ComputeFastSwE: ComputeFastSwE - a fast function to calculate errors via the...

In DCAN-Labs/MarginalModelCIFTI: MarginalModelCifti constructs and tests marginal models for surface and volume data.

Description

This function is used to quickly calculate error from a marginal model via a sandwich estimator. The function can handle a single block (i.e. repeated measure)

Usage

ComputeFastSwE(X, nested, Nelm, resid_map, npredictors, beta_map, adjustment)

Arguments

X	The predictor data recast as a matrix
nested	A vector denoting the blocks (i.e. groups) which are used to calculate variance separately if set to NULL will compute as if a single group
Nelm	An integer denoting the number of voxels/vertices
resid_map	The residuals from the estimated data fits, usually by lm.fit or lmfit
npredictors	The number of predictors in X
beta_map	The beta map from the estimated data fits, usually by lm.fit or lmfit
adjustment	The residuals will be adjusted according to the small sample size adjustment. Acceptable values are "HC2", "HC3", and NULL.

Examples

T_map <- ComputeFastSwE(X=external_df,nested=nested,Nelm=Nelm,resid_map=resid_map,npredictors=npredictors,beta_map=beta_map,adjustment=adjustment)

DCAN-Labs/MarginalModelCIFTI documentation built on Nov. 30, 2021, 3:40 p.m.