Skip to contents

Fit one of three mixed model.

Source: R/time_model.R
time_model.Rd

Fit a mixed model regression with "cubic slope", "linear splines" or "cubic splines" as fixed and random effects.

Usage

time_model(
  x,
  y,
  cov = NULL,
  data,
  method = c("cubic_slope", "linear_splines", "cubic_splines"),
  knots = list(cubic_slope = NULL, linear_splines = c(0.75, 5.5, 11), cubic_splines =
    c(1, 8, 12))[[method]],
  use_car1 = FALSE,
  id_var = "ID",
  quiet = FALSE
)

Arguments

x

A length one character vector with the main covariate name (i.e., right-hand side).

y

A length one character vector with the variable name to be explained (i.e., left-hand side).

cov

A vector of addtional/optional covariates names to included in the fixed effect part of the linear mixed-effects models.

data

A data.frame containing the variables named in x and y.

method

The type of model, i.e., one of "cubic_slope", "linear_splines" or "cubic_splines".

knots

The knots defining the splines for "linear_splines" and "cubic_splines" methods.

use_car1

A logical indicating whether to use continuous auto-correlation, i.e., CAR(1) as correlation structure.

id_var

A string indicating the name of the variable to be used as the individual identifier.

quiet

A logical indicating whether to suppress the output.

Value

An object of class "lme" representing the linear mixed-effects model fit.

Examples

data("bmigrowth")
ls_mod <- time_model(
  x = "age",
  y = "log(bmi)",
  cov = NULL,
  data = bmigrowth[bmigrowth[["sex"]] == 0, ],
  method = "linear_splines"
)
#> nlme::lme(
#>   fixed = log(bmi) ~ gsp(age, knots = c(0.75, 5.5, 11), degree = rep(1, 4), smooth = rep(0, 3)),
#>   data = data,
#>   random = ~ gsp(age, knots = c(0.75, 5.5, 11), degree = rep(1, 4), smooth = rep(0, 3)) | ID,
#>   na.action = stats::na.omit,
#>   method = "ML",
#>   control = nlme::lmeControl(opt = "optim", maxIter = 500, msMaxIter = 500)
#> )
sres <- as.data.frame(summary(ls_mod)[["tTable"]])
rownames(sres) <- sub("gsp\\(.*\\)\\)", "gsp(...)", rownames(sres))
sres
#>                         Value   Std.Error  DF    t-value      p-value
#> (Intercept)        2.66826332 0.016046220 480 166.286095 0.000000e+00
#> gsp(...)D1(0)      0.27458917 0.024989904 480  10.988004 3.309661e-25
#> gsp(...)C(0.75).1 -0.25208766 0.025973809 480  -9.705456 1.873317e-20
#> gsp(...)C(5.5).1   0.05132095 0.007890419 480   6.504211 1.964795e-10
#> gsp(...)C(11).1   -0.02340424 0.011618719 480  -2.014356 4.452943e-02