construct a baseline model to model noise and other non-event-related sources of variance

Usage

baseline_model(
  basis = c("constant", "poly", "bs", "ns"),
  degree = 1,
  sframe,
  intercept = c("runwise", "global", "none"),
  nuisance_list = NULL
)

Arguments

basis: the basis function type
degree: the degree of the spline function.
sframe: sframe a sampling_frame object
intercept: whether to include an intercept for each block. Automatically set to FALSE when basis == "constant".
nuisance_list: a list of nuisance matrices, one matrix per fMRI block

Examples


## bspline basis with degree = 3. This will produce a design matrix with three 
## splines regressor and a constant intercept.
sframe <- sampling_frame(blocklens=c(100,100), TR=2)
bmod <- baseline_model(basis="bs", degree=3, sframe=sframe)
bmod_global <- baseline_model(basis="bs", degree=3, 
sframe=sframe, intercept="global")

bmod_nointercept <- baseline_model(basis="bs", degree=3, 
sframe=sframe, intercept="none")

stopifnot(ncol(design_matrix(bmod)) == 8)
stopifnot(ncol(design_matrix(bmod_global)) == 7)
stopifnot(ncol(design_matrix(bmod_nointercept)) == 6)

## polynomial with no intercept term
bmod <- baseline_model(basis="poly", degree=3, sframe=sframe, intercept="none")

## a baseline model that only has dummy-coded intercept terms, one per block, 
## i.e. to model runwise mean shifts only.

bmod <- baseline_model(basis="constant", degree=1, sframe=sframe)

## global intercept only
bmod <- baseline_model(basis="constant", degree=1, sframe=sframe, intercept="global")


## add an arbitrary nuisance matrix with two columns, i.e. motion regressors, 
## physiological noise, etc.

nuismat <- matrix(rnorm(100*2), 100, 2)
bmod <- baseline_model(basis="bs", degree=3, sframe=sframe, 
nuisance_list=list(nuismat, nuismat))
stopifnot(ncol(design_matrix(bmod)) == 12)