r2mlm3_manual: Compute R-squared values for three-level multilevel models,...

In r2mlm: R-Squared Measures for Multilevel Models

Compute R-squared values for three-level multilevel models, manually inputting parameter estimates.

Description

r2mlm3_manual takes as input raw data and three-level multilevel model (MLM) parameter estimates and outputs all relevant R-squared measures as well as an accompanying bar chart.

Usage

r2mlm3_manual(
  data,
  l1_covs,
  l2_covs,
  l3_covs,
  random_covs12,
  random_covs13,
  random_covs23,
  gamma_1,
  gamma_2,
  gamma_3,
  Tau12,
  Tau13,
  Tau23,
  sigma2,
  clustermeancentered = TRUE,
  Tau2_noncmc = NULL,
  Tau3_noncmc = NULL,
  l2clusterID_noncmc = NULL,
  l3clusterID_noncmc = NULL,
  bargraph = TRUE
)

Arguments

data	Dataset with rows denoting observations and columns denoting variables
l1_covs	Vector of numbers (or variable names) corresponding to the columns in the dataset of the level-1 predictors used in the MLM (if none used, set to NULL)
l2_covs	Vector of numbers (or variable names) corresponding to the columns in the dataset of the level-2 predictors used in the MLM (if none used, set to NULL)
l3_covs	Vector of numbers (or variable names) corresponding to the columns in the dataset of the level-3 predictors used in the MLM (if none used, set to NULL)
random_covs12	Vector of numbers (or variable names) corresponding to the columns in the dataset of the level-1 predictors that have random slopes across level-2 units in the MLM (if no such random slopes, set to NULL)
random_covs13	Vector of numbers (or variable names) corresponding to the columns in the dataset of the level-1 predictors that have random slopes across level-3 units in the MLM (if no such random slopes, set to NULL)
random_covs23	Vector of numbers (or variable names) corresponding to the columns in the dataset of the level-2 predictors that have random slopes across level-3 units in the MLM (if no such random slopes, set to NULL)
gamma_1	Vector of fixed slope estimates for all level-1 predictors, to be entered in the order of the predictors listed by l1_covs (if none, set to NULL)
gamma_2	Vector of fixed slope estimates for all level-2 predictors, to be entered in the order of the predictors listed by l2_covs (if none, set to NULL)
gamma_3	Vector of fixed slope estimates for all level-3 predictors, to be entered in the order of the predictors listed by l3_covs (if none, set to NULL)
Tau12	For cluster-mean-centered model results (set to NULL if entering non-cluster-mean-centered model results), this is the random effect covariance matrix with the first row/column denoting the intercept variance and covariances across level-2 units and each subsequent row/column denotes a given level-1 predictor’s random slope variance and covariances across level-2 units (to be entered in the order listed by random_covs12; if none, set to NULL)
Tau13	For cluster-mean-centered model results (set to NULL if entering non-cluster-mean-centered model results), this is the random effect covariance matrix with the first row/column denoting the intercept variance and covariances across level-3 units and each subsequent row/column denotes a given level-1 predictor’s random slope variance and covariances across level-3 units (to be entered in the order listed by random_covs13; if none, set to NULL)
Tau23	For cluster-mean-centered model results (set to NULL if entering non-cluster-mean-centered model results), this is the random effect covariance matrix with each row/column denoting a given level-2 predictor’s random slope variance and covariances across level-3 units (to be entered in the order listed by random_covs23; if none, set to NULL)
sigma2	Level-1 residual variance
clustermeancentered	By default, this argument is set to TRUE, indicating that cluster-mean-centered model results are being inputted. When instead entering non-cluster-mean-centered model results, set this argument to FALSE. Additionally, for non-cluster-mean-centered model results, random effect variances/covariances are to be entered in arguments Tau2_noncmc and Tau3_noncmc (defined below), rather than in the Tau12, Tau13, and Tau23 arguments used for cluster-mean-centered model results. Additionally, when entering non-cluster-mean-centered model results, user must specify l2clusterID_noncmc and l3clusterID_noncmc (neither of which are necessary for cluster-mean-centered model results). Function input is otherwise the same for cluster-mean-centered and non-cluster-mean-centered model results.
Tau2_noncmc	For non-cluster-mean-centered model results, this is the level-2 random effect covariance matrix; the first row/column denotes the intercept variance and covariances across level-2 units and each subsequent row/column denotes a given predictor’s random slope variance and covariances across level-2 units (to be entered in the order listed by randomcovsl2_noncmc; by default, this argument is set to NULL)
Tau3_noncmc	For non-cluster-mean-centered model results, this is the level-3 random effect covariance matrix; the first row/column denotes the intercept variance and covariances across level-3 units and each subsequent row/column denotes a given predictor’s random slope variance and covariances across level-3 units (to be entered in the order listed by randomcovsl2_noncmc; by default, this argument is set to NULL)
l2clusterID_noncmc	For non-cluster-mean-centered model results, this is the number (or variable name) corresponding to the column in the dataset containing the level-2 cluster identification (function assumes that each level-2 cluster ID is unique; by default, this argument is set to NULL)
l3clusterID_noncmc	For non-cluster-mean-centered model results, this is the number (or variable name) corresponding to the column in the dataset containing the level-3 cluster identification (function assumes that each level-3 cluster ID is unique; by default, this argument is set to NULL)
bargraph	Optional bar graph output, default is TRUE.

Details

This function can also accommodate two-level models. To input results for two-level models, set the following arguments equal to NULL: l3_covs, random_covs13, random_covs23, gamma_3, Tau13, Tau23.

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.

See Also

Other r2mlm single model functions: r2mlm_ci(), r2mlm_long_manual(), r2mlm_manual(), r2mlm()

r2mlm documentation built on May 29, 2024, 10:49 a.m.