Predict from an ordered panel model

Predict from an ordered panel model

Usage

# S3 method for class 'panordered'
predict(object, newdata = NULL, type = c("prob", "class", "link"), ...)

Arguments

object

a "panordered" fit (from panglm() with an ordered family)

newdata

optional data frame; defaults to the fitted data

type

"prob" for the matrix of category probabilities (population-averaged over the random intercept for model = "random"), "class" for the most likely category, or "link" for x'beta

...

unused

Value

a matrix with one column per category ("prob"), a factor ("class") or a numeric vector ("link")

See also

Other panglm methods: coefplot(), confint.panglm(), effectcurve(), fitted.panglm(), fixef(), glance.panglm(), logLik.panglm(), model.matrix.panglm(), partialeffects.panordered(), plot.panglm(), plot.panglm_ape(), plot.panglm_effectcurve(), predict.panglm(), residuals.panglm(), summary.panglm(), tidy.panglm(), vcov.panglm()

Examples

data(copd)
copd$lf <- cut(copd$fev1, 3, labels = c("low", "mid", "high"))
fit <- panglm(lf ~ crp + age, data = copd, index = c("id", "visit"),
              model = "pooling", family = "ologit")
head(predict(fit, type = "prob"))
#>            low       mid       high
#> [1,] 0.3622632 0.5380532 0.09968362
#> [2,] 0.2083513 0.5987692 0.19287953
#> [3,] 0.3091034 0.5676442 0.12325240
#> [4,] 0.3381230 0.5522571 0.10961992
#> [5,] 0.2869118 0.5779029 0.13518524
#> [6,] 0.2197194 0.5977054 0.18257514
predict(fit, newdata = copd[1:3, ], type = "class")
#> [1] mid mid mid
#> Levels: low mid high