innerEstim: PLS inner estimation

In matrixpls: Matrix-Based Partial Least Squares Estimation

Description

Calculates a set of inner weights.

Usage

innerEstim.centroid(S, W, inner.mod, ignoreInnerModel = FALSE, ...)

innerEstim.path(S, W, inner.mod, ...)

innerEstim.factor(S, W, inner.mod, ignoreInnerModel = FALSE, ...)

innerEstim.identity(S, W, inner.mod, ...)

innerEstim.gsca(S, W, inner.mod, ...)

Arguments

S	Covariance matrix of the data.
W	Weight matrix, where the indicators are on colums and composites are on the rows.
inner.mod	A square matrix specifying the relationships of the composites in the model.
ignoreInnerModel	Should the inner model be ignored and all correlations be used.
...	Other arguments are ignored.

Details

In the centroid scheme, inner weights are set to the signs (1 or -1) of correlations between composites that are connected in the model specified in inner.mod and zero otherwise.

In the path scheme, inner weights are based on regression estimates of the relationships between composites that are connected in the model specified in inner.mod, and correlations for the inverse relationships. If a relationship is reciprocal, regression is used for both directions.

In the factor scheme, inner weights are set to the correlations between composites that are connected in the model specified in inner.mod and zero otherwise.

In the identity scheme identity matrix is used as the inner weight matrix E.

Centroid, inner, and path schemes fall back to to identity scheme for composites that are not connected to any other composites.

For information about GSCA weights, see GSCA.

Value

A matrix of unscaled inner weights E with the same dimensions as inner.mod.

Functions

• innerEstim.centroid: inner estimation with centroid scheme.

• innerEstim.path: inner estimation with path scheme.

• innerEstim.factor: inner estimation with factor scheme.

• innerEstim.identity: inner estimation with identity scheme.

• innerEstim.gsca: inner estimation with generalized structured component analysis.

References

Lohmöller J.-B. (1989) Latent variable path modeling with partial least squares. Heidelberg: Physica-Verlag.

matrixpls documentation built on April 28, 2021, 5:07 p.m.