View source: R/design.experiment.r
design.experiment | R Documentation |
Design an experiment
design.experiment(
list.IV,
type.IV,
formula,
calculate.coef.num = F,
seed = NA,
beta.min = 0,
beta.max = 20,
betas = NA,
theta.min = 0,
theta.max = 8,
thetas = NA,
thetas.orthogonal = T,
s.min = 0,
s.max = 20,
s = NA
)
list.IV |
a list of the independent variables with their relative values |
type.IV |
a vector specifying whether each IV is within ("w") or between ("b") |
formula |
a string describing the linear model to be simulated, of the type ~ F1 + (F2*F3) |
calculate.coef.num |
logical, if TRUE the function just calculates the number of coefficients corresponding to the variables listed |
seed |
optional, a seed to apply to the simulation (for reproducibility) |
beta.min |
lower boundary of the uniform distribution from which the values/means of the betas are extracted (if betas = NA) |
beta.max |
upper boundary of the uniform distribution from which the values/means of the betas are extracted (if betas = NA) |
betas |
this parameters allows to assign a specific mean/value to each parameter of the model. The length of betas must be equal to the amount of coefficients in the model specified by the formula. |
theta.min |
lower boundary of the uniform distribution from which the standard deviation of the betas are extracted (if thetas = NA) |
theta.max |
upper boundary of the uniform distribution from which the standard deviation of the betas are extracted (if thetas = NA) |
thetas |
this parameters allows to assign a specific standard deviation to each parameter of the model. The length of thetas must be equal to the amount of coefficients in the model specified by the formula. |
thetas.orthogonal |
logical, are the parameters orthogonal? |
s.min |
lower boundary of the uniform distribution from which the standard deviation of the model's residuals is extracted (if s = NA) |
s.max |
upper boundary of the uniform distribution from which the standard deviation of the model's residuals is extracted (if s = NA) |
s |
this parameters allows to assign a specific standard deviation to the model's residuals |
An object of the class mu.exp.design to be used with the function sample.experiment with the following values
seed the seed that will be used for simulation
ncoef the number of coefficients of the model
beta.matrix coefficients matrix
theta.matrix random components matrix
corr.matrix random components correlation matrix
sigma the model residuals standard deviation
IV list of the parameters of the model (basically returns list.IV)
type_IV returns type.IV
formula returns the formula
libraries()
# set a seed
trial.seed <- 9000
# initialize the factors list
lIV <- list(
Var1 = factor(1:2, labels = c("a","b"))
,
Var2 = factor(1:2)
)
tIV <- c("w","b")
# describe the model
exp.formula <- ~ Var1*Var2
# initialize the coefficients
cus.beta <- c(1, 4, 5, 1)*3 # means of the fixed effects
cus.theta <- c(1, 4, 5, 1) # standard errors of the random components
cus.sigma <- 3 # sigma of the model
# few examples
(r1 <- design.experiment(lIV, tIV, exp.formula, seed=trial.seed))
(r2 <- design.experiment(lIV, tIV, exp.formula, seed=trial.seed, thetas.orthogonal=F))
(r3 <- design.experiment(lIV, tIV, exp.formula, seed=trial.seed, beta.min=-5, beta.max=10, theta.min=0, theta.max=10, s.min=5, s.max=12))
(r4 <- design.experiment(lIV, tIV, exp.formula, seed=trial.seed, betas=cus.beta, thetas=cus.theta, s=cus.sigma, thetas.orthogonal=F))
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.