Models. British Journal of Mathematical and Statistical Psychology. doi:10.1111/bmsp.12195

See also

Examples

if (FALSE) {
# generate some data
income_options <- c("below_20", "20_to_40", "40_to_100", "greater_100")
income <- factor(sample(income_options, 100, TRUE),
                 levels = income_options, ordered = TRUE)
mean_ls <- c(30, 60, 70, 75)
ls <- mean_ls[income] + rnorm(100, sd = 7)
dat <- data.frame(income, ls)

# fit a simple monotonic model
fit1 <- brm(ls ~ mo(income), data = dat)
summary(fit1)
plot(fit1, N = 6)
plot(conditional_effects(fit1), points = TRUE)

# model interaction with other variables
dat$x <- sample(c("a", "b", "c"), 100, TRUE)
fit2 <- brm(ls ~ mo(income)*x, data = dat)
summary(fit2)
plot(conditional_effects(fit2), points = TRUE)

# ensure conditional monotonicity
fit3 <- brm(ls ~ mo(income, id = "i")*x, data = dat)
summary(fit3)
plot(conditional_effects(fit3), points = TRUE)
}