r2mlm_ci {r2mlm}

Compute confidence intervals for R-squared in multilevel models.

Description

r2mlm_ci reads in a multilevel model (MLM) object generated using lmer or nlme along with bootstrap specifications and returns the upper and lower bounds of confidence intervals for all R-squared measures available in the r2mlm framework.

Usage

r2mlm_ci(model, nsim, boottype, confinttype, level = 0.95, progress = T)

Arguments

model

A model generated using lmer or nlme. Note that models using lmer must specify random effects at the end of the model, like so: outcome ~ 1 + fixed_effects + (random_effects | cluster_variable). Anything else (e.g., outcome ~ 1 + (random_effects | cluster_variable) + fixed_effects) will not work.

nsim

The number of bootstrapping iterations to use for the bootstrapped sampling distribution. Common values are 500 and 1000.

boottype

A character vector for the type of bootstrapping to perform. Options are parametric and residual. Parametric bootstrapping assumes normally distributed residuals, whereas residual does not.

confinttype

A character vector for the type of confidence interval to calculate. Options are norm (for normal), basic, and perc (for percentile).

level

The desired confidence level, defaults to 0.95, yielding a 95 confidence interval.

progress

TRUE/FALSE for printing progress bar or not, defaults to TRUE.

Details

Note that bootstrapping confidence intervals for many R-squared values at once is computationally intensive, and as a result runs somewhat slowly. For this reason, the progress bar displays by default.

Value

If the input is a valid model, then the output will be a list of R-squared confidence intervals for all 12 measures estimated by the r2mlm function.

See Also

Rights, J. D., & Sterba, S. K. (2019). Quantifying explained variance in multilevel models: An integrative framework for defining R-squared measures. Psychological Methods, 24(3), 309–338. <doi:10.1037/met0000184>

Other r2mlm single model functions: r2mlm3_manual(), r2mlm_long_manual(), r2mlm_manual(), r2mlm()

Examples

## Not run: 
# The "bobyqa" optimizer is required for this particular model to converge

model_lme4 <- lmer(satisfaction ~ 1 + salary_c + control_c + salary_m + control_m +
s_t_ratio + (1 + salary_c + control_c| schoolID), data = teachsat, REML =
TRUE, control = lmerControl(optimizer = "bobyqa"))

r2mlm_ci(model = model_lme4,
         nsim = 100,
         boottype = c("residual"),
         confinttype = c("perc"),
         level = 0.95,
         progress = TRUE)

## End(Not run)