r2mlm (version 0.3.8)

r2mlm_manual: Compute R-squared values for multilevel models, manually inputting parameter estimates.

Description

r2mlm_manual takes as input raw data and parameter estimates from a multilevel model, and outputs all relevant R-squared measures from the Rights and Sterba (2019) framework of R-squared measures for multilevel models, which can be visualized together as a set using the outputted bar chart decompositions of outcome variance. That is, when predictors are cluster-mean-centered, all R-squared measures from Rights & Sterba (2019) Table 1 and decompositions from Rights & Sterba (2019) Figure 1 are outputted. When predictors are not cluster-mean-centered, the total R-squareds from Rights & Sterba (2019) Table 5, as well as bar chart decompositions are outputted. Any number of level-1 and/or level-2 predictors is supported. Any of the level-1 predictors can have random slopes.

Usage

r2mlm_manual(
  data,
  within_covs,
  between_covs,
  random_covs,
  gamma_w,
  gamma_b,
  Tau,
  sigma2,
  has_intercept = TRUE,
  clustermeancentered = TRUE,
  bargraph = TRUE
)

Value

If the input is valid, then the output will be a list and associated graphical representation of R-squared decompositions. If the input is not valid, it will return an error.

Arguments

data

Dataset with rows denoting observations and columns denoting variables.

within_covs

List of numbers corresponding to the columns in the dataset of the level-1 predictors used in the MLM (if none used, set to NULL).

between_covs

List of numbers corresponding to the columns in the dataset of the level-2 predictors used in the MLM (if none used, set to NULL).

random_covs

List of numbers corresponding to the columns in the dataset of the level-1 predictors that have random slopes in the MLM (if no random slopes, set to NULL).

gamma_w

Vector of fixed slope estimates for all level-1 predictors, to be entered in the order of the predictors listed by within_covs (if none, set to NULL).

gamma_b

Vector of fixed intercept estimate (if applicable; see has_intercept below) and fixed slope estimates for all level-2 predictors, to be entered intercept first (if applicable) followed by level-2 slopes in the order listed by between_covs (if none, set to NULL).

Tau

Random effect covariance matrix; note that the first row/column denotes the intercept variance and covariances (if intercept is fixed, set all to 0) and each subsequent row/column denotes a given random slope’s variance and covariances (to be entered in the order listed by random_covs).

sigma2

Level-1 residual variance.

has_intercept

If set to TRUE, the first element of gamma_b is assumed to be the fixed intercept estimate; if set to FALSE, the first element of gamma_b is assumed to be the first fixed level- 2 predictor slope; set to TRUE by default.

clustermeancentered

If set to TRUE, all level-1 predictors (indicated by the within_covs list) are assumed to be cluster-mean-centered and function will output all decompositions; if set to FALSE, function will output only total decompositions (see Description above); set to TRUE by default.

bargraph

Optional bar graph output, default is TRUE.

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:10.1080/00273171.2019.1660605>

Other r2mlm single model functions: r2mlm3_manual(), r2mlm_ci(), r2mlm_long_manual(), r2mlm()

Examples

# The bobyqa optimizer is required for this model to converge in lme4

model <- 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_manual(data = teachsat,
             within_covs = c(5, 4),
             between_covs = c(7, 6, 8),
             random_covs =  c(5, 4),
             gamma_w = c(0.074485, 0.310800),
             gamma_b = c(4.352652, 0.036759, 0.027532, -0.035250),
             Tau = matrix(c(0.387, 0.0000646,0.00625,
                            0.0000646, 0.00277, -0.000333,
                            0.00625, -0.000333, 0.0285), 3, 3),
             sigma2 = 0.55031,
             has_intercept = TRUE,
             clustermeancentered = TRUE)