Alternating least-sqaures for estimating row and column scores in constrained dual scaling, where different groups are allowed for.

1 2 |

`a` |
A |

`m` |
Integer; the number of items. |

`q` |
Integer; the rating scale from |

`G` |
An indicator matrix of size |

`Fr.cent` |
The centred F_r matrix. |

`eps` |
The numerical tolerance level for the loss. |

`maxit` |
Integer; the maximum number of iterations allowed. |

`Mmat` |
Matrix of spline basis functions. |

`info.level` |
Integer controlling the amount of information printed. |

`const` |
The constant part of the loss function. |

`K` |
The number of latent classes. |

`n` |
The number of samples. |

`tol` |
tolerance |

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.