The `matrixpls`

method for generic function `fitted`

computes the model implied
covariance matrix by combining `inner`

, `reflective`

, and `formative`

as a
simultaneous equations system. The error terms are constrained to be uncorrelated and
covariances between exogenous variables are fixed at their sample values. Defining a
composite as dependent variable in both inner and formative creates an impossible model
and results in an error.

1 2 |

`object` |
matrixpls estimation result object produced by the |

`...` |
All other arguments are ignored. |

a matrix containing the model implied covariances.

Other post-estimation functions: `ave`

,
`cr`

, `effects.matrixpls`

,
`fitSummary`

, `gof`

,
`htmt`

, `loadings`

,
`predict.matrixpls`

, `r2`

,
`residuals.matrixpls`

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.