Use mdes.bira2r1() to calculate the minimum detectable effect size, power.bira2r1() to calculate the statistical power, and mrss.bira2r1() to calculate the minimum required sample size.
mdes.bira2r1(power=.80, alpha=.05, two.tailed=TRUE,
rho2, omega2, p=.50, g2=0, r21=0, r2t2=0,
n, J)power.bira2r1(es=.25, alpha=.05, two.tailed=TRUE,
rho2, omega2, g2=0, p=.50, r21=0, r2t2=0,
n, J)
mrss.bira2r1(es=.25, power=.80, alpha=.05, two.tailed=TRUE,
n, J0=10, tol=.10,
rho2, omega2, g2=0, p=.50, r21=0, r2t2=0)
statistical power
effect size.
probability of type I error.
logical; TRUE for two-tailed hypothesis testing, FALSE for one-tailed hypothesis testing.
proportion of variance in the outcome between level 2 units (unconditional ICC2).
treatment effect heterogeneity as ratio of treatment effect variance among level 2 units to the residual variance at level 2.
average proportion of level 1 units randomly assigned to treatment within level 2 units.
number of covariates at level 2.
proportion of level 1 variance in the outcome explained by level 1 covariates.
proportion of treatment effect variance among level 2 units explained by level 2 covariates.
harmonic mean of level 1 units across level 2 units (or simple average).
level 2 sample size.
starting value for J.
tolerance to end iterative process for finding J.
function name.
list of parameters used in power calculation.
degrees of freedom.
noncentrality parameter.
statistical power
minimum detectable effect size.
number of level 2 units.
# NOT RUN {
# cross-checks
mdes.bira2r1(rho2=.17, omega2=.50, n=15, J=20)
power.bira2r1(es=.366, rho2=.17, omega2=.50, n=15, J=20)
mrss.bira2r1(es=.366, rho2=.17, omega2=.50, n=15)
# }
Run the code above in your browser using DataLab