marginal.cor: Calculate marginal correlations with response

Description Usage Arguments Value

View source: R/MarginalCor.r


Calculates marginal correlations between a functional covariate and a scalar response.


marginal.cor(object, id = NULL, response = NULL, alpha = 0.05)



An object of type funeigen or funreg. One or the other of these is needed in order to provide a smoothed reconstructed curves for the functional covariate for each subject.


The vector of subject id's. These tell which responses in response correspond to which curves in object.


The vector of responses


The alpha level for confidence intervals (one minus the two-sided coverage)


Returns a list with one component for each functional covariate. Each such component contains the between-subjects correlations between the fitted smoothed latent values of the functional covariate, and the response variable. We call this a marginal correlation because it simply ignores the other functional covariates (rather than trying to adjust or control for them). Both the functional regression coefficient and the marginal correlation can be useful, although they have different substantive interpretations.

funreg documentation built on Oct. 4, 2021, 5:07 p.m.

Related to marginal.cor in funreg...