![]() |
|
Settings for least-squares type models
If 'y', then the input data set may be normalized or otherwise mangled
Use for the apop_iv regression, qv.
The covariance can be computationally expensive, so if this is 'n' I won't bother with it.
If 'y', fill the expected/actual/residual part of the output model.
| gsl_vector* apop_ls_settings::weights |
If this has a value, then I'll do WLS; if NULL, OLS