PAMM: Simulation function to assess power of mixed models

In pamm: Power Analysis for Random Effects in Mixed Models

Simulation function to assess power of mixed models

Description

Given a specific varaince-covariance structure for random effect, the function simulate different group size and assess p-values and power of random intercept and random slope

Usage

PAMM(
  numsim,
  group,
  repl,
  randompart,
  fixed = c(0, 1, 0),
  n.X = NA,
  autocorr.X = 0,
  X.dist = "gaussian",
  intercept = 0,
  heteroscedasticity = c("null"),
  ftype = "lmer",
  mer.sim = FALSE
)

Arguments

numsim	number of simulation for each step
group	number of group. Could be specified as a vector
repl	number of replicates per group . Could be specified as a vector
randompart	vector of lenght 4 or 5, with 1: variance component of intercept, VI; 2: variance component of slope, VS; 3: residual variance, VR; 4: relation between random intercept and random slope; 5: "cor" or "cov" determine if the relation 4 between I ans S is a correlation or a covariance. Default: "cor"
fixed	vector with mean, variance and estimate of fixed effect to simulate. Default: c(0, 1, 0)
n.X	number of different values to simulate for the fixed effect (covariate). If NA, all values of X are independent between groups. If the value specified is equivalent to the number of replicates per group, repl, then all groups are observed for the same values of the covariate. Default: NA
autocorr.X	correlation between two successive covariate value for a group. Default: 0
X.dist	specify the distribution of the fixed effect. Only "gaussian" (normal distribution) and "unif" (uniform distribution) are accepted actually. Default: "gaussian"
intercept	a numeric value giving the expected intercept value. Default:0
heteroscedasticity	a vector specifying heterogeneity in residual variance across X. If c("null") residual variance is homogeneous across X. If c("power",t1,t2) models heterogeneity with a constant plus power variance function. Letting v denote the variance covariate and \sigma^2(v) denote the variance function evaluated at v, the constant plus power variance function is defined as \sigma^2(v) = (\theta_1 + |v|^{\theta_2})^2, where \theta_1,\theta_2 are the variance function coefficients. If c("exp",t),models heterogeneity with an exponential variance function. Letting v denote the variance covariate and \sigma^2(v) denote the variance function evaluated at v, the exponential variance function is defined as \sigma^2(v) = e^{2 * \theta * v}, where \theta is the variance function coefficient.
ftype	character value "lmer", "lme" or "MCMCglmm" specifying the function to use to fit the model. Actually "lmer" only is accepted
mer.sim	simulate the data using simulate.merMod from lme4. Faster for large sample size but not as flexible.

Details

P-values for random effects are estimated using a log-likelihood ratio test between two models with and without the effect. Power represent the percentage of simulations providing a significant p-value for a given random structure

Value

data frame reporting estimated P-values and power with CI for random intercept and random slope

\@seealso [EAMM()], [SSF()], [plot.PAMM()]

Examples

## Not run: 
ours <- PAMM(numsim = 10, group = c(seq(10, 50, 10), 100),
             repl = c(3, 4, 6),
             randompart = c(0.4, 0.1, 0.5, 0.1), fixed = c(0, 1, 0.7))
plot(ours,"both")
   
## End(Not run)

pamm documentation built on Aug. 29, 2023, 1:10 a.m.